3D-ResNets-PyTorch
Our paper "Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?" is accepted to CVPR2018!
We update the paper information.
We uploaded some of fine-tuned models on UCF-101 and HMDB-51.
ResNeXt-101 fine-tuned on UCF-101 (split1)
ResNeXt-101 (64 frame inputs) fine-tuned on UCF-101 (split1)
ResNeXt-101 fine-tuned on HMDB-51 (split1)
ResNeXt-101 (64 frame inputs) fine-tuned on HMDB-51 (split1)
We published a new paper on arXiv.
We also added the following new models and their Kinetics pretrained models in this repository.
ResNet-50, 101, 152, 200
Pre-activation ResNet-200
Wide ResNet-50
ResNeXt-101
DenseNet-121, 201
In addition, we supported new datasets (UCF-101 and HDMB-51) and fine-tuning functions.
Some minor changes are included.
Outputs are normalized by softmax in test.
If you do not want to perform the normalization, please use --no_softmax_in_test
option.
This is the PyTorch code for the following papers:
This code includes training, fine-tuning and testing on Kinetics, ActivityNet, UCF-101, and HMDB-51.
If you want to classify your videos or extract video features of them using our pretrained models, use this code.
The Torch (Lua) version of this code is available here.
Note that the Torch version only includes ResNet-18, 34, 50, 101, and 152.
If you use this code or pre-trained models, please cite the following:
@inproceedings{hara3dcnns, author={Kensho Hara and Hirokatsu Kataoka and Yutaka Satoh}, title={Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, pages={6546--6555}, year={2018}, }
Pre-trained models are available here.
All models are trained on Kinetics.
ResNeXt-101 achieved the best performance in our experiments. (See paper in details.)
resnet-18-kinetics.pth: --model resnet --model_depth 18 --resnet_shortcut A resnet-34-kinetics.pth: --model resnet --model_depth 34 --resnet_shortcut A resnet-34-kinetics-cpu.pth: CPU ver. of resnet-34-kinetics.pth resnet-50-kinetics.pth: --model resnet --model_depth 50 --resnet_shortcut B resnet-101-kinetics.pth: --model resnet --model_depth 101 --resnet_shortcut B resnet-152-kinetics.pth: --model resnet --model_depth 152 --resnet_shortcut B resnet-200-kinetics.pth: --model resnet --model_depth 200 --resnet_shortcut B preresnet-200-kinetics.pth: --model preresnet --model_depth 200 --resnet_shortcut B wideresnet-50-kinetics.pth: --model wideresnet --model_depth 50 --resnet_shortcut B --wide_resnet_k 2 resnext-101-kinetics.pth: --model resnext --model_depth 101 --resnet_shortcut B --resnext_cardinality 32 densenet-121-kinetics.pth: --model densenet --model_depth 121 densenet-201-kinetics.pth: --model densenet --model_depth 201
Some of fine-tuned models on UCF-101 and HMDB-51 (split 1) are also available.
resnext-101-kinetics-ucf101_split1.pth: --model resnext --model_depth 101 --resnet_shortcut B --resnext_cardinality 32 resnext-101-64f-kinetics-ucf101_split1.pth: --model resnext --model_depth 101 --resnet_shortcut B --resnext_cardinality 32 --sample_duration 64 resnext-101-kinetics-hmdb51_split1.pth: --model resnext --model_depth 101 --resnet_shortcut B --resnext_cardinality 32 resnext-101-64f-kinetics-hmdb51_split1.pth: --model resnext --model_depth 101 --resnet_shortcut B --resnext_cardinality 32 --sample_duration 64
This table shows the averaged accuracies over top-1 and top-5 on Kinetics.
Method | Accuracies |
---|---|
ResNet-18 | 66.1 |
ResNet-34 | 71.0 |
ResNet-50 | 72.2 |
ResNet-101 | 73.3 |
ResNet-152 | 73.7 |
ResNet-200 | 73.7 |
ResNet-200 (pre-act) | 73.4 |
Wide ResNet-50 | 74.7 |
ResNeXt-101 | 75.4 |
DenseNet-121 | 70.8 |
DenseNet-201 | 72.3 |
conda install pytorch torchvision cuda80 -c soumith
FFmpeg, FFprobe
wget http://johnvansickle.com/ffmpeg/releases/ffmpeg-release-64bit-static.tar.xz tar xvf ffmpeg-release-64bit-static.tar.xz cd ./ffmpeg-3.3.3-64bit-static/; sudo cp ffmpeg ffprobe /usr/local/bin;
Python 3
Download videos using the official crawler.
Convert from avi to jpg files using utils/video_jpg.py
python utils/video_jpg.py avi_video_directory jpg_video_directory
Generate fps files using utils/fps.py
python utils/fps.py avi_video_directory jpg_video_directory
Download videos using the official crawler.
Locate test set in video_directory/test
.
Convert from avi to jpg files using utils/video_jpg_kinetics.py
python utils/video_jpg_kinetics.py avi_video_directory jpg_video_directory
Generate n_frames files using utils/n_frames_kinetics.py
python utils/n_frames_kinetics.py jpg_video_directory
Generate annotation file in json format similar to ActivityNet using utils/kinetics_json.py
The CSV files (kinetics_{train, val, test}.csv) are included in the crawler.
python utils/kinetics_json.py train_csv_path val_csv_path test_csv_path dst_json_path
Download videos and train/test splits here.
Convert from avi to jpg files using utils/video_jpg_ucf101_hmdb51.py
python utils/video_jpg_ucf101_hmdb51.py avi_video_directory jpg_video_directory
Generate n_frames files using utils/n_frames_ucf101_hmdb51.py
python utils/n_frames_ucf101_hmdb51.py jpg_video_directory
Generate annotation file in json format similar to ActivityNet using utils/ucf101_json.py
annotation_dir_path
includes classInd.txt, trainlist0{1, 2, 3}.txt, testlist0{1, 2, 3}.txt
python utils/ucf101_json.py annotation_dir_path
Download videos and train/test splits here.
Convert from avi to jpg files using utils/video_jpg_ucf101_hmdb51.py
python utils/video_jpg_ucf101_hmdb51.py avi_video_directory jpg_video_directory
Generate n_frames files using utils/n_frames_ucf101_hmdb51.py
python utils/n_frames_ucf101_hmdb51.py jpg_video_directory
Generate annotation file in json format similar to ActivityNet using utils/hmdb51_json.py
annotation_dir_path
includes brush_hair_test_split1.txt, ...
python utils/hmdb51_json.py annotation_dir_path
Assume the structure of data directories is the following:
~/ data/ kinetics_videos/ jpg/ .../ (directories of class names) .../ (directories of video names) ... (jpg files) results/ save_100.pth kinetics.json
Confirm all options.
python main.lua -h
Train ResNets-34 on the Kinetics dataset (400 classes) with 4 CPU threads (for data loading).
Batch size is 128.
Save models at every 5 epochs. All GPUs is used for the training. If you want a part of GPUs, use CUDA_VISIBLE_DEVICES=...
.
python main.py --root_path ~/data --video_path kinetics_videos/jpg --annotation_path kinetics.json --result_path results --dataset kinetics --model resnet --model_depth 34 --n_classes 400 --batch_size 128 --n_threads 4 --checkpoint 5
Continue Training from epoch 101. (~/data/results/save_100.pth is loaded.)
python main.py --root_path ~/data --video_path kinetics_videos/jpg --annotation_path kinetics.json --result_path results --dataset kinetics --resume_path results/save_100.pth --model_depth 34 --n_classes 400 --batch_size 128 --n_threads 4 --checkpoint 5
Fine-tuning conv5_x and fc layers of a pretrained model (~/data/models/resnet-34-kinetics.pth) on UCF-101.
python main.py --root_path ~/data --video_path ucf101_videos/jpg --annotation_path ucf101_01.json --result_path results --dataset ucf101 --n_classes 400 --n_finetune_classes 101 --pretrain_path models/resnet-34-kinetics.pth --ft_begin_index 4 --model resnet --model_depth 34 --resnet_shortcut A --batch_size 128 --n_threads 4 --checkpoint 5
上一篇:keras-resnet
还没有评论,说两句吧!
热门资源
Keras-ResNeXt
Keras ResNeXt Implementation of ResNeXt models...
seetafaceJNI
项目介绍 基于中科院seetaface2进行封装的JAVA...
spark-corenlp
This package wraps Stanford CoreNLP annotators ...
capsnet-with-caps...
CapsNet with capsule-wise convolution Project ...
inferno-boilerplate
This is a very basic boilerplate example for pe...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com