degardinbruno / human-self-learning-anomaly Goto Github PK
View Code? Open in Web Editor NEWCode for the paper "Human Activity Analysis: Iterative Weak/Self-Supervised Learning Frameworks for Detecting Abnormal Events", IJCB 2020
License: Other
Code for the paper "Human Activity Analysis: Iterative Weak/Self-Supervised Learning Frameworks for Detecting Abnormal Events", IJCB 2020
License: Other
There seems to be no license file uploaded. Kindly upload one. Thanks
Could you give me these csv files which you used in this project? Thanks!
-- **annotation
| |-- strong // Insert here your .csv files to be used by the SS Model
| | |-- train.csv // empty, to be filled by the WS Model and Bayesian Classifier
| | |-- test.csv
| | |-- val.csv
| | |-- unlabeled_set.csv // Same remaining videos unlabeled from the weak, but in C3D raw segment format
| | |-- test_notes.csv
| | -- val_notes.csv |
-- weak // Insert here your .csv files to be used by the WS Model
| |-- train.csv // Small percentage (i.e., 30%) of the original training set
| |-- test.csv
| |-- val.csv
| |-- unlabeled_set.csv // Remaining videos are unlabeled for self-supervision purposes
| |-- test_notes.csv
| `-- val_notes.csv
Hello
I'm in Preprocessing Dataset, I use UBI_FIGHTS dataset.
When running the step2 normalize_videos.py file, it beginning processes the frames as well and then stopping the processes suddenly as the output is shown below:
(venv) sumaya@sumaya-virtual-machine:~/Downloads/human_self_learning_anomaly-master/utils$ python3 normalize_videos.py --root_frames /home/sumaya/Downloads/human_self_learning_anomaly-master/frames --root_sub_videos /home/sumaya/Downloads/human_self_learning_anomaly-master/frames --erase_frames
Normalizing video duration...
1
Moviepy - Building video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_1_0_1_0_1/F_1_0_1_0_1_0.mp4.
Moviepy - Writing video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_1_0_1_0_1/F_1_0_1_0_1_0.mp4
Moviepy - Done !
Moviepy - video ready /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_1_0_1_0_1/F_1_0_1_0_1_0.mp4
Successfully normalized!
Normalizing video duration...
5
Moviepy - Building video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_0.mp4.
Moviepy - Writing video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_0.mp4
Moviepy - Done !
Moviepy - video ready /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_0.mp4
Moviepy - Building video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_1.mp4.
Moviepy - Writing video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_1.mp4
Moviepy - Done !
Moviepy - video ready /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_1.mp4
Moviepy - Building video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_2.mp4.
Moviepy - Writing video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_2.mp4
Moviepy - Done !
Moviepy - video ready /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_2.mp4
Moviepy - Building video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_3.mp4.
Moviepy - Writing video /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_3.mp4
Moviepy - Done !
Moviepy - video ready /home/sumaya/Downloads/human_self_learning_anomaly-master/frames/dataset/F_38_1_2_0_0/F_38_1_2_0_0_3.mp4
Killed
What is the problem?
It was available several days ago, but now the link is down. Thanks in advance :)
Hi,thanks for your great job. I want to get the dataset, but the link seems to be down.
Hello Bruno Degardin,
Really appreciate the amazing effort in the paper and in the code as well.
I tried to run the code but I faced an issue (I am just beginner in the AI field, pardon my silly questions).
We I ran:
1- video_frames -> there was no modification needed
2- normalize_videos -> I had to change frames path, where will read and partition the images.
3- normalize_notes -> I did understand what is the output, because when I run this command
python3 utils/normalize_notes.py --root_csv data/UBI_FIGHTS/annotation --dest_csv data/annotation --fps 30 --duration 16
Could not run, because it is asking for annotation csv files which I did not understand from where to get them, could you please explain it to me?
Thank you a lot
Hello, when I try to run the requirements.txt it always have an issue with some packages not being installed successfully. What problems do you think there may be? I would like to know which python version you were using at the time. Thank you.
Thanks for your wok!I found the video frame level label is not accurate, such as F_51_1_2_0_0, there is a fight in the video from the beginning, but the labeldoesn't start until frame 491.Could you please tell me the reason? Is it because my label extraction is not accurate?
I tried to experiment with this project with small data.
However, during the normalization process, the val_notes.csv test_notes.csv file could not be obtained.
According to Readme, it can be obtained by running the normalize_notes file, but it was each csv file I got.
Can you tell me how to get val_notes and test_notes, and how they are filled?
Are the annotations in normalize_notes the annotations in UBI_FIGHTS?
http://socia-lab.di.ubi.pt/EventDetection is not available
When I run the test.py the program cannot work successfully . It hints me that:
Using TensorFlow backend.
2022-04-10 11:18:38.853189: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library cudart64_101.dll
2022-04-10 11:18:41.601766: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'nvcuda.dll'; dlerror: nvcuda.dll not found
2022-04-10 11:18:41.602005: E tensorflow/stream_executor/cuda/cuda_driver.cc:351] failed call to cuInit: UNKNOWN ERROR (303)
2022-04-10 11:18:41.605862: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: DESKTOP-DNTLE7D
2022-04-10 11:18:41.606161: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: DESKTOP-DNTLE7D
2022-04-10 11:18:41.606971: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
Traceback (most recent call last):
File "D:/human-self-learning-anomaly-master/human-self-learning-anomaly-master/test.py", line 47, in
test(opt.weak_model, opt.strong_model, opt.model_iteration, not opt.val, opt.path_test, opt.path_test_note, pred_gap, opt.features)
File "D:/human-self-learning-anomaly-master/human-self-learning-anomaly-master/test.py", line 14, in test
notes, scores = WC.test(flag_test, iteration, path_test, path_test_note, pred_gap) if model_weak else SC.test(flag_test, iteration, path_test, path_test_note, num_features)
File "D:\human-self-learning-anomaly-master\human-self-learning-anomaly-master\strong_classifier.py", line 294, in test
read_annotation(test_notes, 1) # Load test/val annotations
File "D:\human-self-learning-anomaly-master\human-self-learning-anomaly-master\strong_classifier.py", line 207, in read_annotation
notes_test.append(int(row[0])) if flag_test else notes_train.append(int(row[0]))
ValueError: invalid literal for int() with base 10: '\ufeff'
Can you give me some help?
Hi, thanks for sharing your work.
Frame AUC is usually used. In some work, the AUC of normal and abnormal events is calculated. While others use AUC of the abnormal events only. What did you use in your paper?
Thanks for your excellent work. I would like to know how to run the inference.py? Where I can use the 'root_C3D_dir'? Thank you
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.