AI Rank
中文
← Open Source
jfzhang95

pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.

Model DevelopmentArchitecturePython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
1.23k
Stars
251
Forks
+0
This week
1
Contributors
Created 2018-07-31 · Updated 2026-09-23 · #11038 today
Top developers
sdxass

jfzhang95/pytorch-video-recognition is ranked 11,038 with 1,234 stars.

Same-category comparison

jfzhang95/pytorch-video-recognition is ranked 11,038 among these 8 peers; jakesnell/prototypical-networks is ranked 11,031.

Same-category comparison
NameRankMetrics
facebookresearch/simsiam11,026
Language:
Python
Stars:
1,236
Forks:
174
Description:
PyTorch implementation of SimSiam https//arxiv.org/abs/2011.10566.
ivan-vasilev/neuralnetworks11,027
Language:
Java
Stars:
1,236
Forks:
345
Description:
java deep learning algorithms and deep neural networks with gpu acceleration.
BR-IDL/PaddleViT11,029
Language:
Python
Stars:
1,235
Forks:
328
Description:
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+.
jakesnell/prototypical-networks11,031
Language:
Python
Stars:
1,235
Forks:
270
Description:
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning".
python-adaptive/adaptive11,050
Language:
Python
Stars:
1,230
Forks:
64
Description:
:chart_with_upwards_trend: Adaptive: parallel active learning of mathematical functions.
yuanxiaosc/Entity-Relation-Extraction11,052
Language:
Python
Stars:
1,230
Forks:
269
Description:
Entity and Relation Extraction Based on TensorFlow and BERT. Schema based Knowledge Extraction, SKE 2019.
huoyijie/AdvancedEAST11,054
Language:
Python
Stars:
1,229
Forks:
371
Description:
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.https://github.com/huoyijie/raspberrypi-car.
Genesis-Embodied-AI/RoboGen11,058
Language:
Python
Stars:
1,228
Forks:
108
Description:
A generative and self-guided robotic agent that endlessly propose and master new skills.
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryArchitecture
Stars1,234
Forks251
Contributors1
Created date2018-07-31
Updated date2026-09-23
Stars in 1 day0
Stars in 7 days0
Rank11,038
Previous rank10,992
Rank change-46
7-day stars rank12,862
Previous 7-day stars rank12,880
7-day stars rank change18
Total stars rank9,483
Previous total stars rank9,477
Total stars rank change-6
CountrySingapore
README summary

pytorch-video-recognition Introduction This repo contains several models for video action recognition, including C3D, R2Plus1D, R3D, inplemented using PyTorch (0. Currently, we train these models on UCF101 and HMDB51 datasets. **More models and datasets will be available soon! ** **Note: An interesting online web game based on C3D model is in here. ** Installation The code was tested with Anaconda and Python 3. After installing the Anaconda environment: 0. Download pretrained model from BaiduYun or GoogleDrive. Currently only support pretrained model

for C3D. Configure your dataset and pretrained model path in mypath. You can choose different models and datasets in train. Datasets: I used two different datasets: UCF101 and HMDB. Dataset directory tree is shown below **UCF101** Make sure to put the files as the following structure: After pre-processing, the output dir's structure is as follows: Note: HMDB dataset's directory tree is similar to UCF101 dataset's. Experiments These models were trained in machine with NVIDIA TITAN X 12gb GPU. Note

that I splited train/val/test data for each dataset using sklearn. If you want to train models using official train/val/test data, you can look in dataset. Currently, I only train C3D model in UCF and HMDB datasets. The train/val/test accuracy and loss curves for each experiment are shown below: **UCF101** **HMDB51** Experiments for other models will be updated soon .

Frequently asked questions

How many stars and forks are recorded?

jfzhang95/pytorch-video-recognition has 1,234 stars and 251 forks.

What is the repository rank?

jfzhang95/pytorch-video-recognition is ranked 11,038.

What language and category are recorded?

jfzhang95/pytorch-video-recognition has 1,234 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

jfzhang95/pytorch-video-recognition is compared with jakesnell/prototypical-networks, ranked 11,031 with 1,235 stars.

README

pytorch-video-recognition

Introduction

This repo contains several models for video action recognition, including C3D, R2Plus1D, R3D, inplemented using PyTorch (0.4.0). Currently, we train these models on UCF101 and HMDB51 datasets. More models and datasets will be available soon!

Note: An interesting online web game based on C3D model is in here.

Installation

The code was tested with Anaconda and Python 3.5. After installing the Anaconda environment:

  1. Clone the repo:

    git clone https://github.com/jfzhang95/pytorch-video-recognition.git
cd pytorch-video-recognition

  2. Install dependencies:

    For PyTorch dependency, see pytorch.org for more details.

    For custom dependencies:

    conda install opencv
pip install tqdm scikit-learn tensorboardX

  3. Download pretrained model from BaiduYun or GoogleDrive. Currently only support pretrained model for C3D.

  4. Configure your dataset and pretrained model path in mypath.py.

  5. You can choose different models and datasets in train.py.

    To train the model, please do:

    python train.py

Datasets:

I used two different datasets: UCF101 and HMDB.

Dataset directory tree is shown below

  • UCF101 Make sure to put the files as the following structure:
    UCF-101
├── ApplyEyeMakeup
│   ├── v_ApplyEyeMakeup_g01_c01.avi
│   └── ...
├── ApplyLipstick
│   ├── v_ApplyLipstick_g01_c01.avi
│   └── ...
└── Archery
│   ├── v_Archery_g01_c01.avi
│   └── ...

After pre-processing, the output dir's structure is as follows:

ucf101
├── ApplyEyeMakeup
│   ├── v_ApplyEyeMakeup_g01_c01
│   │   ├── 00001.jpg
│   │   └── ...
│   └── ...
├── ApplyLipstick
│   ├── v_ApplyLipstick_g01_c01
│   │   ├── 00001.jpg
│   │   └── ...
│   └── ...
└── Archery
│   ├── v_Archery_g01_c01
│   │   ├── 00001.jpg
│   │   └── ...
│   └── ...

Note: HMDB dataset's directory tree is similar to UCF101 dataset's.

Experiments

These models were trained in machine with NVIDIA TITAN X 12gb GPU. Note that I splited train/val/test data for each dataset using sklearn. If you want to train models using official train/val/test data, you can look in dataset.py, and modify it to your needs.

Currently, I only train C3D model in UCF and HMDB datasets. The train/val/test accuracy and loss curves for each experiment are shown below:

  • UCF101

  • HMDB51

Experiments for other models will be updated soon ...

Nearby in the ranking
Similar items