binhhoangtieu

I got the same error when I use: model.load_weights('c3d-sports1M_weights.h5') Traceback (most recent call last): File "3dcnn.py", line 262, in main() File "3dcnn.py", line 137, in main model.load_weights('c3d-sports1M_weights.h5') File "/home/nghialuan/.local/lib/python3.6/site-packages/keras/models.py", line...

This error may be caused by the number of extracted file is less than 16 (look into this folder F:/UCF-101//Archery/v_Archery_g07_c04)

> thanks，u r right.but why? i used the shell code in ubuntu to extract those frames. Because your video is not long enough, you can change the file "convert_video_to_images.sh" for...

This is number of test samples, you can see this in the ./list/test.list (number of lines). The same with 9537 in line 40. Hope this helps

Here is a [good sample](https://github.com/Hvass-Labs/TensorFlow-Tutorials/blob/master/05_Ensemble_Learning.ipynb) for how to fuse multi networks

According to predict_c3d_ucf101.py, from left to right for each row: true label, class prob for true label, predicted label, class prob for predicted label If you want to use pre-trained,...

Try to change your batch_size?

Yes, solved with my problem because my accuracy is changed after each iteration. I'm not sure about your case.

@zeynepgokce : Check your input data and pre-trained model restoration