Implement slightly different caffe-segnet in tensorflow

Overview

Tensorflow-SegNet

Implement slightly different (see below for detail) SegNet in tensorflow, successfully trained segnet-basic in CamVid dataset.

Due to indice unravel still unavailable in tensorflow, the original upsampling method is temporarily replaced simply by deconv( or conv-transpose) layer (without pooling indices). You can follow the issue here: https://github.com/tensorflow/tensorflow/issues/2169 (The current workaround for unpooling layer is a bit slow because it lacks of GPU support.)

for model detail, please go to https://github.com/alexgkendall/caffe-segnet

Requirement

tensorflow 1.0 Pillow (optional, for write label image) scikit-image

Update

Update to tf 1.0

Finally get some time to refactor a bit, removing some un-used function and remove the hard-coded file path Now the model should be easy to config. The parameters can be found in main.py.

I planned to add more feature such as dilation, multi-resolution, sequential learning..etc. Making it more like a "basic" segmentation toolbox and support more dataset as well. Therefore the model and documentation will be changed accordingly in the future.

More utility function will be added and some messed coding style will be fixed. Any feature request is also welcomed.

Usage

see also example.sh training:

python main.py --log_dir=path_to_your_log --image_dir=path_to_CamVid_train.txt --val_dir=path_to_CamVid_val.txt --batch_size=5

finetune:

python main.py --finetune=path_to_saved_ckpt --log_dir=path_to_your_log --image_dir=path_to_CamVid_train.txt --val_dir=path_to_CamVid_val.txt --batch_size=5

testing:

python main.py --testing=path_to_saved_ckpt --log_dir=path_to_your_log --test_dir=path_to_CamVid_train.txt --batch_size=5 --save_image=True

You can set default path and parameters in main.py line 6~18. note: in --testing you can specify whether to save predicted images, currently only save one image for manually checking, will be configured to be more flexible.

Dataset

This Implement default to use CamVid dataset as described in the original SegNet paper, The dataset can be download from author's github https://github.com/alexgkendall/SegNet-Tutorial in the CamVid folder

example format:

"path_to_image1" "path_to_corresponded_label_image1",

"path_to_image2" "path_to_corresponded_label_image2",

"path_to_image3" "path_to_corresponded_label_image3",

.......

Owner
Tseng Kuan Lun
Computer Vision React React-Native
Tseng Kuan Lun
SmartSim Infrastructure Library.

Home Install Documentation Slack Invite Cray Labs SmartSim SmartSim makes it easier to use common Machine Learning (ML) libraries like PyTorch and Ten

Cray Labs 139 Jan 01, 2023
PaSST: Efficient Training of Audio Transformers with Patchout

PaSST: Efficient Training of Audio Transformers with Patchout This is the implementation for Efficient Training of Audio Transformers with Patchout Pa

165 Dec 26, 2022
PyTorch implementation of Histogram Layers from DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation

deep-hist PyTorch implementation of Histogram Layers from DeepHist: Differentiable Joint and Color Histogram Layers for Image-to-Image Translation PyT

Winfried Lötzsch 10 Dec 06, 2022
A torch.Tensor-like DataFrame library supporting multiple execution runtimes and Arrow as a common memory format

TorchArrow (Warning: Unstable Prototype) This is a prototype library currently under heavy development. It does not currently have stable releases, an

Facebook Research 536 Jan 06, 2023
Torchyolo - Yolov3 ve Yolov4 modellerin Pytorch uygulamasıdır

TORCHYOLO : Yolo Modellerin Pytorch Uygulaması Yapılacaklar: Yolov3 model.py ve

Kadir Nar 3 Aug 22, 2022
Delving into Localization Errors for Monocular 3D Object Detection, CVPR'2021

Delving into Localization Errors for Monocular 3D Detection By Xinzhu Ma, Yinmin Zhang, Dan Xu, Dongzhan Zhou, Shuai Yi, Haojie Li, Wanli Ouyang. Intr

XINZHU.MA 124 Jan 04, 2023
CondenseNet: Light weighted CNN for mobile devices

CondenseNets This repository contains the code (in PyTorch) for "CondenseNet: An Efficient DenseNet using Learned Group Convolutions" paper by Gao Hua

Shichen Liu 690 Nov 30, 2022
TextBPN Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection

TextBPN Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection; Accepted by ICCV2021. Note: The complete code (including training and t

S.X.Zhang 84 Dec 13, 2022
Post-training Quantization for Neural Networks with Provable Guarantees

Post-training Quantization for Neural Networks with Provable Guarantees Authors: Jinjie Zhang ( Yixuan Zhou 2 Nov 29, 2022

ppo_pytorch_cpp - an implementation of the proximal policy optimization algorithm for the C++ API of Pytorch

PPO Pytorch C++ This is an implementation of the proximal policy optimization algorithm for the C++ API of Pytorch. It uses a simple TestEnvironment t

Martin Huber 59 Dec 09, 2022
Official Implementation of DE-DETR and DELA-DETR in "Towards Data-Efficient Detection Transformers"

DE-DETRs By Wen Wang, Jing Zhang, Yang Cao, Yongliang Shen, and Dacheng Tao This repository is an official implementation of DE-DETR and DELA-DETR in

Wen Wang 61 Dec 12, 2022
Pytorch implementation of winner from VQA Chllange Workshop in CVPR'17

2017 VQA Challenge Winner (CVPR'17 Workshop) pytorch implementation of Tips and Tricks for Visual Question Answering: Learnings from the 2017 Challeng

Mark Dong 166 Dec 11, 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
A PyTorch implementation of unsupervised SimCSE

A PyTorch implementation of unsupervised SimCSE

99 Dec 23, 2022
Certifiable Outlier-Robust Geometric Perception

Certifiable Outlier-Robust Geometric Perception About This repository holds the implementation for certifiably solving outlier-robust geometric percep

83 Dec 31, 2022
Spiking Neural Network for Computer Vision using SpikingJelly framework and Pytorch-Lightning

Spiking Neural Network for Computer Vision using SpikingJelly framework and Pytorch-Lightning

Sami BARCHID 2 Oct 20, 2022
Semi-Supervised Semantic Segmentation with Pixel-Level Contrastive Learning from a Class-wise Memory Bank

This repository provides the official code for replicating experiments from the paper: Semi-Supervised Semantic Segmentation with Pixel-Level Contrast

Iñigo Alonso Ruiz 58 Dec 15, 2022
Deep Learning Head Pose Estimation using PyTorch.

Hopenet is an accurate and easy to use head pose estimation network. Models have been trained on the 300W-LP dataset and have been tested on real data with good qualitative performance.

Nataniel Ruiz 1.3k Dec 26, 2022
A complete, self-contained example for training ImageNet at state-of-the-art speed with FFCV

ffcv ImageNet Training A minimal, single-file PyTorch ImageNet training script designed for hackability. Run train_imagenet.py to get... ...high accur

FFCV 92 Dec 31, 2022
Runtime type annotations for the shape, dtype etc. of PyTorch Tensors.

torchtyping Type annotations for a tensor's shape, dtype, names, ... Turn this: def batch_outer_product(x: torch.Tensor, y: torch.Tensor) - torch.Ten

Patrick Kidger 1.2k Jan 03, 2023