武汉大学机器学习与模式识别课程-基于python实现的实验，监督学习，无监督学习，神经网络等等源码+文档说明

## 第一步：准备动作数据集 ### test数据集下载地址 链接：https://pan.baidu.com/s/1M0IW4fhvWPHNYFwDNo7DYg 提取码：zav5 大小：6.22G ### 标签定义 | label | meaning | label | meaning | | :---- | :---------------- | ----- | ----------------- | | 1 | holding_cloth | 5 | open_door_enter | | 2 | eating | 6 | carrying_bag | | 3 | go_up_down_stairs | 7 | smoking_cigarette | | 4 | open_door_leave | 0 | others | ### train val 数据集下载 **where are the train/test datasets from** 1. holding_cloth - Charades 2. eating - Kinetics 400 3. go_up_down_stairs 4. open_door_leave - AVA (exit) 5. open_door_enter - AVA (enter) 6. carrying_bag - Charades 7. smoking_cigarette - Kinetics 400 8. others ## 第二步 环境搭建 相关参考及教程： https://pytorchvideo.org/docs/tutorial_classification ## 参考 https://github.com/xiaobai1217/Awesome-Video-Datasets/blob/main/README.md @article{sigurdsson2016hollywood, author = {Gunnar A. Sigurdsson and G{\"u}l Varol and Xiaolong Wang and Ivan Laptev and Ali Farhadi and Abhinav Gupta}, title = {Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding}, journal = {ArXiv e-prints}, eprint = {1604.01753}, year = {2016}, url = {http://arxiv.org/abs/1604.01753}, } @inproceedings{TSN2016ECCV, author = {Limin Wang and Yuanjun Xiong and Zhe Wang and Yu Qiao and Dahua Lin and Xiaoou Tang and Luc {Val Gool}}, title = {Temporal Segment Networks: Towards Good Practices for Deep Action Recognition}, booktitle = {ECCV}, year = {2016}, } @inproceedings{inproceedings, author = {Carreira, J. and Zisserman, Andrew}, year = {2017}, month = {07}, pages = {4724-4733}, title = {Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset}, doi = {10.1109/CVPR.2017.502} } @inproceedings{gu2018ava, title={Ava: A video dataset of spatio-temporally localized atomic visual actions}, author={Gu, Chunhui and Sun, Chen and Ross, David A and Vondrick, Carl and Pantofaru, Caroline and Li, Yeqing and Vijayanarasimhan, Sudheendra and Toderici, George and Ricco, Susanna and Sukthankar, Rahul and others}, booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition}, pages={6047--6056}, year={2018} } Donahue, J., Hendricks, L. A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., & Darrell, T. (2014). Long-term recurrent convolutional networks for visual recognition and description. arXiv preprint arXiv:1411.4389.Chicago