donnyyou / Torch Segmentation
Licence: apache-2.0
Semantic Segmentation
Stars: ✭ 165
Labels
Projects that are alternatives of or similar to Torch Segmentation
Maml Jax
Implementation of Model-Agnostic Meta-Learning (MAML) in Jax
Stars: ✭ 164 (-0.61%)
Mutual labels: jupyter-notebook
Simple Ehm
A simple tool for a simple task: remove filler sounds ("ehm") from pre-recorded speeches. AI powered.
Stars: ✭ 164 (-0.61%)
Mutual labels: jupyter-notebook
Tensorflow2 Crash Course
A quick crash course in understanding the essentials of TensorFlow 2 and the integrated Keras API
Stars: ✭ 162 (-1.82%)
Mutual labels: jupyter-notebook
Ta
Technical Analysis Library using Pandas and Numpy
Stars: ✭ 2,649 (+1505.45%)
Mutual labels: jupyter-notebook
Replika Research
Replika.ai Research Papers, Posters, Slides & Datasets
Stars: ✭ 164 (-0.61%)
Mutual labels: jupyter-notebook
Notes
Contains Example Programs and Notebooks for some courses at Bogazici University, Department of Computer Engineering
Stars: ✭ 163 (-1.21%)
Mutual labels: jupyter-notebook
Rwf2000 Video Database For Violence Detection
A large scale video database for violence detection, which has 2,000 video clips containing violent or non-violent behaviours.
Stars: ✭ 165 (+0%)
Mutual labels: jupyter-notebook
Dsp
Metis Data Science Bootcamp - Official Prework Repository
Stars: ✭ 164 (-0.61%)
Mutual labels: jupyter-notebook
Workshops
Workshops organized to introduce students to security, AI, AR/VR, hardware and software
Stars: ✭ 162 (-1.82%)
Mutual labels: jupyter-notebook
Newsrecommender
A news recommendation system tailored for user communities
Stars: ✭ 164 (-0.61%)
Mutual labels: jupyter-notebook
Machine Learning
Machine learning library written in readable python code
Stars: ✭ 163 (-1.21%)
Mutual labels: jupyter-notebook
Fixy
Amacımız Türkçe NLP literatüründeki birçok farklı sorunu bir arada çözebilen, eşsiz yaklaşımlar öne süren ve literatürdeki çalışmaların eksiklerini gideren open source bir yazım destekleyicisi/denetleyicisi oluşturmak. Kullanıcıların yazdıkları metinlerdeki yazım yanlışlarını derin öğrenme yaklaşımıyla çözüp aynı zamanda metinlerde anlamsal analizi de gerçekleştirerek bu bağlamda ortaya çıkan yanlışları da fark edip düzeltebilmek.
Stars: ✭ 165 (+0%)
Mutual labels: jupyter-notebook
Scientific graphics in python
Электронный учебник-пособие по научной графике в python
Stars: ✭ 163 (-1.21%)
Mutual labels: jupyter-notebook
A Journey Into Convolutional Neural Network Visualization
A journey into Convolutional Neural Network visualization
Stars: ✭ 165 (+0%)
Mutual labels: jupyter-notebook
Appearance Flow
A deep learning framework for synthesizing novel views of objects and scenes
Stars: ✭ 164 (-0.61%)
Mutual labels: jupyter-notebook
MT-Segmentation
@misc{mt-segmentation,
author = {Ansheng You, Zhenhua Chai},
title = {MT-Segmentation},
howpublished = {\url{http://git.sankuai.com/users/youansheng/repos/mt-segmentation}},
year = {2020}
}
This repository provides source code for most deep learning based cv problems. We'll do our best to keep this repository up-to-date. If you do find a problem about this repository, please raise an issue or submit a pull request.
Implemented Papers
-
Semantic Segmentation
- DeepLabV3: Rethinking Atrous Convolution for Semantic Image Segmentation
- PSPNet: Pyramid Scene Parsing Network
- DenseASPP: DenseASPP for Semantic Segmentation in Street Scenes
- Asymmetric Non-local Neural Networks for Semantic Segmentation
QuickStart with TorchCV
Now only support Python3.x, pytorch 1.3.
pip3 install -r requirements.txt
cd lib/exts
sh make.sh
Performances with MT-Segmentation
All the performances showed below fully reimplemented the papers' results.
Semantic Segmentation
- Cityscapes (Single Scale Whole Image Test): Base LR 0.01, Crop Size 769
Model | Backbone | Train | Test | mIOU | BS | Iters | Scripts |
---|---|---|---|---|---|---|---|
PSPNet | 3x3-Res101 | train | val | 78.20 | 8 | 4W | PSPNet |
DeepLabV3 | 3x3-Res101 | train | val | 79.13 | 8 | 4W | DeepLabV3 |
- ADE20K (Single Scale Whole Image Test): Base LR 0.02, Crop Size 520
Model | Backbone | Train | Test | mIOU | PixelACC | BS | Iters | Scripts |
---|---|---|---|---|---|---|---|---|
PSPNet | 3x3-Res50 | train | val | 41.52 | 80.09 | 16 | 15W | PSPNet |
DeepLabv3 | 3x3-Res50 | train | val | 42.16 | 80.36 | 16 | 15W | DeepLabV3 |
PSPNet | 3x3-Res101 | train | val | 43.60 | 81.30 | 16 | 15W | PSPNet |
DeepLabv3 | 3x3-Res101 | train | val | 44.13 | 81.42 | 16 | 15W | DeepLabV3 |
Commands with MT-Segmentation
Take PSPNet as an example. ("tag" could be any string, include an empty one.)
- Training
cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag
- Resume Training
cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh train tag
- Validate
cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh val tag
- Testing:
cd scripts/cityscapes/
bash run_fs_pspnet_cityscapes_seg.sh test tag
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].