From 022b3c4ac18d2f9249cc06c3b20e796cc53b69e5 Mon Sep 17 00:00:00 2001 From: sissioy Date: Sun, 11 Jul 2021 05:10:07 +0000 Subject: [PATCH 1/2] =?UTF-8?q?=E6=96=B0=E5=BB=BA=20=E5=8A=A8=E4=BD=9C?= =?UTF-8?q?=E8=AF=86=E5=88=AB-=E6=9D=A8=E6=80=9D=E9=9B=A8?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .../.keep" | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/.keep" diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/.keep" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/.keep" new file mode 100644 index 0000000..e69de29 -- Gitee From afb50f78d25606ab288f4c0842c30b59b4f59f90 Mon Sep 17 00:00:00 2001 From: sissioy Date: Sun, 11 Jul 2021 05:11:31 +0000 Subject: [PATCH 2/2] upload --- .../README.md" | 94 + .../data/ava-data-download/enter_t.txt" | 108 + .../data/ava-data-download/enter_t_pro" | 108 + .../data/ava-data-download/enter_v.txt" | 29 + .../data/ava-data-download/enter_v_pro" | 29 + .../data/ava-data-download/exit_t.txt" | 52 + .../data/ava-data-download/exit_t_pro" | 52 + .../data/ava-data-download/exit_v.txt" | 12 + .../data/ava-data-download/exit_v_pro" | 12 + .../data/ava-data-download/tmp.py" | 9 + .../data/ava-data-extra.sh" | 126 ++ .../data/ava_v2.1/ava_action_list_v2.1.pbtxt" | 400 ++++ ...tion_list_v2.1_for_activitynet_2018.pbtxt" | 240 +++ .../ava_included_timestamps_v2.1.txt" | 897 ++++++++ .../ava_test_excluded_timestamps_v2.1.csv" | 66 + .../data/frame_path.csv" | 0 .../data/frame_path.sh" | 17 + .../data_prepare.ipynb" | 1903 +++++++++++++++++ .../main.ipynb" | 1 + .../tmp.ipynb" | 1 + 20 files changed, 4156 insertions(+) create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/README.md" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t.txt" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t_pro" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v.txt" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v_pro" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t.txt" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t_pro" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v.txt" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v_pro" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/tmp.py" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-extra.sh" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1.pbtxt" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1_for_activitynet_2018.pbtxt" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_included_timestamps_v2.1.txt" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_test_excluded_timestamps_v2.1.csv" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/frame_path.csv" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/frame_path.sh" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data_prepare.ipynb" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/main.ipynb" create mode 100644 "code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/tmp.ipynb" diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/README.md" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/README.md" new file mode 100644 index 0000000..c950690 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/README.md" @@ -0,0 +1,94 @@ +## 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 \ No newline at end of file diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t.txt" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t.txt" new file mode 100644 index 0000000..f3ceab2 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t.txt" @@ -0,0 +1,108 @@ +-OyDO1g74vc.mp4 +-ZFgsrolSxo.mkv +0f39OWEqJ24.mp4 +26V9UzqSguo.mp4 +2E_e8JlvTlg.mkv +2KpThOF_QmE.mkv +2fwni_Kjf2M.mkv +2qQs3Y9OJX0.mkv +32HR3MnDZ8g.mp4 +3_VjIRdXVdM.mkv +5MxjqHfkWFI.mkv +5milLu-6bWI.mp4 +7YpF6DntOYw.mkv +7g37N3eoQ9s.mkv +7nHkh4sP5Ks.mkv +8JSxLhDMGtE.mkv +8nO5FFbIAog.webm +9IF8uTRrWAM.mkv +9eAOr_ttXp0.mkv +9mLYmkonWZQ.mkv +B1MAUxpKaV8.mkv +BCiuXAuCKAU.mp4 +BY3sZmvUp-0.mp4 +C25wkwAMB-w.mkv +C3qk4yAMANk.mkv +CG98XdYsgrA.mkv +E7JcKooKVsM.mp4 +Feu1_8NazPE.mp4 +G5Yr20A5z_Q.mkv +HTYT2vF-j_w.mkv +HV0H6oc4Kvs.mkv +Hi8QeP_VPu0.mkv +HymKCzQJbB8.mkv +I8j6Xq2B5ys.mp4 +IKdBLciu_-A.mp4 +J1jDc2rTJlg.mkv +JNb4nWexD0I.mkv +KWoSGtglCms.mkv +Kb1fduj-jdY.mp4 +Ksd1JQFHYWA.mp4 +LIavUJVrXaI.mkv +LrDT25hmApw.mkv +N5UD8FGzDek.mkv +O5m_0Yay4EU.mkv +OfMdakd4bHI.mkv +P90hF2S1JzA.mkv +PNZQ2UJfyQE.mp4 +PcFEhUKhN6g.mkv +QotkBTEePI8.mkv +Rm518TUhbRY.mkv +S0tkhGJjwLA.mkv +SHBMiL5f_3Q.mkv +TCmNvNLRWrc.mkv +TcB0IFBwk-k.mkv +UOfuzrwkclM.mkv +U_WzY2k8IBM.mkv +UgZFdrNT6W0.mkv +UsLnxI_zGpY.mkv +Vmef_8MY46w.mkv +WVde9pyaHg4.mkv +YYWdB7h1INo.mkv +Ytga8ciKWJc.mkv +_a9SWtcaNj8.mkv +_mAfwH6i90E.mkv +aDEYi1OG0vU.mkv +b5pRYl_djbs.mp4 +bAVXp1oGjHA.mkv +cKA-qeZuH_w.mkv +cWYJHb25EVs.mp4 +cc4y-yYm5Ao.mkv +dMH8L7mqCNI.mkv +gjdgj04FzR0.mp4 +hbYvDvJrpNk.mp4 +iSlDMboCSao.mkv +jBs_XYHI7gM.mkv +jI0HIlSsa3s.mkv +jgAwJ0RqmYg.mp4 +jqZpiHlJUig.mkv +kplbKz3_fZk.mkv +l-jxh8gpxuY.mkv +lWXhqIAvarw.mkv +mfsbYdLx9wE.mkv +mkcDANJjDcM.mkv +oq_bufAhyl8.mkv +phVLLTMzmKk.mkv +plkJ45_-pMk.mp4 +qpoWHELxL-4.mp4 +qrkff49p4E4.mp4 +rFgb2ECMcrY.mkv +rJKeqfTlAeY.mkv +rk8Xm0EAOWs.mkv +skiZueh4lfY.mkv +t0V4drbYDnc.mkv +t1LXrJOvPDg.mkv +tt0t_a1EDCE.mkv +uq_HBsvP548.mkv +uzPI7FcF79U.mkv +vfjywN5CN0Y.mkv +wogRuPNBUi8.mp4 +x-6CtPWVi6E.mkv +xO4ABy2iOQA.mp4 +xp67EC-Hvwk.mkv +y7ncweROe9U.mkv +yo-Kg2YxlZs.mkv +yqImJuC5UzI.mp4 +yvgCGJ6vfkY.mkv +z3kgrh0L_80.mkv +zR725veL-DI.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t_pro" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t_pro" new file mode 100644 index 0000000..c1904ce --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_t_pro" @@ -0,0 +1,108 @@ +https://s3.amazonaws.com/ava-dataset/trainval/-OyDO1g74vc.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/-ZFgsrolSxo.mkv +https://s3.amazonaws.com/ava-dataset/trainval/0f39OWEqJ24.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/26V9UzqSguo.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/2E_e8JlvTlg.mkv +https://s3.amazonaws.com/ava-dataset/trainval/2KpThOF_QmE.mkv +https://s3.amazonaws.com/ava-dataset/trainval/2fwni_Kjf2M.mkv +https://s3.amazonaws.com/ava-dataset/trainval/2qQs3Y9OJX0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/32HR3MnDZ8g.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/3_VjIRdXVdM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/5MxjqHfkWFI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/5milLu-6bWI.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/7YpF6DntOYw.mkv +https://s3.amazonaws.com/ava-dataset/trainval/7g37N3eoQ9s.mkv +https://s3.amazonaws.com/ava-dataset/trainval/7nHkh4sP5Ks.mkv +https://s3.amazonaws.com/ava-dataset/trainval/8JSxLhDMGtE.mkv +https://s3.amazonaws.com/ava-dataset/trainval/8nO5FFbIAog.webm +https://s3.amazonaws.com/ava-dataset/trainval/9IF8uTRrWAM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/9eAOr_ttXp0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/9mLYmkonWZQ.mkv +https://s3.amazonaws.com/ava-dataset/trainval/B1MAUxpKaV8.mkv +https://s3.amazonaws.com/ava-dataset/trainval/BCiuXAuCKAU.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/BY3sZmvUp-0.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/C25wkwAMB-w.mkv +https://s3.amazonaws.com/ava-dataset/trainval/C3qk4yAMANk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/CG98XdYsgrA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/E7JcKooKVsM.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/Feu1_8NazPE.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/G5Yr20A5z_Q.mkv +https://s3.amazonaws.com/ava-dataset/trainval/HTYT2vF-j_w.mkv +https://s3.amazonaws.com/ava-dataset/trainval/HV0H6oc4Kvs.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Hi8QeP_VPu0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/HymKCzQJbB8.mkv +https://s3.amazonaws.com/ava-dataset/trainval/I8j6Xq2B5ys.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/IKdBLciu_-A.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/J1jDc2rTJlg.mkv +https://s3.amazonaws.com/ava-dataset/trainval/JNb4nWexD0I.mkv +https://s3.amazonaws.com/ava-dataset/trainval/KWoSGtglCms.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Kb1fduj-jdY.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/Ksd1JQFHYWA.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/LIavUJVrXaI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/LrDT25hmApw.mkv +https://s3.amazonaws.com/ava-dataset/trainval/N5UD8FGzDek.mkv +https://s3.amazonaws.com/ava-dataset/trainval/O5m_0Yay4EU.mkv +https://s3.amazonaws.com/ava-dataset/trainval/OfMdakd4bHI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/P90hF2S1JzA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/PNZQ2UJfyQE.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/PcFEhUKhN6g.mkv +https://s3.amazonaws.com/ava-dataset/trainval/QotkBTEePI8.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Rm518TUhbRY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/S0tkhGJjwLA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/SHBMiL5f_3Q.mkv +https://s3.amazonaws.com/ava-dataset/trainval/TCmNvNLRWrc.mkv +https://s3.amazonaws.com/ava-dataset/trainval/TcB0IFBwk-k.mkv +https://s3.amazonaws.com/ava-dataset/trainval/UOfuzrwkclM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/U_WzY2k8IBM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/UgZFdrNT6W0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/UsLnxI_zGpY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Vmef_8MY46w.mkv +https://s3.amazonaws.com/ava-dataset/trainval/WVde9pyaHg4.mkv +https://s3.amazonaws.com/ava-dataset/trainval/YYWdB7h1INo.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Ytga8ciKWJc.mkv +https://s3.amazonaws.com/ava-dataset/trainval/_a9SWtcaNj8.mkv +https://s3.amazonaws.com/ava-dataset/trainval/_mAfwH6i90E.mkv +https://s3.amazonaws.com/ava-dataset/trainval/aDEYi1OG0vU.mkv +https://s3.amazonaws.com/ava-dataset/trainval/b5pRYl_djbs.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/bAVXp1oGjHA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/cKA-qeZuH_w.mkv +https://s3.amazonaws.com/ava-dataset/trainval/cWYJHb25EVs.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/cc4y-yYm5Ao.mkv +https://s3.amazonaws.com/ava-dataset/trainval/dMH8L7mqCNI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/gjdgj04FzR0.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/hbYvDvJrpNk.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/iSlDMboCSao.mkv +https://s3.amazonaws.com/ava-dataset/trainval/jBs_XYHI7gM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/jI0HIlSsa3s.mkv +https://s3.amazonaws.com/ava-dataset/trainval/jgAwJ0RqmYg.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/jqZpiHlJUig.mkv +https://s3.amazonaws.com/ava-dataset/trainval/kplbKz3_fZk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/l-jxh8gpxuY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/lWXhqIAvarw.mkv +https://s3.amazonaws.com/ava-dataset/trainval/mfsbYdLx9wE.mkv +https://s3.amazonaws.com/ava-dataset/trainval/mkcDANJjDcM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/oq_bufAhyl8.mkv +https://s3.amazonaws.com/ava-dataset/trainval/phVLLTMzmKk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/plkJ45_-pMk.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/qpoWHELxL-4.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/qrkff49p4E4.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/rFgb2ECMcrY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/rJKeqfTlAeY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/rk8Xm0EAOWs.mkv +https://s3.amazonaws.com/ava-dataset/trainval/skiZueh4lfY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/t0V4drbYDnc.mkv +https://s3.amazonaws.com/ava-dataset/trainval/t1LXrJOvPDg.mkv +https://s3.amazonaws.com/ava-dataset/trainval/tt0t_a1EDCE.mkv +https://s3.amazonaws.com/ava-dataset/trainval/uq_HBsvP548.mkv +https://s3.amazonaws.com/ava-dataset/trainval/uzPI7FcF79U.mkv +https://s3.amazonaws.com/ava-dataset/trainval/vfjywN5CN0Y.mkv +https://s3.amazonaws.com/ava-dataset/trainval/wogRuPNBUi8.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/x-6CtPWVi6E.mkv +https://s3.amazonaws.com/ava-dataset/trainval/xO4ABy2iOQA.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/xp67EC-Hvwk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/y7ncweROe9U.mkv +https://s3.amazonaws.com/ava-dataset/trainval/yo-Kg2YxlZs.mkv +https://s3.amazonaws.com/ava-dataset/trainval/yqImJuC5UzI.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/yvgCGJ6vfkY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/z3kgrh0L_80.mkv +https://s3.amazonaws.com/ava-dataset/trainval/zR725veL-DI.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v.txt" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v.txt" new file mode 100644 index 0000000..31ebe31 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v.txt" @@ -0,0 +1,29 @@ +55Ihr6uVIDA.mkv +914yZXz-iRs.mkv +9Y_l9NsnYE0.mp4 +BXCh3r-pPAM.mkv +CMCPhm2L400.mkv +Di1MG6auDYo.mkv +Gvp-cj3bmIY.webm +IzvOYVMltkI.mp4 +KHHgQ_Pe4cI.mkv +NO2esmws190.mkv +O_NYCUhZ9zw.mp4 +QCLQYnt3aMo.webm +TEQ9sAj-DPo.mp4 +UOyyTUX5Vo4.mkv +WSPvfxtqisg.mkv +XpGRS72ghag.mkv +_7oWZq_s_Sk.mkv +_eBah6c5kyA.mkv +fpprSy6AzKk.mkv +l2XO3tQk8lI.mkv +lDmLcWWBp1E.mkv +om_83F5VwTQ.mp4 +qx2vAO5ofmo.mp4 +rXFlJbXyZyc.mkv +sNQJfYvhcPk.mp4 +u1ltv6r14KQ.mkv +uNT6HrrnqPU.webm +xeGWXqSvC-8.webm +z-fsLpGHq6o.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v_pro" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v_pro" new file mode 100644 index 0000000..8a64543 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/enter_v_pro" @@ -0,0 +1,29 @@ +https://s3.amazonaws.com/ava-dataset/trainval/55Ihr6uVIDA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/914yZXz-iRs.mkv +https://s3.amazonaws.com/ava-dataset/trainval/9Y_l9NsnYE0.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/BXCh3r-pPAM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/CMCPhm2L400.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Di1MG6auDYo.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Gvp-cj3bmIY.webm +https://s3.amazonaws.com/ava-dataset/trainval/IzvOYVMltkI.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/KHHgQ_Pe4cI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/NO2esmws190.mkv +https://s3.amazonaws.com/ava-dataset/trainval/O_NYCUhZ9zw.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/QCLQYnt3aMo.webm +https://s3.amazonaws.com/ava-dataset/trainval/TEQ9sAj-DPo.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/UOyyTUX5Vo4.mkv +https://s3.amazonaws.com/ava-dataset/trainval/WSPvfxtqisg.mkv +https://s3.amazonaws.com/ava-dataset/trainval/XpGRS72ghag.mkv +https://s3.amazonaws.com/ava-dataset/trainval/_7oWZq_s_Sk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/_eBah6c5kyA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/fpprSy6AzKk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/l2XO3tQk8lI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/lDmLcWWBp1E.mkv +https://s3.amazonaws.com/ava-dataset/trainval/om_83F5VwTQ.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/qx2vAO5ofmo.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/rXFlJbXyZyc.mkv +https://s3.amazonaws.com/ava-dataset/trainval/sNQJfYvhcPk.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/u1ltv6r14KQ.mkv +https://s3.amazonaws.com/ava-dataset/trainval/uNT6HrrnqPU.webm +https://s3.amazonaws.com/ava-dataset/trainval/xeGWXqSvC-8.webm +https://s3.amazonaws.com/ava-dataset/trainval/z-fsLpGHq6o.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t.txt" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t.txt" new file mode 100644 index 0000000..4971412 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t.txt" @@ -0,0 +1,52 @@ +-IELREHX_js.mp4 +2E_e8JlvTlg.mkv +2qQs3Y9OJX0.mkv +9IF8uTRrWAM.mkv +9bK05eBt1GM.mp4 +9mLYmkonWZQ.mkv +9tyiDEYiWiA.mkv +B1MAUxpKaV8.mkv +C3qk4yAMANk.mkv +CG98XdYsgrA.mkv +Ie35yEssHko.mkv +JNb4nWexD0I.mkv +KWoSGtglCms.mkv +KWoSGtglCms.mkv +OfMdakd4bHI.mkv +OfMdakd4bHI.mkv +PNZQ2UJfyQE.mp4 +PcFEhUKhN6g.mkv +TM5MPJIq1Is.mkv +TM5MPJIq1Is.mkv +UgZFdrNT6W0.mkv +UgZFdrNT6W0.mkv +UgZFdrNT6W0.mkv +UgZFdrNT6W0.mkv +VsYPP2I0aUQ.mkv +XglAvHaEtHY.mp4 +Ytga8ciKWJc.mkv +_ithRWANKB0.mp4 +aMYcLyh9OhU.mkv +cLiJgvrDlWw.mp4 +eA55_shhKko.mkv +fZs-yXm-uUs.mp4 +iSlDMboCSao.mkv +jBs_XYHI7gM.mkv +lWXhqIAvarw.mkv +lWXhqIAvarw.mkv +miB-wo2PfLI.mkv +phrYEKv0rmw.mkv +pieVIsGmLsc.mkv +qrkff49p4E4.mp4 +qrkff49p4E4.mp4 +rk8Xm0EAOWs.mkv +rk8Xm0EAOWs.mkv +t0V4drbYDnc.mkv +tt0t_a1EDCE.mkv +x-6CtPWVi6E.mkv +x-6CtPWVi6E.mkv +xO4ABy2iOQA.mp4 +xO4ABy2iOQA.mp4 +xp67EC-Hvwk.mkv +yMtGmGa8KZ0.mkv +yo-Kg2YxlZs.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t_pro" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t_pro" new file mode 100644 index 0000000..a409947 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_t_pro" @@ -0,0 +1,52 @@ +https://s3.amazonaws.com/ava-dataset/trainval/-IELREHX_js.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/2E_e8JlvTlg.mkv +https://s3.amazonaws.com/ava-dataset/trainval/2qQs3Y9OJX0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/9IF8uTRrWAM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/9bK05eBt1GM.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/9mLYmkonWZQ.mkv +https://s3.amazonaws.com/ava-dataset/trainval/9tyiDEYiWiA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/B1MAUxpKaV8.mkv +https://s3.amazonaws.com/ava-dataset/trainval/C3qk4yAMANk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/CG98XdYsgrA.mkv +https://s3.amazonaws.com/ava-dataset/trainval/Ie35yEssHko.mkv +https://s3.amazonaws.com/ava-dataset/trainval/JNb4nWexD0I.mkv +https://s3.amazonaws.com/ava-dataset/trainval/KWoSGtglCms.mkv +https://s3.amazonaws.com/ava-dataset/trainval/KWoSGtglCms.mkv +https://s3.amazonaws.com/ava-dataset/trainval/OfMdakd4bHI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/OfMdakd4bHI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/PNZQ2UJfyQE.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/PcFEhUKhN6g.mkv +https://s3.amazonaws.com/ava-dataset/trainval/TM5MPJIq1Is.mkv +https://s3.amazonaws.com/ava-dataset/trainval/TM5MPJIq1Is.mkv +https://s3.amazonaws.com/ava-dataset/trainval/UgZFdrNT6W0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/UgZFdrNT6W0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/UgZFdrNT6W0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/UgZFdrNT6W0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/VsYPP2I0aUQ.mkv +https://s3.amazonaws.com/ava-dataset/trainval/XglAvHaEtHY.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/Ytga8ciKWJc.mkv +https://s3.amazonaws.com/ava-dataset/trainval/_ithRWANKB0.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/aMYcLyh9OhU.mkv +https://s3.amazonaws.com/ava-dataset/trainval/cLiJgvrDlWw.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/eA55_shhKko.mkv +https://s3.amazonaws.com/ava-dataset/trainval/fZs-yXm-uUs.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/iSlDMboCSao.mkv +https://s3.amazonaws.com/ava-dataset/trainval/jBs_XYHI7gM.mkv +https://s3.amazonaws.com/ava-dataset/trainval/lWXhqIAvarw.mkv +https://s3.amazonaws.com/ava-dataset/trainval/lWXhqIAvarw.mkv +https://s3.amazonaws.com/ava-dataset/trainval/miB-wo2PfLI.mkv +https://s3.amazonaws.com/ava-dataset/trainval/phrYEKv0rmw.mkv +https://s3.amazonaws.com/ava-dataset/trainval/pieVIsGmLsc.mkv +https://s3.amazonaws.com/ava-dataset/trainval/qrkff49p4E4.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/qrkff49p4E4.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/rk8Xm0EAOWs.mkv +https://s3.amazonaws.com/ava-dataset/trainval/rk8Xm0EAOWs.mkv +https://s3.amazonaws.com/ava-dataset/trainval/t0V4drbYDnc.mkv +https://s3.amazonaws.com/ava-dataset/trainval/tt0t_a1EDCE.mkv +https://s3.amazonaws.com/ava-dataset/trainval/x-6CtPWVi6E.mkv +https://s3.amazonaws.com/ava-dataset/trainval/x-6CtPWVi6E.mkv +https://s3.amazonaws.com/ava-dataset/trainval/xO4ABy2iOQA.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/xO4ABy2iOQA.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/xp67EC-Hvwk.mkv +https://s3.amazonaws.com/ava-dataset/trainval/yMtGmGa8KZ0.mkv +https://s3.amazonaws.com/ava-dataset/trainval/yo-Kg2YxlZs.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v.txt" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v.txt" new file mode 100644 index 0000000..f3b8fd2 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v.txt" @@ -0,0 +1,12 @@ +9Y_l9NsnYE0.mp4 +KVq6If6ozMY.mkv +QCLQYnt3aMo.webm +XpGRS72ghag.mkv +XpGRS72ghag.mkv +ZosVdkY76FU.mkv +ZosVdkY76FU.mkv +lDmLcWWBp1E.mkv +qx2vAO5ofmo.mp4 +tghXjom3120.mkv +xeGWXqSvC-8.webm +yn9WN9lsHRE.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v_pro" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v_pro" new file mode 100644 index 0000000..ea3ecf2 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/exit_v_pro" @@ -0,0 +1,12 @@ +https://s3.amazonaws.com/ava-dataset/trainval/9Y_l9NsnYE0.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/KVq6If6ozMY.mkv +https://s3.amazonaws.com/ava-dataset/trainval/QCLQYnt3aMo.webm +https://s3.amazonaws.com/ava-dataset/trainval/XpGRS72ghag.mkv +https://s3.amazonaws.com/ava-dataset/trainval/XpGRS72ghag.mkv +https://s3.amazonaws.com/ava-dataset/trainval/ZosVdkY76FU.mkv +https://s3.amazonaws.com/ava-dataset/trainval/ZosVdkY76FU.mkv +https://s3.amazonaws.com/ava-dataset/trainval/lDmLcWWBp1E.mkv +https://s3.amazonaws.com/ava-dataset/trainval/qx2vAO5ofmo.mp4 +https://s3.amazonaws.com/ava-dataset/trainval/tghXjom3120.mkv +https://s3.amazonaws.com/ava-dataset/trainval/xeGWXqSvC-8.webm +https://s3.amazonaws.com/ava-dataset/trainval/yn9WN9lsHRE.mkv diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/tmp.py" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/tmp.py" new file mode 100644 index 0000000..196a955 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-download/tmp.py" @@ -0,0 +1,9 @@ +f1 = open("exit_t.txt") +str1 = "https://s3.amazonaws.com/ava-dataset/trainval/" + +with open("exit_t_pro", "w", encoding="utf-8") as f2: + for i in f1.readlines(): + f2.write(str1 + i) + + +f1.close() diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-extra.sh" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-extra.sh" new file mode 100644 index 0000000..92a440a --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava-data-extra.sh" @@ -0,0 +1,126 @@ +# IN_DATA_DIR="../../data/ava/videos" +# OUT_DATA_DIR="../../data/ava/videos_15min" + +# if [[ ! -d "${OUT_DATA_DIR}" ]]; then +# echo "${OUT_DATA_DIR} doesn't exist. Creating it."; +# mkdir -p ${OUT_DATA_DIR} +# fi + +# for video in $(ls -A1 -U ${IN_DATA_DIR}/*) +# do +# out_name="${OUT_DATA_DIR}/${video##*/}" +# if [ ! -f "${out_name}" ]; then +# ffmpeg -ss 900 -t 901 -i "${video}" "${out_name}" +# fi +# done + +目录结构 +|--ava + |--enter-train + |--enter-val + |--exit-train + |--exit-val + |--short_videos + |--enter-train + |--enter-val + |--exit-train + |--exit-val + |--frames + |--enter-train + |--enter-val + |--exit-train + |--exit-val + + +for dir in `cat dir.log`; do + cd $dir; + IN_DATA_DIR="./${dir}" + OUT_DATA_DIR="../short_videos/${dir}" + + if [[ ! -d "${OUT_DATA_DIR}" ]]; then + echo "${OUT_DATA_DIR} doesn't exist. Creating it."; + mkdir -p ${OUT_DATA_DIR} + fi + + i = 2 + for line in `cat *.csv` # csv + do + echo line $i:$line + youtube_id=`echo $line | cut -d ',' -f1` + video_type=`echo $line | cut -d ',' -f2` + keyframe=`echo $line | cut -d ',' -f3` + video_name = "${youtube_id}.${video_type}" + # smoking eating carryingbag updownstairs others holding cloth + start_time=`exp $keyframe -2` + end_time=`exp $keyframe +2` + # enter/exit 的特殊需求 + start_time=`exp $keyframe -2` + end_time=`exp $keyframe +2` + + ffmpeg -ss "${start_time}" -t 4 -i "${video_name}" "${OUT_DATA_DIR}/${video_name}" + + let "i=$i+1" + done + + cd .. +done + +for dir in `cat dir.log`; +do + +IN_DATA_DIR="./short_videos" +OUT_DATA_DIR="./frames/${dir}" + +if [[ ! -d "${OUT_DATA_DIR}" ]]; then + echo "${OUT_DATA_DIR} doesn't exist. Creating it."; + mkdir -p ${OUT_DATA_DIR} +fi + +i = 2 +for line in `cat $1` # csv +do + echo line $i:$line + youtube_id=`echo $line | cut -d ',' -f1` + video_type=`echo $line | cut -d ',' -f2` + keyframe=`echo $line | cut -d ',' -f3` + video_name = "${youtube_id}.${video_type}" + # smoking eating carryingbag updownstairs others holding cloth + start_time=`exp $keyframe -2` + end_time=`exp $keyframe +2` + # enter/exit 的特殊需求 + start_time=`exp $keyframe -2` + end_time=`exp $keyframe +2` + + ffmpeg -ss "${start_time}" -t 4 -i "${IN_DATA_DIR}/${video_name}" -codec copy "${OUT_DATA_DIR}/${video_name}" + + let "i=$i+1" +done + +echo "Finish cutting videos ! " +echo "Starting extracting frames ! " + +if [[ ! -d "${OUT_DATA_DIR}" ]]; then + echo "${OUT_DATA_DIR} doesn't exist. Creating it."; + mkdir -p ${OUT_DATA_DIR} +fi + +for video in $(ls -A1 -U ${IN_DATA_DIR}/*) +do + video_name=${video##*/} + + if [[ $video_name = *".webm" ]]; then + video_name=${video_name::-5} + else + video_name=${video_name::-4} + fi + + out_video_dir=${OUT_DATA_DIR}/${video_name}/ + mkdir -p "${out_video_dir}" + + out_name="${out_video_dir}/${video_name}_%06d.jpg" + + ffmpeg -i "${video}" -r 30 -q:v 1 "${out_name}" +done + + +echo "done extracting ! " \ No newline at end of file diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1.pbtxt" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1.pbtxt" new file mode 100644 index 0000000..d400eff --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1.pbtxt" @@ -0,0 +1,400 @@ +label { + name: "bend/bow (at the waist)" + label_id: 1 + label_type: PERSON_MOVEMENT +} +label { + name: "crawl" + label_id: 2 + label_type: PERSON_MOVEMENT +} +label { + name: "crouch/kneel" + label_id: 3 + label_type: PERSON_MOVEMENT +} +label { + name: "dance" + label_id: 4 + label_type: PERSON_MOVEMENT +} +label { + name: "fall down" + label_id: 5 + label_type: PERSON_MOVEMENT +} +label { + name: "get up" + label_id: 6 + label_type: PERSON_MOVEMENT +} +label { + name: "jump/leap" + label_id: 7 + label_type: PERSON_MOVEMENT +} +label { + name: "lie/sleep" + label_id: 8 + label_type: PERSON_MOVEMENT +} +label { + name: "martial art" + label_id: 9 + label_type: PERSON_MOVEMENT +} +label { + name: "run/jog" + label_id: 10 + label_type: PERSON_MOVEMENT +} +label { + name: "sit" + label_id: 11 + label_type: PERSON_MOVEMENT +} +label { + name: "stand" + label_id: 12 + label_type: PERSON_MOVEMENT +} +label { + name: "swim" + label_id: 13 + label_type: PERSON_MOVEMENT +} +label { + name: "walk" + label_id: 14 + label_type: PERSON_MOVEMENT +} +label { + name: "answer phone" + label_id: 15 + label_type: OBJECT_MANIPULATION +} +label { + name: "brush teeth" + label_id: 16 + label_type: OBJECT_MANIPULATION +} +label { + name: "carry/hold (an object)" + label_id: 17 + label_type: OBJECT_MANIPULATION +} +label { + name: "catch (an object)" + label_id: 18 + label_type: OBJECT_MANIPULATION +} +label { + name: "chop" + label_id: 19 + label_type: OBJECT_MANIPULATION +} +label { + name: "climb (e.g., a mountain)" + label_id: 20 + label_type: OBJECT_MANIPULATION +} +label { + name: "clink glass" + label_id: 21 + label_type: OBJECT_MANIPULATION +} +label { + name: "close (e.g., a door, a box)" + label_id: 22 + label_type: OBJECT_MANIPULATION +} +label { + name: "cook" + label_id: 23 + label_type: OBJECT_MANIPULATION +} +label { + name: "cut" + label_id: 24 + label_type: OBJECT_MANIPULATION +} +label { + name: "dig" + label_id: 25 + label_type: OBJECT_MANIPULATION +} +label { + name: "dress/put on clothing" + label_id: 26 + label_type: OBJECT_MANIPULATION +} +label { + name: "drink" + label_id: 27 + label_type: OBJECT_MANIPULATION +} +label { + name: "drive (e.g., a car, a truck)" + label_id: 28 + label_type: OBJECT_MANIPULATION +} +label { + name: "eat" + label_id: 29 + label_type: OBJECT_MANIPULATION +} +label { + name: "enter" + label_id: 30 + label_type: OBJECT_MANIPULATION +} +label { + name: "exit" + label_id: 31 + label_type: OBJECT_MANIPULATION +} +label { + name: "extract" + label_id: 32 + label_type: OBJECT_MANIPULATION +} +label { + name: "fishing" + label_id: 33 + label_type: OBJECT_MANIPULATION +} +label { + name: "hit (an object)" + label_id: 34 + label_type: OBJECT_MANIPULATION +} +label { + name: "kick (an object)" + label_id: 35 + label_type: OBJECT_MANIPULATION +} +label { + name: "lift/pick up" + label_id: 36 + label_type: OBJECT_MANIPULATION +} +label { + name: "listen (e.g., to music)" + label_id: 37 + label_type: OBJECT_MANIPULATION +} +label { + name: "open (e.g., a window, a car door)" + label_id: 38 + label_type: OBJECT_MANIPULATION +} +label { + name: "paint" + label_id: 39 + label_type: OBJECT_MANIPULATION +} +label { + name: "play board game" + label_id: 40 + label_type: OBJECT_MANIPULATION +} +label { + name: "play musical instrument" + label_id: 41 + label_type: OBJECT_MANIPULATION +} +label { + name: "play with pets" + label_id: 42 + label_type: OBJECT_MANIPULATION +} +label { + name: "point to (an object)" + label_id: 43 + label_type: OBJECT_MANIPULATION +} +label { + name: "press" + label_id: 44 + label_type: OBJECT_MANIPULATION +} +label { + name: "pull (an object)" + label_id: 45 + label_type: OBJECT_MANIPULATION +} +label { + name: "push (an object)" + label_id: 46 + label_type: OBJECT_MANIPULATION +} +label { + name: "put down" + label_id: 47 + label_type: OBJECT_MANIPULATION +} +label { + name: "read" + label_id: 48 + label_type: OBJECT_MANIPULATION +} +label { + name: "ride (e.g., a bike, a car, a horse)" + label_id: 49 + label_type: OBJECT_MANIPULATION +} +label { + name: "row boat" + label_id: 50 + label_type: OBJECT_MANIPULATION +} +label { + name: "sail boat" + label_id: 51 + label_type: OBJECT_MANIPULATION +} +label { + name: "shoot" + label_id: 52 + label_type: OBJECT_MANIPULATION +} +label { + name: "shovel" + label_id: 53 + label_type: OBJECT_MANIPULATION +} +label { + name: "smoke" + label_id: 54 + label_type: OBJECT_MANIPULATION +} +label { + name: "stir" + label_id: 55 + label_type: OBJECT_MANIPULATION +} +label { + name: "take a photo" + label_id: 56 + label_type: OBJECT_MANIPULATION +} +label { + name: "text on/look at a cellphone" + label_id: 57 + label_type: OBJECT_MANIPULATION +} +label { + name: "throw" + label_id: 58 + label_type: OBJECT_MANIPULATION +} +label { + name: "touch (an object)" + label_id: 59 + label_type: OBJECT_MANIPULATION +} +label { + name: "turn (e.g., a screwdriver)" + label_id: 60 + label_type: OBJECT_MANIPULATION +} +label { + name: "watch (e.g., TV)" + label_id: 61 + label_type: OBJECT_MANIPULATION +} +label { + name: "work on a computer" + label_id: 62 + label_type: OBJECT_MANIPULATION +} +label { + name: "write" + label_id: 63 + label_type: OBJECT_MANIPULATION +} +label { + name: "fight/hit (a person)" + label_id: 64 + label_type: PERSON_INTERACTION +} +label { + name: "give/serve (an object) to (a person)" + label_id: 65 + label_type: PERSON_INTERACTION +} +label { + name: "grab (a person)" + label_id: 66 + label_type: PERSON_INTERACTION +} +label { + name: "hand clap" + label_id: 67 + label_type: PERSON_INTERACTION +} +label { + name: "hand shake" + label_id: 68 + label_type: PERSON_INTERACTION +} +label { + name: "hand wave" + label_id: 69 + label_type: PERSON_INTERACTION +} +label { + name: "hug (a person)" + label_id: 70 + label_type: PERSON_INTERACTION +} +label { + name: "kick (a person)" + label_id: 71 + label_type: PERSON_INTERACTION +} +label { + name: "kiss (a person)" + label_id: 72 + label_type: PERSON_INTERACTION +} +label { + name: "lift (a person)" + label_id: 73 + label_type: PERSON_INTERACTION +} +label { + name: "listen to (a person)" + label_id: 74 + label_type: PERSON_INTERACTION +} +label { + name: "play with kids" + label_id: 75 + label_type: PERSON_INTERACTION +} +label { + name: "push (another person)" + label_id: 76 + label_type: PERSON_INTERACTION +} +label { + name: "sing to (e.g., self, a person, a group)" + label_id: 77 + label_type: PERSON_INTERACTION +} +label { + name: "take (an object) from (a person)" + label_id: 78 + label_type: PERSON_INTERACTION +} +label { + name: "talk to (e.g., self, a person, a group)" + label_id: 79 + label_type: PERSON_INTERACTION +} +label { + name: "watch (a person)" + label_id: 80 + label_type: PERSON_INTERACTION +} diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1_for_activitynet_2018.pbtxt" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1_for_activitynet_2018.pbtxt" new file mode 100644 index 0000000..5e2c485 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_action_list_v2.1_for_activitynet_2018.pbtxt" @@ -0,0 +1,240 @@ +item { + name: "bend/bow (at the waist)" + id: 1 +} +item { + name: "crouch/kneel" + id: 3 +} +item { + name: "dance" + id: 4 +} +item { + name: "fall down" + id: 5 +} +item { + name: "get up" + id: 6 +} +item { + name: "jump/leap" + id: 7 +} +item { + name: "lie/sleep" + id: 8 +} +item { + name: "martial art" + id: 9 +} +item { + name: "run/jog" + id: 10 +} +item { + name: "sit" + id: 11 +} +item { + name: "stand" + id: 12 +} +item { + name: "swim" + id: 13 +} +item { + name: "walk" + id: 14 +} +item { + name: "answer phone" + id: 15 +} +item { + name: "carry/hold (an object)" + id: 17 +} +item { + name: "climb (e.g., a mountain)" + id: 20 +} +item { + name: "close (e.g., a door, a box)" + id: 22 +} +item { + name: "cut" + id: 24 +} +item { + name: "dress/put on clothing" + id: 26 +} +item { + name: "drink" + id: 27 +} +item { + name: "drive (e.g., a car, a truck)" + id: 28 +} +item { + name: "eat" + id: 29 +} +item { + name: "enter" + id: 30 +} +item { + name: "hit (an object)" + id: 34 +} +item { + name: "lift/pick up" + id: 36 +} +item { + name: "listen (e.g., to music)" + id: 37 +} +item { + name: "open (e.g., a window, a car door)" + id: 38 +} +item { + name: "play musical instrument" + id: 41 +} +item { + name: "point to (an object)" + id: 43 +} +item { + name: "pull (an object)" + id: 45 +} +item { + name: "push (an object)" + id: 46 +} +item { + name: "put down" + id: 47 +} +item { + name: "read" + id: 48 +} +item { + name: "ride (e.g., a bike, a car, a horse)" + id: 49 +} +item { + name: "sail boat" + id: 51 +} +item { + name: "shoot" + id: 52 +} +item { + name: "smoke" + id: 54 +} +item { + name: "take a photo" + id: 56 +} +item { + name: "text on/look at a cellphone" + id: 57 +} +item { + name: "throw" + id: 58 +} +item { + name: "touch (an object)" + id: 59 +} +item { + name: "turn (e.g., a screwdriver)" + id: 60 +} +item { + name: "watch (e.g., TV)" + id: 61 +} +item { + name: "work on a computer" + id: 62 +} +item { + name: "write" + id: 63 +} +item { + name: "fight/hit (a person)" + id: 64 +} +item { + name: "give/serve (an object) to (a person)" + id: 65 +} +item { + name: "grab (a person)" + id: 66 +} +item { + name: "hand clap" + id: 67 +} +item { + name: "hand shake" + id: 68 +} +item { + name: "hand wave" + id: 69 +} +item { + name: "hug (a person)" + id: 70 +} +item { + name: "kiss (a person)" + id: 72 +} +item { + name: "lift (a person)" + id: 73 +} +item { + name: "listen to (a person)" + id: 74 +} +item { + name: "push (another person)" + id: 76 +} +item { + name: "sing to (e.g., self, a person, a group)" + id: 77 +} +item { + name: "take (an object) from (a person)" + id: 78 +} +item { + name: "talk to (e.g., self, a person, a group)" + id: 79 +} +item { + name: "watch (a person)" + id: 80 +} diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_included_timestamps_v2.1.txt" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_included_timestamps_v2.1.txt" new file mode 100644 index 0000000..0475eb7 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_included_timestamps_v2.1.txt" @@ -0,0 +1,897 @@ +0902 +0903 +0904 +0905 +0906 +0907 +0908 +0909 +0910 +0911 +0912 +0913 +0914 +0915 +0916 +0917 +0918 +0919 +0920 +0921 +0922 +0923 +0924 +0925 +0926 +0927 +0928 +0929 +0930 +0931 +0932 +0933 +0934 +0935 +0936 +0937 +0938 +0939 +0940 +0941 +0942 +0943 +0944 +0945 +0946 +0947 +0948 +0949 +0950 +0951 +0952 +0953 +0954 +0955 +0956 +0957 +0958 +0959 +0960 +0961 +0962 +0963 +0964 +0965 +0966 +0967 +0968 +0969 +0970 +0971 +0972 +0973 +0974 +0975 +0976 +0977 +0978 +0979 +0980 +0981 +0982 +0983 +0984 +0985 +0986 +0987 +0988 +0989 +0990 +0991 +0992 +0993 +0994 +0995 +0996 +0997 +0998 +0999 +1000 +1001 +1002 +1003 +1004 +1005 +1006 +1007 +1008 +1009 +1010 +1011 +1012 +1013 +1014 +1015 +1016 +1017 +1018 +1019 +1020 +1021 +1022 +1023 +1024 +1025 +1026 +1027 +1028 +1029 +1030 +1031 +1032 +1033 +1034 +1035 +1036 +1037 +1038 +1039 +1040 +1041 +1042 +1043 +1044 +1045 +1046 +1047 +1048 +1049 +1050 +1051 +1052 +1053 +1054 +1055 +1056 +1057 +1058 +1059 +1060 +1061 +1062 +1063 +1064 +1065 +1066 +1067 +1068 +1069 +1070 +1071 +1072 +1073 +1074 +1075 +1076 +1077 +1078 +1079 +1080 +1081 +1082 +1083 +1084 +1085 +1086 +1087 +1088 +1089 +1090 +1091 +1092 +1093 +1094 +1095 +1096 +1097 +1098 +1099 +1100 +1101 +1102 +1103 +1104 +1105 +1106 +1107 +1108 +1109 +1110 +1111 +1112 +1113 +1114 +1115 +1116 +1117 +1118 +1119 +1120 +1121 +1122 +1123 +1124 +1125 +1126 +1127 +1128 +1129 +1130 +1131 +1132 +1133 +1134 +1135 +1136 +1137 +1138 +1139 +1140 +1141 +1142 +1143 +1144 +1145 +1146 +1147 +1148 +1149 +1150 +1151 +1152 +1153 +1154 +1155 +1156 +1157 +1158 +1159 +1160 +1161 +1162 +1163 +1164 +1165 +1166 +1167 +1168 +1169 +1170 +1171 +1172 +1173 +1174 +1175 +1176 +1177 +1178 +1179 +1180 +1181 +1182 +1183 +1184 +1185 +1186 +1187 +1188 +1189 +1190 +1191 +1192 +1193 +1194 +1195 +1196 +1197 +1198 +1199 +1200 +1201 +1202 +1203 +1204 +1205 +1206 +1207 +1208 +1209 +1210 +1211 +1212 +1213 +1214 +1215 +1216 +1217 +1218 +1219 +1220 +1221 +1222 +1223 +1224 +1225 +1226 +1227 +1228 +1229 +1230 +1231 +1232 +1233 +1234 +1235 +1236 +1237 +1238 +1239 +1240 +1241 +1242 +1243 +1244 +1245 +1246 +1247 +1248 +1249 +1250 +1251 +1252 +1253 +1254 +1255 +1256 +1257 +1258 +1259 +1260 +1261 +1262 +1263 +1264 +1265 +1266 +1267 +1268 +1269 +1270 +1271 +1272 +1273 +1274 +1275 +1276 +1277 +1278 +1279 +1280 +1281 +1282 +1283 +1284 +1285 +1286 +1287 +1288 +1289 +1290 +1291 +1292 +1293 +1294 +1295 +1296 +1297 +1298 +1299 +1300 +1301 +1302 +1303 +1304 +1305 +1306 +1307 +1308 +1309 +1310 +1311 +1312 +1313 +1314 +1315 +1316 +1317 +1318 +1319 +1320 +1321 +1322 +1323 +1324 +1325 +1326 +1327 +1328 +1329 +1330 +1331 +1332 +1333 +1334 +1335 +1336 +1337 +1338 +1339 +1340 +1341 +1342 +1343 +1344 +1345 +1346 +1347 +1348 +1349 +1350 +1351 +1352 +1353 +1354 +1355 +1356 +1357 +1358 +1359 +1360 +1361 +1362 +1363 +1364 +1365 +1366 +1367 +1368 +1369 +1370 +1371 +1372 +1373 +1374 +1375 +1376 +1377 +1378 +1379 +1380 +1381 +1382 +1383 +1384 +1385 +1386 +1387 +1388 +1389 +1390 +1391 +1392 +1393 +1394 +1395 +1396 +1397 +1398 +1399 +1400 +1401 +1402 +1403 +1404 +1405 +1406 +1407 +1408 +1409 +1410 +1411 +1412 +1413 +1414 +1415 +1416 +1417 +1418 +1419 +1420 +1421 +1422 +1423 +1424 +1425 +1426 +1427 +1428 +1429 +1430 +1431 +1432 +1433 +1434 +1435 +1436 +1437 +1438 +1439 +1440 +1441 +1442 +1443 +1444 +1445 +1446 +1447 +1448 +1449 +1450 +1451 +1452 +1453 +1454 +1455 +1456 +1457 +1458 +1459 +1460 +1461 +1462 +1463 +1464 +1465 +1466 +1467 +1468 +1469 +1470 +1471 +1472 +1473 +1474 +1475 +1476 +1477 +1478 +1479 +1480 +1481 +1482 +1483 +1484 +1485 +1486 +1487 +1488 +1489 +1490 +1491 +1492 +1493 +1494 +1495 +1496 +1497 +1498 +1499 +1500 +1501 +1502 +1503 +1504 +1505 +1506 +1507 +1508 +1509 +1510 +1511 +1512 +1513 +1514 +1515 +1516 +1517 +1518 +1519 +1520 +1521 +1522 +1523 +1524 +1525 +1526 +1527 +1528 +1529 +1530 +1531 +1532 +1533 +1534 +1535 +1536 +1537 +1538 +1539 +1540 +1541 +1542 +1543 +1544 +1545 +1546 +1547 +1548 +1549 +1550 +1551 +1552 +1553 +1554 +1555 +1556 +1557 +1558 +1559 +1560 +1561 +1562 +1563 +1564 +1565 +1566 +1567 +1568 +1569 +1570 +1571 +1572 +1573 +1574 +1575 +1576 +1577 +1578 +1579 +1580 +1581 +1582 +1583 +1584 +1585 +1586 +1587 +1588 +1589 +1590 +1591 +1592 +1593 +1594 +1595 +1596 +1597 +1598 +1599 +1600 +1601 +1602 +1603 +1604 +1605 +1606 +1607 +1608 +1609 +1610 +1611 +1612 +1613 +1614 +1615 +1616 +1617 +1618 +1619 +1620 +1621 +1622 +1623 +1624 +1625 +1626 +1627 +1628 +1629 +1630 +1631 +1632 +1633 +1634 +1635 +1636 +1637 +1638 +1639 +1640 +1641 +1642 +1643 +1644 +1645 +1646 +1647 +1648 +1649 +1650 +1651 +1652 +1653 +1654 +1655 +1656 +1657 +1658 +1659 +1660 +1661 +1662 +1663 +1664 +1665 +1666 +1667 +1668 +1669 +1670 +1671 +1672 +1673 +1674 +1675 +1676 +1677 +1678 +1679 +1680 +1681 +1682 +1683 +1684 +1685 +1686 +1687 +1688 +1689 +1690 +1691 +1692 +1693 +1694 +1695 +1696 +1697 +1698 +1699 +1700 +1701 +1702 +1703 +1704 +1705 +1706 +1707 +1708 +1709 +1710 +1711 +1712 +1713 +1714 +1715 +1716 +1717 +1718 +1719 +1720 +1721 +1722 +1723 +1724 +1725 +1726 +1727 +1728 +1729 +1730 +1731 +1732 +1733 +1734 +1735 +1736 +1737 +1738 +1739 +1740 +1741 +1742 +1743 +1744 +1745 +1746 +1747 +1748 +1749 +1750 +1751 +1752 +1753 +1754 +1755 +1756 +1757 +1758 +1759 +1760 +1761 +1762 +1763 +1764 +1765 +1766 +1767 +1768 +1769 +1770 +1771 +1772 +1773 +1774 +1775 +1776 +1777 +1778 +1779 +1780 +1781 +1782 +1783 +1784 +1785 +1786 +1787 +1788 +1789 +1790 +1791 +1792 +1793 +1794 +1795 +1796 +1797 +1798 diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_test_excluded_timestamps_v2.1.csv" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_test_excluded_timestamps_v2.1.csv" new file mode 100644 index 0000000..2082715 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/ava_v2.1/ava_test_excluded_timestamps_v2.1.csv" @@ -0,0 +1,66 @@ +-FLn0aeA6EU,0913 +72MzYjWz_7g,1184 +72MzYjWz_7g,1185 +72MzYjWz_7g,1186 +72MzYjWz_7g,1187 +72MzYjWz_7g,1188 +72MzYjWz_7g,1189 +72MzYjWz_7g,1190 +72MzYjWz_7g,1191 +72MzYjWz_7g,1192 +72MzYjWz_7g,1193 +72MzYjWz_7g,1197 +72MzYjWz_7g,1198 +72MzYjWz_7g,1199 +72MzYjWz_7g,1200 +BnIFkfDhJ2w,1600 +BnIFkfDhJ2w,1604 +GElolK2jG50,1623 +GQxKfbvL3mg,1434 +IIyYHprTP58,1530 +WMFTBgYWJS8,1286 +WMFTBgYWJS8,1287 +XOe9GeojzCs,1180 +bNP8Q_8u89A,1101 +bNP8Q_8u89A,1490 +bNP8Q_8u89A,1494 +bNP8Q_8u89A,1495 +bNP8Q_8u89A,1505 +bNP8Q_8u89A,1506 +bNP8Q_8u89A,1542 +bNP8Q_8u89A,1543 +ipBRBABLSAk,0936 +ipBRBABLSAk,0937 +ipBRBABLSAk,0938 +ipBRBABLSAk,0939 +ipBRBABLSAk,0940 +ipBRBABLSAk,0941 +ipBRBABLSAk,0942 +ipBRBABLSAk,0944 +ipBRBABLSAk,0946 +ipBRBABLSAk,0947 +ipBRBABLSAk,1538 +ipBRBABLSAk,1539 +ipBRBABLSAk,1540 +ipBRBABLSAk,1541 +ipBRBABLSAk,1542 +ipBRBABLSAk,1546 +ipBRBABLSAk,1548 +ipBRBABLSAk,1552 +ipBRBABLSAk,1553 +ipBRBABLSAk,1558 +ipBRBABLSAk,1559 +ipBRBABLSAk,1560 +ipBRBABLSAk,1561 +ipBRBABLSAk,1562 +ipBRBABLSAk,1567 +ipBRBABLSAk,1568 +ipBRBABLSAk,1569 +ipBRBABLSAk,1570 +ipBRBABLSAk,1571 +ipBRBABLSAk,1589 +ipBRBABLSAk,1590 +ipBRBABLSAk,1592 +ipBRBABLSAk,1598 +ipBRBABLSAk,1600 +zm78XnWN7MU,1607 diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/frame_path.csv" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/frame_path.csv" new file mode 100644 index 0000000..e69de29 diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/frame_path.sh" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/frame_path.sh" new file mode 100644 index 0000000..63cf1ea --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data/frame_path.sh" @@ -0,0 +1,17 @@ +#!/bin/bash + +cd ./val/cloth +for clip in `ls` +do + cd $clip + + # path num_frame label + path="./val/cloth/${clip}" + num_frame=`ls -l |grep "^-"|wc -l` + label=1 + echo "${path} ${num_frame} ${label}" >> ../../val_cloth.txt + + cd .. +done +echo "val_cloth is done!!!" + diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data_prepare.ipynb" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data_prepare.ipynb" new file mode 100644 index 0000000..35a8b20 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/data_prepare.ipynb" @@ -0,0 +1,1903 @@ +{ + "nbformat": 4, + "nbformat_minor": 0, + "metadata": { + "colab": { + "name": "data-prepare.ipynb", + "provenance": [], + "collapsed_sections": [] + }, + "kernelspec": { + "name": "python3", + "display_name": "Python 3" + }, + "language_info": { + "name": "python" + } + }, + "cells": [ + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "A2b5-15KnlCz", + "outputId": "145d56e8-9bf4-40f9-d901-4c3476df9638" + }, + "source": [ + "!ls" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "stream", + "text": [ + "sample_data test.csv train.csv validate.csv\n" + ], + "name": "stdout" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "fab7JHSRoAWq" + }, + "source": [ + "import pandas as pd \n", + "import numpy as np \n", + "import math\n", + "import os" + ], + "execution_count": 1, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "YDV2mW9epD3w" + }, + "source": [ + "df_train = pd.read_csv('train.csv')\n", + "df_test = pd.read_csv('test.csv')\n", + "df_val = pd.read_csv('validate.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "rWKI4EZgjoQn" + }, + "source": [ + "li = ['eating burger','eating cake','eating carrots','eating chips','eating doughnuts','eating hotdog','eating ice cream','eating spaghetti','eating watermelon']\n", + "\n", + "def change2eating(label):\n", + " if label in li:\n", + " return 'eating'\n", + " return label\n", + "df_train['label'] = df_train['label'].apply(change2eating)\n", + "df_test['label'] = df_test['label'].apply(change2eating)\n", + "df_val['label'] = df_val['label'].apply(change2eating)\n" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "alsCY0etsbeh", + "outputId": "1654e1d6-4cb3-4aca-b694-33a89dd62f29" + }, + "source": [ + "df_train.head()" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
labelyoutube_idtime_starttime_endsplit
0testifying---QUuC4vJs8494train
1eating spaghetti--3ouPhoy2A2030train
2dribbling basketball--4-0ihtnBU5868train
3playing tennis--56QUhyDQM185195train
4tap dancing--6q_33gNew132142train
\n", + "
" + ], + "text/plain": [ + " label youtube_id time_start time_end split\n", + "0 testifying ---QUuC4vJs 84 94 train\n", + "1 eating spaghetti --3ouPhoy2A 20 30 train\n", + "2 dribbling basketball --4-0ihtnBU 58 68 train\n", + "3 playing tennis --56QUhyDQM 185 195 train\n", + "4 tap dancing --6q_33gNew 132 142 train" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 10 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "iquBGXDxo_L2", + "outputId": "58292b4b-0804-4cec-b91b-54547d550f53" + }, + "source": [ + "# df_see = df_train.groupby(['label'])\n", + "df_val[df_val['label']=='smoking'].head()" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
labelyoutube_idtime_starttime_endsplit
60smoking-0vzKnJrPQs96106validate
111smoking-3D9cHBM4bo2737validate
446smoking-cui-aLqI3g541551validate
850smoking0y_OCH1FnSU010validate
1088smoking1o-qGrLLihw2131validate
\n", + "
" + ], + "text/plain": [ + " label youtube_id time_start time_end split\n", + "60 smoking -0vzKnJrPQs 96 106 validate\n", + "111 smoking -3D9cHBM4bo 27 37 validate\n", + "446 smoking -cui-aLqI3g 541 551 validate\n", + "850 smoking 0y_OCH1FnSU 0 10 validate\n", + "1088 smoking 1o-qGrLLihw 21 31 validate" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 6 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "I9wrFwkfonBw" + }, + "source": [ + "\n", + "def t(label_name):\n", + " df_1 = df_train[df_train['label']==label_name]\n", + " df_2 = df_val[df_val['label']==label_name]\n", + " df_3 = df_test[df_test['label']==label_name]\n", + " return pd.concat([df_1,df_2,df_3])\n", + "\n" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "uhzRR-h9dJFM" + }, + "source": [ + "\n", + "df_val_eat = df_val[df_val['label']=='eating']\n", + "df_val_smoke = df_val[df_val['label']=='smoking']\n", + "df_val_cloth = df_val[df_val['label']=='folding clothes']\n", + "\n", + "df_val_all = pd.concat([df_val_eat,df_val_smoke,df_val_cloth])\n", + "df_val_all.sort_values('youtube_id').to_csv('kinectics_val_sort_id.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "Xnv0QbZ4h2EV" + }, + "source": [ + "df_test_eat = df_test[df_test['label']=='eating']\n", + "df_test_smoke = df_test[df_test['label']=='smoking']\n", + "df_test_cloth = df_test[df_test['label']=='folding clothes']\n", + "\n", + "df_test_all = pd.concat([df_test_eat,df_test_smoke,df_test_cloth])\n", + "df_test_all.sort_values('youtube_id').to_csv('kinectics_test_sort_id.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "fLTcIE2K7srC" + }, + "source": [ + "### smoking 7" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "LGXk7R044Atm", + "outputId": "15ad0fe8-f31a-4a6a-c3a5-70819dfabd19" + }, + "source": [ + "df_smoke = t('smoking')\n", + "df_smoke.head()" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
labelyoutube_idtime_starttime_endsplit
150smoking-3oeeJz_bjk919train
578smoking-EDIE7Ywri0108118train
802smoking-Jt8UtIUgDg1929train
847smoking-KmI1S3A9Rc252262train
967smoking-N4zRqR3Gqo010train
\n", + "
" + ], + "text/plain": [ + " label youtube_id time_start time_end split\n", + "150 smoking -3oeeJz_bjk 9 19 train\n", + "578 smoking -EDIE7Ywri0 108 118 train\n", + "802 smoking -Jt8UtIUgDg 19 29 train\n", + "847 smoking -KmI1S3A9Rc 252 262 train\n", + "967 smoking -N4zRqR3Gqo 0 10 train" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 8 + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "NmG5kVxM74Bp" + }, + "source": [ + "### eating 2" + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "3tA9bhxv6MgJ", + "outputId": "2038cc8a-3354-4459-a8ec-a4837fa81ba6" + }, + "source": [ + "df_eat = t('eating')\n", + "df_eat.head()" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
labelyoutube_idtime_starttime_endsplit
1eating--3ouPhoy2A2030train
41eating-0R6wpipD-c3545train
49eating-0aDlftNdyw280290train
145eating-3gv9XDUOFA1929train
169eating-4CxOUPL6o44959train
\n", + "
" + ], + "text/plain": [ + " label youtube_id time_start time_end split\n", + "1 eating --3ouPhoy2A 20 30 train\n", + "41 eating -0R6wpipD-c 35 45 train\n", + "49 eating -0aDlftNdyw 280 290 train\n", + "145 eating -3gv9XDUOFA 19 29 train\n", + "169 eating -4CxOUPL6o4 49 59 train" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 10 + } + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "DDXRaYzx77bN" + }, + "source": [ + "### cloth 1\n", + "c000 Holding some clothes \n", + "\n", + "c001 Putting clothes somewhere \n", + "\n", + "c002 Taking some clothes from somewhere \n", + "\n", + "c003 Throwing clothes somewhere\n", + "\n", + "c004 Tidying some clothes\n", + "\n", + "c005 Washing some clothes\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "3GKmcwR6kF6S" + }, + "source": [ + "df_cloth = pd.read_csv(\"/content/Charades_v1_train.csv\")\n" + ], + "execution_count": 23, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 639 + }, + "id": "C7G7A9Nukohw", + "outputId": "24605d2d-8ec7-4d8e-d7f0-9cba720fc6b4" + }, + "source": [ + "df_cloth.head()" + ], + "execution_count": 24, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idsubjectscenequalityrelevanceverifiedscriptobjectsdescriptionsactionslength
046GP8HR43Kitchen6.07.0YesA person cooking on a stove while watching som...food;stove;windowA person cooks food on a stove before looking ...c092 11.90 21.20;c147 0.00 12.6024.83
1N11GT0KZ7Stairs6.07.0YesOne person opens up a folded blanket, then sne...blanket;broom;floorPerson at the bottom of the staircase shakes a...c098 8.60 14.20;c075 0.00 11.70;c127 0.00 15.2...18.33
20IH696RE8Bedroom6.05.0YesA person is seen leaving a cabinet. They then ...book;box;cabinet;shelfA person is standing in a bedroom. They walk o...NaN30.25
3KRF68YA10Laundry room6.07.0YesA person runs into their laundry room. They gr...clothes;door;phoneA person runs in and shuts door. The person gr...c018 22.60 27.80;c141 4.10 9.60;c148 10.30 25....30.33
4MJO7C6RE8Kitchen6.06.0YesA person runs into their pantry holding a bott...cup;phoneA person runs in place while holding a bottle ...c015 0.00 32.00;c107 0.00 32.0031.38
\n", + "
" + ], + "text/plain": [ + " id subject ... actions length\n", + "0 46GP8 HR43 ... c092 11.90 21.20;c147 0.00 12.60 24.83\n", + "1 N11GT 0KZ7 ... c098 8.60 14.20;c075 0.00 11.70;c127 0.00 15.2... 18.33\n", + "2 0IH69 6RE8 ... NaN 30.25\n", + "3 KRF68 YA10 ... c018 22.60 27.80;c141 4.10 9.60;c148 10.30 25.... 30.33\n", + "4 MJO7C 6RE8 ... c015 0.00 32.00;c107 0.00 32.00 31.38\n", + "\n", + "[5 rows x 11 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 24 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "frziAWwNkbyc" + }, + "source": [ + "cloth_list = ['c000','c001','c002','c003','c004','c005']\n", + "def cloth(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return 0\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in cloth_list:\n", + " return i.split(\" \")[0]\n", + " return 0\n" + ], + "execution_count": 25, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "apbU3bZYlMCo" + }, + "source": [ + "df_cloth_act = df_cloth[[\"id\",\"actions\"]]" + ], + "execution_count": 26, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "DhrNurRzlL6H", + "outputId": "1c6c0065-1204-43d8-ed28-5e1231f01af1" + }, + "source": [ + "df_cloth_act['act_cloth_exist'] = df_cloth_act['actions'].apply(cloth)" + ], + "execution_count": 27, + "outputs": [ + { + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \"\"\"Entry point for launching an IPython kernel.\n" + ], + "name": "stderr" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "B0cCbs_clLxR" + }, + "source": [ + "def cloth_start(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in cloth_list:\n", + " return i.split(\" \")[1]\n", + " return -1\n", + " \n", + "def cloth_end(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in cloth_list:\n", + " return i.split(\" \")[2]\n", + " return -1\n", + "\n", + "def cloth_time(action):\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in cloth_list:\n", + " return round(float(i.split(\" \")[2])-float(i.split(\" \")[1]),2)\n", + " return -1" + ], + "execution_count": 28, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "ocdDUwdHmCL9", + "outputId": "b078b4d0-1e9b-42f1-958a-cf245a9d3d7b" + }, + "source": [ + "df_cloth_act['start_time'] = df_cloth_act['actions'].apply(cloth_start)\n", + "df_cloth_act['end_time'] = df_cloth_act['actions'].apply(cloth_end)\n", + "df_cloth_act['dtime'] = df_cloth_act['actions'].apply(cloth_time)\n", + "df_tmp = df_cloth_act[df_cloth_act['act_cloth_exist']!=0]\n", + "df_tmp[[\"id\",\"start_time\",\"dtime\"]].to_csv('cloth.csv')" + ], + "execution_count": 29, + "outputs": [ + { + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \"\"\"Entry point for launching an IPython kernel.\n", + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \n", + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " This is separate from the ipykernel package so we can avoid doing imports until\n" + ], + "name": "stderr" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "PTKIFc816Wp4", + "outputId": "8ed2433e-b133-4ee5-8728-26cbefa0dfb8" + }, + "source": [ + "df_cloth = t('folding clothes')\n", + "df_cloth.head()" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
labelyoutube_idtime_starttime_endsplit
853folding clothes-KtT7Q730Yg818train
1349folding clothes-U2IQ5qOGmQ414train
1549folding clothes-YKDJrc2p5w919train
2563folding clothes-qlJmXRti-g152162train
2608folding clothes-riGpxoagdg93103train
\n", + "
" + ], + "text/plain": [ + " label youtube_id time_start time_end split\n", + "853 folding clothes -KtT7Q730Yg 8 18 train\n", + "1349 folding clothes -U2IQ5qOGmQ 4 14 train\n", + "1549 folding clothes -YKDJrc2p5w 9 19 train\n", + "2563 folding clothes -qlJmXRti-g 152 162 train\n", + "2608 folding clothes -riGpxoagdg 93 103 train" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 11 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "v9482sYiXTGN" + }, + "source": [ + "df_eat_smoke_cloth = pd.concat([df_eat,df_smoke,df_cloth])\n", + "df_kinetics_id = df_eat_smoke_cloth.drop_duplicates(['youtube_id'])[['youtube_id']]" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "ocz3tqSvkluU" + }, + "source": [ + "df_kinetics_id.sort_values('youtube_id').to_csv('kinectics_sort_id.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "z1JdZ6AbXczh" + }, + "source": [ + "df_kinetics_id.to_csv('kinetics_id.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kD0Qehn4FMYy" + }, + "source": [ + "### ava enter 5/30" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "Te6z9Zs6612G" + }, + "source": [ + "df_ava_train = pd.read_csv('ava_train_v2.1.csv')\n", + "df_ava_val = pd.read_csv('ava_val_v2.1.csv')\n", + "df_ava_train = df_ava_train.rename(columns={\"id\":\"youtube_id\"})\n", + "df_ava_val = df_ava_val.rename(columns={\"id\":\"youtube_id\"})" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 206 + }, + "id": "TRI5mvYgTpBM", + "outputId": "9ced2662-837f-4c98-9c77-878a12e1f4d8" + }, + "source": [ + "df_ava_train.head()" + ], + "execution_count": null, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
youtube_idabcdelabelf
0-5KQ66BBWC49020.0770.1510.2830.811801
1-5KQ66BBWC49020.0770.1510.2830.81191
2-5KQ66BBWC49020.2260.0320.3660.497120
3-5KQ66BBWC49020.2260.0320.3660.497170
4-5KQ66BBWC49020.2260.0320.3660.497800
\n", + "
" + ], + "text/plain": [ + " youtube_id a b c d e label f\n", + "0 -5KQ66BBWC4 902 0.077 0.151 0.283 0.811 80 1\n", + "1 -5KQ66BBWC4 902 0.077 0.151 0.283 0.811 9 1\n", + "2 -5KQ66BBWC4 902 0.226 0.032 0.366 0.497 12 0\n", + "3 -5KQ66BBWC4 902 0.226 0.032 0.366 0.497 17 0\n", + "4 -5KQ66BBWC4 902 0.226 0.032 0.366 0.497 80 0" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 12 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "cjCUGhkGWD5a" + }, + "source": [ + "df_ava_train = df_ava_train[[\"youtube_id\",\"label\"]]\n", + "df_ava_val = df_ava_val[[\"youtube_id\",\"label\"]]" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "ArUJrRrFRshx" + }, + "source": [ + "# 先把txt分开，变成df\n", + "df_tmp = pd.DataFrame(columns=['youtube_id','type',])\n", + "with open('/content/ava_file_names_trainval_v2.1.txt') as f:\n", + " for i in f.readlines():\n", + " s = i.split('.')\n", + " id = s[0]\n", + " tp = s[1].strip('\\n') \n", + " new = pd.DataFrame({\"youtube_id\":[id], \"type\":[tp]})\n", + " df_tmp = df_tmp.append(new,ignore_index=True)\n" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "-hf8b_myYZdc" + }, + "source": [ + "df_enter_train = df_ava_train[df_ava_train['label']==30]\n", + "df_enter_val = df_ava_val[df_ava_val['label']==30]" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "akkgjQWSXb3u" + }, + "source": [ + "# 合并两个df\n", + "df_enter_train_type = df_enter_train.merge(df_tmp, on=\"youtube_id\", how=\"inner\")\n", + "df_enter_val_type = df_enter_val.merge(df_tmp, on=\"youtube_id\", how=\"inner\")" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "dJ625uK9aNH1" + }, + "source": [ + "# 去重\n", + "df_enter_train_type = df_enter_train_type.drop_duplicates(['youtube_id','a'])[['youtube_id','type','a']]\n", + "df_enter_val_type=df_enter_val_type.drop_duplicates(['youtube_id','a'])[['youtube_id','type','a']]" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "u8rXrKv9asYm" + }, + "source": [ + "# 存入csv\n", + "# df_enter_val_type.to_csv('enter_v.csv')\n", + "# df_enter_train_type.to_csv('enter_t.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "Yk_YN9YbhE9b" + }, + "source": [ + "# 存入csv\n", + "df_enter_val_type.to_csv('enter_v_time.csv')\n", + "df_enter_train_type.to_csv('enter_t_time.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "SncTTE_MFZnM" + }, + "source": [ + "### ava leave 4/31" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "RbePfrNftbEY" + }, + "source": [ + "df_exit_train = df_ava_train[df_ava_train['label']==31]\n", + "df_exit_val = df_ava_val[df_ava_val['label']==31]" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "LX3rdoiQtjQ1" + }, + "source": [ + "# 合并两个df\n", + "df_exit_train_type = df_exit_train.merge(df_tmp, on=\"youtube_id\", how=\"inner\")\n", + "df_exit_val_type = df_exit_val.merge(df_tmp, on=\"youtube_id\", how=\"inner\")\n", + "# 去重\n", + "df_exit_train_type = df_exit_train_type.drop_duplicates(['youtube_id','a'])[['youtube_id','type','a']]\n", + "df_exit_val_type=df_exit_val_type.drop_duplicates(['youtube_id','a'])[['youtube_id','type','a']]\n" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "Jlt_60C9uBE8" + }, + "source": [ + "" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "5XD71iKutqTQ" + }, + "source": [ + "# 存入csv\n", + "df_exit_train_type.to_csv('exit_t_time.csv')\n", + "df_exit_val_type.to_csv('exit_v_time.csv')" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "A2NWZWykuAIj" + }, + "source": [ + "### Holding a bag 6\n", + "c020 Holding a bag" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "3GO6nmNLwiPn" + }, + "source": [ + "df_bag = pd.read_csv(\"/content/Charades_v1_train.csv\")\n" + ], + "execution_count": 2, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "uf3vP2irnETH" + }, + "source": [ + "" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "mPgZ2D54xfVg" + }, + "source": [ + "bag_list = ['c020']\n", + "cloth_list = ['c000','c001','c002','c003','c004','c005']\n", + "def bag(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return 0\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in bag_list:\n", + " return i.split(\" \")[0]\n", + " return 0\n" + ], + "execution_count": 6, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "LQomSAnaw_jr" + }, + "source": [ + "df_bag_act = df_bag[[\"id\",\"actions\"]]" + ], + "execution_count": 7, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "jCRBZxkYzGaL", + "outputId": "d4881b7e-b60e-4305-a1b9-39cb7d0c8568" + }, + "source": [ + "df_bag_act['act_bag_exist'] = df_bag_act['actions'].apply(bag)" + ], + "execution_count": 8, + "outputs": [ + { + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \"\"\"Entry point for launching an IPython kernel.\n" + ], + "name": "stderr" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "SIetyoYJ22y2" + }, + "source": [ + "def bag_start(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in bag_list:\n", + " return i.split(\" \")[1]\n", + " return -1\n" + ], + "execution_count": 9, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "qU96Sgvd3fYc" + }, + "source": [ + "def bag_end(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in bag_list:\n", + " return i.split(\" \")[2]\n", + " return -1\n" + ], + "execution_count": 10, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "iSmvNeNrh2TZ" + }, + "source": [ + "def bag_time(action):\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in bag_list:\n", + " return round(float(i.split(\" \")[2])-float(i.split(\" \")[1]),2)\n", + " return -1" + ], + "execution_count": 19, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "D_p_0gk128k9", + "outputId": "2d2462ed-268f-4083-aa34-0221e4fd18eb" + }, + "source": [ + "df_bag_act['start_time'] = df_bag_act['actions'].apply(bag_start)\n", + "df_bag_act['end_time'] = df_bag_act['actions'].apply(bag_end)\n", + "df_bag_act['dtime'] = df_bag_act['actions'].apply(bag_time)" + ], + "execution_count": 20, + "outputs": [ + { + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \"\"\"Entry point for launching an IPython kernel.\n", + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \n", + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " This is separate from the ipykernel package so we can avoid doing imports until\n" + ], + "name": "stderr" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "Ct7jbkwgzee2" + }, + "source": [ + "df_tmp = df_bag_act[df_bag_act['act_bag_exist']!=0]" + ], + "execution_count": 21, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "J1U9248l3LJi" + }, + "source": [ + "df_tmp[[\"id\",\"start_time\",\"dtime\"]].to_csv('bag.csv')" + ], + "execution_count": 22, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "OrzyWuV33_Ay" + }, + "source": [ + "" + ], + "execution_count": null, + "outputs": [] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "_h6130lbGGEu" + }, + "source": [ + "### 切分视频 \n", + "华为云 解压+切分：Kinectics\n", + "\n", + "eating smoking 进度较慢。\n", + "\n", + "pip下载ffmpeg-python\n", + "
\n", + "
\n", + "\n", + "\n", + "enter 和 leave（exit）进度较快，可以在电脑切分。\n", + "\n", + "cloth 和 bag数据集已经下载，但是还没有检查能否使用。\n", + "\n", + "stairs还没有找到\n", + "\n", + "\n", + "\n" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "h5aaGPS8npdL" + }, + "source": [ + "### others\n", + "c018\n", + "c026\n", + "c041\n", + "c053\n", + "c083\n", + "c094\n", + "c103\n", + "c115\n", + "c122\n", + "c134\n", + "\n" + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "_PO3a6UrnoY3" + }, + "source": [ + "others_list = [\"c018\",\"c026\",\"c041\",\"c053\",\"c083\",\"c094\",\"c103\",\"c115\",\"c122\",\"c134\"]" + ], + "execution_count": 32, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "oRYhP7x0pcUO" + }, + "source": [ + "df_others = df_bag" + ], + "execution_count": 36, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 639 + }, + "id": "YapkdZDTpe5w", + "outputId": "1d07d2c4-2081-4953-9eaa-37c73a3d560f" + }, + "source": [ + "df_others.head()" + ], + "execution_count": 37, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
idsubjectscenequalityrelevanceverifiedscriptobjectsdescriptionsactionslength
046GP8HR43Kitchen6.07.0YesA person cooking on a stove while watching som...food;stove;windowA person cooks food on a stove before looking ...c092 11.90 21.20;c147 0.00 12.6024.83
1N11GT0KZ7Stairs6.07.0YesOne person opens up a folded blanket, then sne...blanket;broom;floorPerson at the bottom of the staircase shakes a...c098 8.60 14.20;c075 0.00 11.70;c127 0.00 15.2...18.33
20IH696RE8Bedroom6.05.0YesA person is seen leaving a cabinet. They then ...book;box;cabinet;shelfA person is standing in a bedroom. They walk o...NaN30.25
3KRF68YA10Laundry room6.07.0YesA person runs into their laundry room. They gr...clothes;door;phoneA person runs in and shuts door. The person gr...c018 22.60 27.80;c141 4.10 9.60;c148 10.30 25....30.33
4MJO7C6RE8Kitchen6.06.0YesA person runs into their pantry holding a bott...cup;phoneA person runs in place while holding a bottle ...c015 0.00 32.00;c107 0.00 32.0031.38
\n", + "
" + ], + "text/plain": [ + " id subject ... actions length\n", + "0 46GP8 HR43 ... c092 11.90 21.20;c147 0.00 12.60 24.83\n", + "1 N11GT 0KZ7 ... c098 8.60 14.20;c075 0.00 11.70;c127 0.00 15.2... 18.33\n", + "2 0IH69 6RE8 ... NaN 30.25\n", + "3 KRF68 YA10 ... c018 22.60 27.80;c141 4.10 9.60;c148 10.30 25.... 30.33\n", + "4 MJO7C 6RE8 ... c015 0.00 32.00;c107 0.00 32.00 31.38\n", + "\n", + "[5 rows x 11 columns]" + ] + }, + "metadata": { + "tags": [] + }, + "execution_count": 37 + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "ct0Y0o70uGa4" + }, + "source": [ + "def others(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return 0\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in others_list:\n", + " return i.split(\" \")[0]\n", + " return 0" + ], + "execution_count": 38, + "outputs": [] + }, + { + "cell_type": "code", + "metadata": { + "id": "dWzlc7IQFIwC", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "aa4db5b7-d526-4855-803b-71b930afc3ea" + }, + "source": [ + "df_others_act = df_others[[\"id\",\"actions\"]]\n", + "df_others_act['act_others_exist'] = df_others_act['actions'].apply(others)\n", + "def others_start(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in others_list:\n", + " return i.split(\" \")[1]\n", + " return -1\n", + " \n", + "def others_end(action):\n", + " # 去除所有的nan\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in others_list:\n", + " return i.split(\" \")[2]\n", + " return -1\n", + "\n", + "def others_time(action):\n", + " if action != action:\n", + " return -1\n", + " tmp = action.split(\";\")\n", + " for i in tmp:\n", + " if i.split(\" \")[0] in others_list:\n", + " return round(float(i.split(\" \")[2])-float(i.split(\" \")[1]),2)\n", + " return -1\n", + "\n" + ], + "execution_count": 39, + "outputs": [ + { + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \n" + ], + "name": "stderr" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "0FhwNBFmpY3v", + "outputId": "c245225f-f49e-4da2-b6a4-625a81e1a79d" + }, + "source": [ + "df_others_act['start_time'] = df_others_act['actions'].apply(others_start)\n", + "df_others_act['end_time'] = df_others_act['actions'].apply(others_end)\n", + "df_others_act['dtime'] = df_others_act['actions'].apply(others_time)\n", + "df_tmp = df_others_act[df_others_act['act_others_exist']!=0]\n", + "df_tmp[[\"id\",\"start_time\",\"dtime\"]].to_csv('others.csv')" + ], + "execution_count": 40, + "outputs": [ + { + "output_type": "stream", + "text": [ + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \"\"\"Entry point for launching an IPython kernel.\n", + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:2: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " \n", + "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:3: SettingWithCopyWarning: \n", + "A value is trying to be set on a copy of a slice from a DataFrame.\n", + "Try using .loc[row_indexer,col_indexer] = value instead\n", + "\n", + "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n", + " This is separate from the ipykernel package so we can avoid doing imports until\n" + ], + "name": "stderr" + } + ] + }, + { + "cell_type": "code", + "metadata": { + "id": "1WlMxRnSple7" + }, + "source": [ + "" + ], + "execution_count": null, + "outputs": [] + } + ] +} \ No newline at end of file diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/main.ipynb" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/main.ipynb" new file mode 100644 index 0000000..e281ae5 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/main.ipynb" @@ -0,0 +1 @@ +{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["import cv2 \r\n","import math \r\n","import matplotlib.pyplot as plt \r\n","%matplotlib inline\r\n","import pandas as pd\r\n","from keras.preprocessing import image \r\n","import numpy as np \r\n","from keras.utils import np_utils\r\n","from skimage.transform import resize \r\n","from sklearn.model_selection import train_test_split\r\n","from glob import glob\r\n","from tqdm import tqdm\r\n","import moxing as mox\r\n","import glob\r\n","import os\r\n","\r\n"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["train_image = []\r\n","\r\n","for i in tqdm(range(df_train.shape[0])):\r\n"," dir = df_train['path'][i]\r\n"," \r\n"," img = image.load_img(dir+\"/000005.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n"," \r\n"," img = image.load_img(dir+\"/000010.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n","\r\n"," img = image.load_img(dir+\"/000015.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n"," \r\n"," img = image.load_img(dir+\"/000020.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n"," \r\n","X = np.array(train_image)\r\n","\r\n","X.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["mox.file.copy_parallel('obs://mlpr-classification-data/data/val.csv', 'val.csv')\n","mox.file.copy_parallel('obs://mlpr-classification-data/data/train.csv', 'train.csv')\n","df_train = pd.read_csv('train.csv')\n","df_val = pd.read_csv(\"val.csv\")"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["# !unzip -d train train.zip\n","# !unzip -d val val.zip"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["mox.file.copy_parallel('obs://mlpr-classification-data/data/val/val_frames.zip', 'val.zip')"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["train_img = []"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["val_image = []\r\n","for i in tqdm(range(df_val.shape[0])):\r\n"," dir = df_val['path'][i]\r\n"," cls = df_val['class'][i]\r\n"," \r\n"," if df_val['num_frame'][i]==0:\r\n"," continue\r\n","\r\n"," img = image.load_img(dir+\"/000005.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," val_image.append(img)\r\n"," df_new= df_new.append(pd.DataFrame({'img_path':[dir+\"/000005.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n"," img = image.load_img(dir+\"/000010.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," val_image.append(img)\r\n"," df_new= df_new.append(pd.DataFrame({'img_path':[dir+\"/000010.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n","\r\n"," img = image.load_img(dir+\"/000015.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," val_image.append(img)\r\n"," df_new= df_new.append(pd.DataFrame({'img_path':[dir+\"/000015.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n"," img = image.load_img(dir+\"/000020.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," val_image.append(img)\r\n"," df_new= df_new.append(pd.DataFrame({'img_path':[dir+\"/000020.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n"," \r\n"," \r\n","X_val = np.array(val_image)\r\n","X_val.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["t = df_train[df_train['num_frame']!=0][['class']]"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["df_new = pd.DataFrame(columns=['img_path', 'class'])"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["df_new.head()"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["df_new_train = pd.DataFrame(columns=['img_path', 'class'])"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["train_image = []\r\n","for i in tqdm(range(df_train.shape[0])):\r\n"," dir = df_train['path'][i]\r\n"," cls = df_train['class'][i]\r\n"," \r\n"," if df_train['num_frame'][i]==0:\r\n"," continue\r\n","\r\n","\r\n"," img = image.load_img(dir+\"/000005.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n"," df_new_train= df_new_train.append(pd.DataFrame({'img_path':[dir+\"/000005.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n"," img = image.load_img(dir+\"/000010.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n"," df_new_train= df_new_train.append(pd.DataFrame({'img_path':[dir+\"/000010.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n","\r\n"," img = image.load_img(dir+\"/000015.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n"," df_new_train= df_new_train.append(pd.DataFrame({'img_path':[dir+\"/000015.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n"," img = image.load_img(dir+\"/000020.jpg\", target_size=(224,224,3))\r\n"," img = image.img_to_array(img)\r\n"," img = img/255\r\n"," train_image.append(img)\r\n"," df_new_train= df_new_train.append(pd.DataFrame({'img_path':[dir+\"/000020.jpg\"],'class':[cls]}), ignore_index=True)\r\n","\r\n"," \r\n","X_train = np.array(train_image)\r\n","\r\n","X_train.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["df_new_train.head()"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["y_train = df_new_train['class']\n","y_val = df_new['class']\n","y_train = pd.get_dummies(y_train)\n","y_val = pd.get_dummies(y_val)"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["base_model = VGG16(weights='imagenet', include_top=False)"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["import keras\n","from keras.models import Sequential\n","from keras.applications.vgg16 import VGG16\n","from keras.layers import Dense, InputLayer, Dropout, Flatten\n","from keras.layers import Conv2D, MaxPooling2D, GlobalMaxPooling2D\n","from keras.preprocessing import image\n","import numpy as np\n","import pandas as pd\n","import matplotlib.pyplot as plt\n","from tqdm import tqdm\n","from sklearn.model_selection import train_test_split\n"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["# base_model = VGG16(weights='imagenet', include_top=False)\r\n","\r\n","X_val = base_model.predict(X_val)\r\n","X_val.shape\r\n"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["X_train = base_model.predict(X_train)\r\n","X_train.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["# mox.file.copy_parallel('obs://mlpr-classification-data/data/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5', 'vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5')\n"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["X_train = X_train.reshape(4036, 7*7*512)\n","X_val = X_val.reshape(656, 7*7*512)"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["max = X_train.max()\n","X_train = X_train/max\n","X_val = X_val/max"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["X_train.shape"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["model = Sequential()\r\n","model.add(Dense(1024, activation='relu', input_shape=(25088,)))\r\n","model.add(Dropout(0.5))\r\n","model.add(Dense(512, activation='relu'))\r\n","model.add(Dropout(0.5))\r\n","model.add(Dense(256, activation='relu'))\r\n","model.add(Dropout(0.5))\r\n","model.add(Dense(128, activation='relu'))\r\n","model.add(Dropout(0.5))\r\n","model.add(Dense(8, activation='softmax'))"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["from keras.callbacks import ModelCheckpoint\n","mcp_save = ModelCheckpoint('weight.hdf5', save_best_only=True, monitor='val_loss', mode='min')"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["model.compile(loss='categorical_crossentropy',optimizer='Adam',metrics=['accuracy'])"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["model.fit(X_train, y_train, epochs=200, validation_data=(X_val, y_val), callbacks=[mcp_save], batch_size=128)"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["mox.file.copy_parallel('weight.hdf5','obs://mlpr-classification-data/data/weight.hdf5', )\n"]}],"metadata":{"interpreter":{"hash":"9c3aa38a2d651aa120c9aa3dfa4256cf305d5ea997da8fd3b7d02e7067957313"},"kernelspec":{"display_name":"Python 3.8.6 64-bit","name":"python3"},"language_info":{"name":"python","version":""}},"nbformat":4,"nbformat_minor":4} \ No newline at end of file diff --git "a/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/tmp.ipynb" "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/tmp.ipynb" new file mode 100644 index 0000000..0aff356 --- /dev/null +++ "b/code/2021_spring/\345\212\250\344\275\234\350\257\206\345\210\253-\346\235\250\346\200\235\351\233\250/tmp.ipynb" @@ -0,0 +1 @@ +{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["from keras.models import Sequential\n","from keras.layers import Dense, Dropout, Flatten\n","from keras.layers import Conv2D, MaxPooling2D\n","from keras.preprocessing import image\n","import numpy as np\n","import pandas as pd\n","from tqdm import tqdm\n","from keras.applications.vgg16 import VGG16\n","import cv2\n","import math\n","import os\n","from glob import glob\n","from scipy import stats as s\n","\n"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["base_model = VGG16(weights='imagenet', include_top=False)"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["model = Sequential()\n","model.add(Dense(1024, activation='relu', input_shape=(25088,)))\n","model.add(Dropout(0.5))\n","model.add(Dense(512, activation='relu'))\n","model.add(Dropout(0.5))\n","model.add(Dense(256, activation='relu'))\n","model.add(Dropout(0.5))\n","model.add(Dense(128, activation='relu'))\n","model.add(Dropout(0.5))\n","model.add(Dense(8, activation='softmax'))\n"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["import moxing as mox\n","mox.file.copy_parallel('obs://mlpr-classification-data/data/weight.hdf5', 'weight.hdf5')"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["model.load_weights(\"weight.hdf5\")\n"]},{"cell_type":"code","execution_count":null,"metadata":{"trusted":true},"outputs":[],"source":["model.compile(loss='categorical_crossentropy',optimizer='Adam',metrics=['accuracy'])"]}],"metadata":{"interpreter":{"hash":"9c3aa38a2d651aa120c9aa3dfa4256cf305d5ea997da8fd3b7d02e7067957313"},"kernelspec":{"display_name":"Python 3.8.6 64-bit","name":"python3"},"language_info":{"name":"python","version":""}},"nbformat":4,"nbformat_minor":4} \ No newline at end of file -- Gitee