QuadTree Attention for Vision Transformers (ICLR2022)

Overview

This repository contains codes for quadtree attention. This repo contains codes for feature matching, image classficiation, object detection and semantic segmentation.

Installation

  1. Compile the quadtree attention operation cd QuadTreeAttention&&python setup.py install
  2. Install the package for each task according to each README.md in the separate directory.

Model Zoo and Baselines

We provide baselines results and model zoo in the following.

Feature matching

  • Quadtree on Feature matching
Method [email protected] [email protected] [email protected] Model
ScanNet 24.9 44.7 61.8 [Google]/[GitHub]
Megadepth 53.5 70.2 82.2 [Google]/[GitHub]

Image classification

  • Quadtree on ImageNet-1K
Method Flops [email protected] Model
Quadtree-B-b0 0.6 72.0 [Google]/[GitHub]
Quadtree-B-b1 2.3 80.0 [Google]/[GitHub]
Quadtree-B-b2 4.5 82.7 [Google]/[GitHub]
Quadtree-B-b3 7.8 83.8 [Google]/[GitHub]
Quadtree-B-b4 11.5 84.0 [Google]/[GitHub]

Object detection and instance segmentation

  • Quadtree on COCO

Baseline Detectors

Method Backbone Pretrain Lr schd Aug Box AP Mask AP Model
RetinaNet Quadtree-B-b0 ImageNet-1K 1x No 38.4 - [Google]/[GitHub]
RetinaNet Quadtree-B-b1 ImageNet-1K 1x No 42.6 - [Google]/[GitHub]
RetinaNet Quadtree-B-b2 ImageNet-1K 1x No 46.2 - [Google]/[GitHub]
RetinaNet Quadtree-B-b3 ImageNet-1K 1x No 47.3 - [Google]/[GitHub]
RetinaNet Quadtree-B-b4 ImageNet-1K 1x No 47.9 - [Google]/[GitHub]
Mask R-CNN Quadtree-B-b0 ImageNet-1K 1x No 38.8 36.5 [Google]/[GitHub]
Mask R-CNN Quadtree-B-b1 ImageNet-1K 1x No 43.5 40.1 [Google]/[GitHub]
Mask R-CNN Quadtree-B-b2 ImageNet-1K 1x No 46.7 42.4 [Google]/[GitHub]
Mask R-CNN Quadtree-B-b3 ImageNet-1K 1x No 48.3 43.3 [Google]/[GitHub]
Mask R-CNN Quadtree-B-b4 ImageNet-1K 1x No 48.6 43.6 [Google]/[GitHub]

Semantic Segmentation

  • Quadtree on ADE20K
Method Backbone Pretrain Iters mIoU Model
Semantic FPN Quadtree-b0 ImageNet-1K 160K 39.9 [Google]/[GitHub]
Semantic FPN Quadtree-b1 ImageNet-1K 160K 44.7 [Google]/[GitHub]
Semantic FPN Quadtree-b2 ImageNet-1K 160K 48.7 [Google]/[GitHub]
Semantic FPN Quadtree-b3 ImageNet-1K 160K 50.0 [Google]/[GitHub]
Semantic FPN Quadtree-b4 ImageNet-1K 160K 50.6 [Google]/[GitHub]

Citation

@article{tang2022quadtree,
  title={QuadTree Attention for Vision Transformers},
  author={Tang, Shitao and Zhang, Jiahui and Zhu, Siyu and Tan, Ping},
  journal={ICLR},
  year={2022}
}
Comments
  • Run QuadTreeAttention on CPU

    Run QuadTreeAttention on CPU

    Hi,

    Thank for your work. We are getting very interesting feature matching results in our tests.

    Now we would like the algorithm running on cpu. We made some changes (over torch) in order to run on cpu, but we are getting below error. Is there a score_computation function implemented to run in cpu?

    File "../../QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/functions/quadtree_attention.py", line 11, in forward x = score_computation_cuda.score_forward(query, key, index)

    opened by hmarichalds 6
  • Image resolution for outdoor feature matching

    Image resolution for outdoor feature matching

    Hello @Tangshitao , Thanks for providing excellent work on QuadTreeAttention.

    I want to point out the 2 bugs in FeatureMatching/notebooks/demo_single_pair.ipynb .

    1. The first bug is while loading the default config of KeyError of block_type, which I have corrected by appending configs from training setup into the cvpr_ds_config.py. I have added following lines in cvpr_ds_config.py:
    # 5. Quadtree
    _CN.COARSE.BLOCK_TYPE = 'quadtree'  
    _CN.COARSE.ATTN_TYPE = 'B'  
    _CN.COARSE.TOPKS=[32, 16, 16]  
    _CN.FINE.BLOCK_TYPE = 'loftr'  
    
    1. The second bug I am facing while inferring outdoor weights during resizing operation at the following line:
      img0_raw = cv2.resize(img0_raw, (img0_raw.shape[1]//8*8, img0_raw.shape[0]//8*8)) # input size should be divisible by 8
      This creates an issue down the line in the quadtree attention block while reshaping due to size mismatch. I have resolved the issue by resizing the image to (640, 480) and it is working fine:
      img0_raw = cv2.resize(img0_raw, (480, 640))
      But I believe during the training on Megadeth images, you have kept the higher side to be 832 while being divisible by 8. But during inference, that same process is not working as it working in the original LoFTR notebook.

    TLDR: Could you remove the bugs in demo_single_pair.ipynb in the default config and the resizing operation in outdoor weights?

    opened by UditSinghParihar 5
  • Support for CUDA version 11.x

    Support for CUDA version 11.x

    I appreciate your great work and thank you for releasing it as opensource.

    I guess the current compiling option with setup.py only works with CUDA version 10.2. Are you guys planning to support CUDA 11.x as well? Some gpus like rtx 30 series do not support CUDA 10.x, which is quite annoying..

    Thank you for your attention :)

    opened by HJoonKwon 2
  • For FeatureMatching, the QuadTreeAttention-based LoFTR is slower than the original LoFTR

    For FeatureMatching, the QuadTreeAttention-based LoFTR is slower than the original LoFTR

    Hi, I find this paper very inspiring and interesting. Really appreciate the code and paper.

    After testing the code on the Feature Matching task, I find it achieves better performance than the original LoFTR. But it runs a bit slower than the original LoFTR. For example, on my machine, for the same input pair of images, it runs ~0.380 s, while the original LoFTR runs ~0.27 s.

    I am wondering if this is expected, or is it possibly due to my improper compilation of the QuadTreeAttention, or for some other reasons?

    Thanks a lot for your help.

    opened by KaneKun 1
  • Running scripts for reproducing causes Segmentation Fault

    Running scripts for reproducing causes Segmentation Fault

    I already have LoFTR setup and on running the scripts for reproducing outdoor results I immedeately get a seg fault. I have compiled the required operations as mentioned in the readme, and the setup seemed to have gone smoothly without any errors. Would appreciate any help regarding this!

    Output of python setup.py install -

    running install
    running bdist_egg
    running egg_info
    writing quadtree_attention_package.egg-info/PKG-INFO
    writing dependency_links to quadtree_attention_package.egg-info/dependency_links.txt
    writing top-level names to quadtree_attention_package.egg-info/top_level.txt
    reading manifest file 'quadtree_attention_package.egg-info/SOURCES.txt'
    writing manifest file 'quadtree_attention_package.egg-info/SOURCES.txt'
    installing library code to build/bdist.linux-x86_64/egg
    running install_lib
    running build_ext
    building 'score_computation_cuda' extension
    Emitting ninja build file /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/build.ninja...
    Compiling objects...
    Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
    /anaconda/envs/loftr/lib/python3.8/site-packages/setuptools/command/install.py:34: SetuptoolsDeprecationWarning: setup.py install is deprecated. Use build and pip and other standards-based tools.
      warnings.warn(
    /anaconda/envs/loftr/lib/python3.8/site-packages/setuptools/command/easy_install.py:144: EasyInstallDeprecationWarning: easy_install command is deprecated. Use build and pip and other standards-based tools.
      warnings.warn(
    [1/2] c++ -MMD -MF /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/score_computation.o.d -pthread -B /anaconda/envs/loftr/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -fwrapv -O2 -Wall -fPIC -O2 -isystem /anaconda/envs/loftr/include -fPIC -O2 -isystem /anaconda/envs/loftr/include -fPIC -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/TH -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/anaconda/envs/loftr/include/python3.8 -c -c /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp -o /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/score_computation.o -g -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=score_computation_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Parallel.h:140:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:13,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ParallelOpenMP.h:83:0: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
     #pragma omp parallel for if ((end - begin) >= grain_size)
     
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp: In function ‘std::vector<at::Tensor> score_cuda_forward(at::Tensor, at::Tensor, at::Tensor)’:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:8:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:15:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(input1);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:8:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(input2);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:8:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:17:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(index);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp: In function ‘std::vector<at::Tensor> score_cuda_backward(at::Tensor, at::Tensor, at::Tensor, at::Tensor)’:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:8:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:27:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(grad_output1);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:8:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:28:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(input1);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:8:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:29:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(input2);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:6:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:8:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:30:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(index);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.h:3,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    [2/2] /usr/local/cuda/bin/nvcc --generate-dependencies-with-compile --dependency-output /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/score_computation_kernal.o.d -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/TH -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/anaconda/envs/loftr/include/python3.8 -c -c /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation_kernal.cu -o /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/score_computation_kernal.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O2 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=score_computation_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -std=c++14
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation_kernal.cu: In lambda function:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation_kernal.cu:83:43: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
         AT_DISPATCH_FLOATING_TYPES(query.type(), "ScoreData_ongpu", ([&] {
                                               ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:1: note: declared here
       DeprecatedTypeProperties & type() const {
     ^ ~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation_kernal.cu:83:98: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [-Wdeprecated-declarations]
         AT_DISPATCH_FLOATING_TYPES(query.type(), "ScoreData_ongpu", ([&] {
                                                                                                      ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Dispatch.h:109:1: note: declared here
     inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties& t) {
     ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation_kernal.cu: In lambda function:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation_kernal.cu:171:41: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
         AT_DISPATCH_FLOATING_TYPES(key.type(), "ScoreDatabackward_ongpu", ([&] {
                                             ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:1: note: declared here
       DeprecatedTypeProperties & type() const {
     ^ ~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/score_computation_kernal.cu:171:96: warning: ‘c10::ScalarType detail::scalar_type(const at::DeprecatedTypeProperties&)’ is deprecated: passing at::DeprecatedTypeProperties to an AT_DISPATCH macro is deprecated, pass an at::ScalarType instead [-Wdeprecated-declarations]
         AT_DISPATCH_FLOATING_TYPES(key.type(), "ScoreDatabackward_ongpu", ([&] {
                                                                                                    ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Dispatch.h:109:1: note: declared here
     inline at::ScalarType scalar_type(const at::DeprecatedTypeProperties& t) {
     ^~~~~~~~~~~
    g++ -pthread -B /anaconda/envs/loftr/compiler_compat -shared -Wl,--allow-shlib-undefined -Wl,-rpath,/anaconda/envs/loftr/lib -Wl,-rpath-link,/anaconda/envs/loftr/lib -L/anaconda/envs/loftr/lib -Wl,--allow-shlib-undefined -Wl,-rpath,/anaconda/envs/loftr/lib -Wl,-rpath-link,/anaconda/envs/loftr/lib -L/anaconda/envs/loftr/lib /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/score_computation.o /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/score_computation_kernal.o -L/anaconda/envs/loftr/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.8/score_computation_cuda.cpython-38-x86_64-linux-gnu.so
    building 'value_aggregation_cuda' extension
    Emitting ninja build file /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/build.ninja...
    Compiling objects...
    Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
    [1/2] c++ -MMD -MF /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/value_aggregation.o.d -pthread -B /anaconda/envs/loftr/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -fwrapv -O2 -Wall -fPIC -O2 -isystem /anaconda/envs/loftr/include -fPIC -O2 -isystem /anaconda/envs/loftr/include -fPIC -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/TH -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/anaconda/envs/loftr/include/python3.8 -c -c /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp -o /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/value_aggregation.o -g -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=value_aggregation_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Parallel.h:140:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:13,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ParallelOpenMP.h:83:0: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
     #pragma omp parallel for if ((end - begin) >= grain_size)
     
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp: In function ‘void value_aggregation_cuda_forward(at::Tensor, at::Tensor, at::Tensor, at::Tensor)’:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:7:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:15:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(score);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:7:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:16:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(value);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:7:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:17:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(index);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:28:56: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
         value_aggregation_forward_kernel(score.data<float>(), value.data<float>(),
                                                            ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:28:77: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
         value_aggregation_forward_kernel(score.data<float>(), value.data<float>(),
                                                                                 ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:29:26: warning: ‘T* at::Tensor::data() const [with T = long int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
             index.data<long>(), output.data<float>(), B, N, K, H, M, D,
                              ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:29:48: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
             index.data<long>(), output.data<float>(), B, N, K, H, M, D,
                                                    ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp: In function ‘void value_aggregation_cuda_backward(at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor, at::Tensor)’:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:7:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:42:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(score);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:7:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:43:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(value);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:7:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:44:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(index);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/DeviceType.h:8:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Device.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/core/Allocator.h:6,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:42: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                                              ^
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:173:65: note: in definition of macro ‘C10_UNLIKELY’
     #define C10_UNLIKELY(expr)  (__builtin_expect(static_cast<bool>(expr), 0))
                                                                     ^~~~
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:362:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’
       if (C10_UNLIKELY_OR_CONST(!(cond))) {                                 \
           ^~~~~~~~~~~~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:5:23: note: in expansion of macro ‘TORCH_CHECK’
     #define CHECK_CUDA(x) TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor")
                           ^~~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:7:24: note: in expansion of macro ‘CHECK_CUDA’
     #define CHECK_INPUT(x) CHECK_CUDA(x); CHECK_CONTIGUOUS(x)
                            ^~~~~~~~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:45:5: note: in expansion of macro ‘CHECK_INPUT’
         CHECK_INPUT(grad_output);
         ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:303:30: note: declared here
       DeprecatedTypeProperties & type() const {
                                  ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:57:63: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
         value_aggregation_backward_kernel(grad_output.data<float>(), score.data<float>(),
                                                                   ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:57:84: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
         value_aggregation_backward_kernel(grad_output.data<float>(), score.data<float>(),
                                                                                        ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:58:27: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
             value.data<float>(), index.data<long>(), grad_score.data<float>(), grad_value.data<float>(),
                               ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:58:47: warning: ‘T* at::Tensor::data() const [with T = long int]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
             value.data<float>(), index.data<long>(), grad_score.data<float>(), grad_value.data<float>(),
                                                   ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:58:73: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
             value.data<float>(), index.data<long>(), grad_score.data<float>(), grad_value.data<float>(),
                                                                             ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:58:99: warning: ‘T* at::Tensor::data() const [with T = float]’ is deprecated: Tensor.data<T>() is deprecated. Please use Tensor.data_ptr<T>() instead. [-Wdeprecated-declarations]
             value.data<float>(), index.data<long>(), grad_score.data<float>(), grad_value.data<float>(),
                                                                                                       ^
    In file included from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Tensor.h:3:0,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/Context.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include/torch/all.h:8,
                     from /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/extension.h:4,
                     from /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation.cpp:1:
    /anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:398:7: note: declared here
       T * data() const {
           ^~~~
    [2/2] /usr/local/cuda/bin/nvcc --generate-dependencies-with-compile --dependency-output /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/value_aggregation_kernel.o.d -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/TH -I/anaconda/envs/loftr/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda/include -I/anaconda/envs/loftr/include/python3.8 -c -c /repos/repos/QuadTreeAttention/QuadTreeAttention/QuadtreeAttention/src/value_aggregation_kernel.cu -o /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/value_aggregation_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -O2 -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=value_aggregation_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_70,code=compute_70 -gencode=arch=compute_70,code=sm_70 -std=c++14
    g++ -pthread -B /anaconda/envs/loftr/compiler_compat -shared -Wl,--allow-shlib-undefined -Wl,-rpath,/anaconda/envs/loftr/lib -Wl,-rpath-link,/anaconda/envs/loftr/lib -L/anaconda/envs/loftr/lib -Wl,--allow-shlib-undefined -Wl,-rpath,/anaconda/envs/loftr/lib -Wl,-rpath-link,/anaconda/envs/loftr/lib -L/anaconda/envs/loftr/lib /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/value_aggregation.o /repos/repos/QuadTreeAttention/QuadTreeAttention/build/temp.linux-x86_64-3.8/QuadtreeAttention/src/value_aggregation_kernel.o -L/anaconda/envs/loftr/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.8/value_aggregation_cuda.cpython-38-x86_64-linux-gnu.so
    creating build/bdist.linux-x86_64/egg
    copying build/lib.linux-x86_64-3.8/score_computation_cuda.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg
    copying build/lib.linux-x86_64-3.8/value_aggregation_cuda.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg
    creating stub loader for score_computation_cuda.cpython-38-x86_64-linux-gnu.so
    creating stub loader for value_aggregation_cuda.cpython-38-x86_64-linux-gnu.so
    byte-compiling build/bdist.linux-x86_64/egg/score_computation_cuda.py to score_computation_cuda.cpython-38.pyc
    byte-compiling build/bdist.linux-x86_64/egg/value_aggregation_cuda.py to value_aggregation_cuda.cpython-38.pyc
    creating build/bdist.linux-x86_64/egg/EGG-INFO
    copying quadtree_attention_package.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO
    copying quadtree_attention_package.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
    copying quadtree_attention_package.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
    copying quadtree_attention_package.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO
    writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt
    zip_safe flag not set; analyzing archive contents...
    __pycache__.score_computation_cuda.cpython-38: module references __file__
    __pycache__.value_aggregation_cuda.cpython-38: module references __file__
    creating 'dist/quadtree_attention_package-0.0.0-py3.8-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it
    removing 'build/bdist.linux-x86_64/egg' (and everything under it)
    Processing quadtree_attention_package-0.0.0-py3.8-linux-x86_64.egg
    creating /anaconda/envs/loftr/lib/python3.8/site-packages/quadtree_attention_package-0.0.0-py3.8-linux-x86_64.egg
    Extracting quadtree_attention_package-0.0.0-py3.8-linux-x86_64.egg to /anaconda/envs/loftr/lib/python3.8/site-packages
    Adding quadtree-attention-package 0.0.0 to easy-install.pth file
    
    Installed /anaconda/envs/loftr/lib/python3.8/site-packages/quadtree_attention_package-0.0.0-py3.8-linux-x86_64.egg
    Processing dependencies for quadtree-attention-package==0.0.0
    Finished processing dependencies for quadtree-attention-package==0.0.0
    
    opened by amanshenoy 1
  • Why training is ~3x slower than Swin?

    Why training is ~3x slower than Swin?

    Thanks for open sourcing this great work. While trying the code, I found the training speed is ~3x slower than Swin Transformer. For example, for quadtree-b2 which has similar FLOPs as Swin-T, training takes ~2.5s per batch. And it is even slower (3s/batch) when I align its macro design (depths, embedding dims, etc.) with Swin-T.

    Can you give some insights to account for this scenario?

    opened by rayleizhu 2
  • Config questions of notebook and scripts of feature matching

    Config questions of notebook and scripts of feature matching

    Thanks for your excellent work.

    In 'FeatureMatching/scripts/reproduce_test/outdoor_ds_quadtree.sh', 'configs/loftr/outdoor/loftr_ds_quadtree.py' is used. But this config is different from 'cvpr_ds_config.py'.

    In 'FeatureMatching/notebooks' only default settings from 'cvpr_ds_config.py' are used. Which setting should be correct for the QuadTreeAttention in feature matching?

    opened by ewrfcas 2
  • Install Problem

    Install Problem

    Hi! Appreciated for your work.

    Could you provide the environment required to install quadtreeattention module?

    I came up with compile errors on both linux and windows system. I have different conda environments including torch1.10 and torch 1.8 (cu11.1), but all envs met different compile problems. Not sure what's the reason.

    opened by lee-vius 2
  • License?

    License?

    Hi,

    Could you please provide a license for your code? We would like to add QuadTreeAttention to kornia in a similar way, as we have LoFTR now there :)

    -- Best, Dmytro

    opened by ducha-aiki 3
Owner
tangshitao
tangshitao
This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

CRGNN Paper : Improving the Training of Graph Neural Networks with Consistency Regularization Environments Implementing environment: GeForce RTX™ 3090

THUDM 28 Dec 09, 2022
NaturalProofs: Mathematical Theorem Proving in Natural Language

NaturalProofs: Mathematical Theorem Proving in Natural Language NaturalProofs: Mathematical Theorem Proving in Natural Language Sean Welleck, Jiacheng

Sean Welleck 83 Jan 05, 2023
DeceFL: A Principled Decentralized Federated Learning Framework

DeceFL: A Principled Decentralized Federated Learning Framework This repository comprises codes that reproduce experiments in Ye, et al (2021), which

Huazhong Artificial Intelligence Lab (HAIL) 10 May 31, 2022
QI-Q RoboMaster2022 CV Algorithm

QI-Q RoboMaster2022 CV Algorithm

2 Jan 10, 2022
Joint Channel and Weight Pruning for Model Acceleration on Mobile Devices

Joint Channel and Weight Pruning for Model Acceleration on Mobile Devices Abstract For practical deep neural network design on mobile devices, it is e

11 Dec 30, 2022
Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

UniSpeech The family of UniSpeech: UniSpeech (ICML 2021): Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR UniSpeech-

Microsoft 282 Jan 09, 2023
CVPR '21: In the light of feature distributions: Moment matching for Neural Style Transfer

In the light of feature distributions: Moment matching for Neural Style Transfer (CVPR 2021) This repository provides code to recreate results present

Nikolai Kalischek 49 Oct 13, 2022
使用深度学习框架提取视频硬字幕;docker容器免安装深度学习库,使用本地api接口使得界面和后端识别分离;

extract-video-subtittle 使用深度学习框架提取视频硬字幕; 本地识别无需联网; CPU识别速度可观; 容器提供API接口; 运行环境 本项目运行环境非常好搭建,我做好了docker容器免安装各种深度学习包; 提供windows界面操作; 容器为CPU版本; 视频演示 https

歌者 16 Aug 06, 2022
UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus

UmlsBERT: Clinical Domain Knowledge Augmentation of Contextual Embeddings Using the Unified Medical Language System Metathesaurus General info This is

71 Oct 25, 2022
Tensorflow implementation of Swin Transformer model.

Swin Transformer (Tensorflow) Tensorflow reimplementation of Swin Transformer model. Based on Official Pytorch implementation. Requirements tensorflow

167 Jan 08, 2023
Code for: https://berkeleyautomation.github.io/bags/

DeformableRavens Code for the paper Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks. Here is the

Daniel Seita 121 Dec 30, 2022
Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

Learning Pixel-level Semantic Affinity with Image-level Supervision This code is deprecated. Please see https://github.com/jiwoon-ahn/irn instead. Int

Jiwoon Ahn 337 Dec 15, 2022
Official Pytorch Implementation of 'Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization' (ICCV-21 Oral)

Learning-Action-Completeness-from-Points Official Pytorch Implementation of 'Learning Action Completeness from Points for Weakly-supervised Temporal A

Pilhyeon Lee 67 Jan 03, 2023
Mixed Transformer UNet for Medical Image Segmentation

MT-UNet Update 2021/11/19 Thank you for your interest in our work. We have uploaded the code of our MTUNet to help peers conduct further research on i

dotman 92 Dec 25, 2022
An implementation of "Learning human behaviors from motion capture by adversarial imitation"

Merel-MoCap-GAIL An implementation of Merel et al.'s paper on generative adversarial imitation learning (GAIL) using motion capture (MoCap) data: Lear

Yu-Wei Chao 34 Nov 12, 2022
[NeurIPS 2020] Blind Video Temporal Consistency via Deep Video Prior

pytorch-deep-video-prior (DVP) Official PyTorch implementation for NeurIPS 2020 paper: Blind Video Temporal Consistency via Deep Video Prior TensorFlo

Yazhou XING 90 Oct 19, 2022
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation E2EC: An End-to-End Contour-based Method for High-Quality H

zhangtao 146 Dec 29, 2022
PyTorch implementation of DreamerV2 model-based RL algorithm

PyDreamer Reimplementation of DreamerV2 model-based RL algorithm in PyTorch. The official DreamerV2 implementation can be found here. Features ... Run

118 Dec 15, 2022
Deep deconfounded recommender (Deep-Deconf) for paper "Deep causal reasoning for recommendations"

Deep Causal Reasoning for Recommender Systems The codes are associated with the following paper: Deep Causal Reasoning for Recommendations, Yaochen Zh

Yaochen Zhu 22 Oct 15, 2022
A Python module for parallel optimization of expensive black-box functions

blackbox: A Python module for parallel optimization of expensive black-box functions What is this? A minimalistic and easy-to-use Python module that e

Paul Knysh 426 Dec 08, 2022