Unofficial Implementation of MLP-Mixer, gMLP, resMLP, Vision Permutator, S2MLPv2, RaftMLP, ConvMLP, ConvMixer in Jittor and PyTorch.

Overview

Jittor-MLP

Unofficial Implementation of MLP-Mixer, gMLP, resMLP, Vision Permutator, S2MLPv2, RaftMLP, ConvMLP, ConvMixer in Jittor and PyTorch.

What's New

Rearrange, Reduce in einops for Jittor is support ! Easier to convert Transformer-based and MLP-based models from PyTorch to Jittor!

  • from .einops_my.layers.jittor import Rearrange, Reduce (shown in ./models_jittor/raft_mlp.py)

Models

  • Jittor and Pytorch implementaion of gMLP

Usage

import jittor as jt
from models_jittor import gMLPForImageClassification as gMLP_jt
from models_jittor import ResMLPForImageClassification as ResMLP_jt
from models_jittor import MLPMixerForImageClassification as MLPMixer_jt
from models_jittor import ViP as ViP_jt
from models_jittor import S2MLPv2 as S2MLPv2_jt
from models_jittor import ConvMixer as ConvMixer_jt
from models_jittor import convmlp_s as ConvMLP_s_jt 
from models_jittor import convmlp_l as ConvMLP_l_jt 
from models_jittor import convmlp_m as ConvMLP_m_jt 
from models_jittor import RaftMLP as RaftMLP_jt

model_jt = MLPMixer_jt(
    image_size=(224,112),
    patch_size=16,
    in_channels=3,
    num_classes=1000,
    d_model=256,
    depth=12,
)

images = jt.randn(8, 3, 224, 224)
with jt.no_grad():
    output = model_jt(images)
print(output.shape) # (8, 1000)

############################################################################

import torch
from models_pytorch import gMLPForImageClassification as gMLP_pt
from models_pytorch import ResMLPForImageClassification as ResMLP_pt
from models_pytorch import MLPMixerForImageClassification as MLPMixer_pt
from models_pytorch import ViP as ViP_pt
from models_pytorch import S2MLPv2 as S2MLPv2_pt 
from models_pytorch import ConvMixer as ConvMixer_pt 
from models_pytorch import convmlp_s as ConvMLP_s_pt 
from models_pytorch import convmlp_l as ConvMLP_l_pt 
from models_pytorch import convmlp_m as ConvMLP_m_pt 
from models_pytorch import RaftMLP as RaftMLP_pt

model_pt = ViP_pt(
    image_size=224,
    patch_size=16,
    in_channels=3,
    num_classes=1000,
    d_model=256,
    depth=30,
    segments = 16,
    weighted = True
)

images = torch.randn(8, 3, 224, 224)

with torch.no_grad():
    output = model_pt(images)
print(output.shape) # (8, 1000)


############################## Non-square images and patch sizes #########################

model_jt = ViP_jt(
    image_size=(224, 112),
    patch_size=(16, 8),
    in_channels=3,
    num_classes=1000,
    d_model=256,
    depth=30,
    segments = 16,
    weighted = True
)
images = jt.randn(8, 3, 224, 112)
with jt.no_grad():
    output = model_jt(images)
print(output.shape) # (8, 1000)

############################## 2 Stages S2MLPv2 #########################
model_pt = S2MLPv2_pt(
    in_channels = 3,
    image_size = (224,224),
    patch_size = [(7,7), (2,2)],
    d_model = [192, 384],
    depth = [4, 14],
    num_classes = 1000, 
    expansion_factor = [3, 3]
)

############################## ConvMLP With Pretrain Params #########################
model_jt = ConvMLP_s_jt(pretrained = True, num_classes = 1000)


############################## RaftMLP #########################
model_jt = RaftMLP_jt(
        layers = [
            {"depth": 12,
            "dim": 768,
            "patch_size": 16,
            "raft_size": 4}
        ],
        gap = True
    )

Citations

@misc{tolstikhin2021mlpmixer,
    title   = {MLP-Mixer: An all-MLP Architecture for Vision},
    author  = {Ilya Tolstikhin and Neil Houlsby and Alexander Kolesnikov and Lucas Beyer and Xiaohua Zhai and Thomas Unterthiner and Jessica Yung and Daniel Keysers and Jakob Uszkoreit and Mario Lucic and Alexey Dosovitskiy},
    year    = {2021},
    eprint  = {2105.01601},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}
@misc{hou2021vision,
    title   = {Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition},
    author  = {Qibin Hou and Zihang Jiang and Li Yuan and Ming-Ming Cheng and Shuicheng Yan and Jiashi Feng},
    year    = {2021},
    eprint  = {2106.12368},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}
@article{liu2021pay,
  title={Pay Attention to MLPs},
  author={Liu, Hanxiao and Dai, Zihang and So, David R and Le, Quoc V},
  journal={arXiv preprint arXiv:2105.08050},
  year={2021}
}
@article{touvron2021resmlp,
  title={Resmlp: Feedforward networks for image classification with data-efficient training},
  author={Touvron, Hugo and Bojanowski, Piotr and Caron, Mathilde and Cord, Matthieu and El-Nouby, Alaaeldin and Grave, Edouard and Joulin, Armand and Synnaeve, Gabriel and Verbeek, Jakob and J{\'e}gou, Herv{\'e}},
  journal={arXiv preprint arXiv:2105.03404},
  year={2021}
}
@article{yu2021s,
  title={S $\^{} 2$-MLPv2: Improved Spatial-Shift MLP Architecture for Vision},
  author={Yu, Tan and Li, Xu and Cai, Yunfeng and Sun, Mingming and Li, Ping},
  journal={arXiv preprint arXiv:2108.01072},
  year={2021}
}
@article{li2021convmlp,
  title={ConvMLP: Hierarchical Convolutional MLPs for Vision},
  author={Li, Jiachen and Hassani, Ali and Walton, Steven and Shi, Humphrey},
  journal={arXiv preprint arXiv:2109.04454},
  year={2021}
}
@article{tatsunami2021raftmlp,
  title={RaftMLP: Do MLP-based Models Dream of Winning Over Computer Vision?},
  author={Tatsunami, Yuki and Taki, Masato},
  journal={arXiv preprint arXiv:2108.04384},
  year={2021}
}
95.47% on CIFAR10 with PyTorch

Train CIFAR10 with PyTorch I'm playing with PyTorch on the CIFAR10 dataset. Prerequisites Python 3.6+ PyTorch 1.0+ Training # Start training with: py

5k Dec 30, 2022
The coda and data for "Measuring Fine-Grained Domain Relevance of Terms: A Hierarchical Core-Fringe Approach" (ACL '21)

We propose a hierarchical core-fringe learning framework to measure fine-grained domain relevance of terms – the degree that a term is relevant to a broad (e.g., computer science) or narrow (e.g., de

Jie Huang 14 Oct 21, 2022
Brain Tumor Detection with Tensorflow Neural Networks.

Brain-Tumor-Detection A convolutional neural network model built with Tensorflow & Keras to detect brain tumor and its different variants. Data of the

404ErrorNotFound 5 Aug 23, 2022
Code and data to accompany the camera-ready version of "Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation" in EMNLP 2021

Code and data to accompany the camera-ready version of "Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation" in EMNLP 2021

Mozhdeh Gheini 16 Jul 16, 2022
Semi-supevised Semantic Segmentation with High- and Low-level Consistency

Semi-supevised Semantic Segmentation with High- and Low-level Consistency This Pytorch repository contains the code for our work Semi-supervised Seman

123 Dec 30, 2022
Face Alignment using python

Face Alignment Face Alignment using python Input Image Aligned Face Aligned Face Aligned Face Input Image Aligned Face Input Image Aligned Face Instal

Sajjad Aemmi 28 Nov 23, 2022
HGCN: Harmonic Gated Compensation Network For Speech Enhancement

HGCN The official repo of "HGCN: Harmonic Gated Compensation Network For Speech Enhancement", which was accepted at ICASSP2022. How to use step1: Calc

ScorpioMiku 33 Nov 14, 2022
BADet: Boundary-Aware 3D Object Detection from Point Clouds (Pattern Recognition 2022)

BADet: Boundary-Aware 3D Object Detection from Point Clouds (Pattern Recognition

Rui Qian 17 Dec 12, 2022
The official implementation of CVPR 2021 Paper: Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation.

Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation This repository is the official implementation of CVPR 2021 paper:

9 Nov 14, 2022
Convert onnx models to pytorch.

onnx2torch onnx2torch is an ONNX to PyTorch converter. Our converter: Is easy to use – Convert the ONNX model with the function call convert; Is easy

ENOT 264 Dec 30, 2022
Fang Zhonghao 13 Nov 19, 2022
codes for IKM (arXiv2021, Submitted to IEEE Trans)

Image-specific Convolutional Kernel Modulation for Single Image Super-resolution This repository is for IKM introduced in the following paper Yuanfei

Yuanfei Huang 9 Dec 29, 2022
generate-2D-quadrilateral-mesh-with-neural-networks-and-tree-search

generate-2D-quadrilateral-mesh-with-neural-networks-and-tree-search This repository contains single-threaded TreeMesh code. I'm Hua Tong, a senior stu

Hua Tong 18 Sep 21, 2022
Deep Learning Theory

Deep Learning Theory 整理了一些深度学习的理论相关内容,持续更新。 Overview Recent advances in deep learning theory 总结了目前深度学习理论研究的六个方向的一些结果,概述型,没做深入探讨(2021)。 1.1 complexity

fq 103 Jan 04, 2023
Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

Real-time face detection and emotion/gender classification using fer2013/imdb datasets with a keras CNN model and openCV.

Octavio Arriaga 5.3k Dec 30, 2022
PyZebrascope - an open-source Python platform for brain-wide neural activity imaging in behaving zebrafish

PyZebrascope - an open-source Python platform for brain-wide neural activity imaging in behaving zebrafish

1 May 31, 2022
Codes and models of NeurIPS2021 paper - DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense neural networks

DominoSearch This is repository for codes and models of NeurIPS2021 paper - DominoSearch: Find layer-wise fine-grained N:M sparse schemes from dense n

11 Sep 10, 2022
A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation (ICCV 2021)

A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation (ICCV 2021) This repository contains the official implemen

81 Dec 14, 2022
Masked regression code - Masked Regression

Masked Regression MR - Python Implementation This repositery provides a python implementation of MR (Masked Regression). MR can efficiently synthesize

Arbish Akram 1 Dec 23, 2021
Graph Convolutional Networks for Temporal Action Localization (ICCV2019)

Graph Convolutional Networks for Temporal Action Localization This repo holds the codes and models for the PGCN framework presented on ICCV 2019 Graph

Runhao Zeng 318 Dec 06, 2022