Video-Classification-2-Stream-CNN
Video-Classification-2-Stream-CNN copied to clipboard
wadhwasahil
Video Classification using 2 stream CNN
https://github.com/wadhwasahil/Video-Classification-2-Stream-CNN/blob/253db1b5c098538197ca7b1752c63a169a27c022/spatial/spatial_vid2img.py#L32 I stumbled across this error
I'm very appricieted of your work,Now there are some troubles when I use your code.Could you please tell me your work enviroment,so far I can find my mistake. Thank you...
Hi @wadhwasahil , @stillbreeze , As stated in the project's title, I suppose to see your model/network in 2 streams (2 inputs) but I only see spatial and temporal model...
It took around 3 days to train the temporal part. It did not save the temporal weights. Has anybody else faced a similar issue?
sorry, i do not still quite understand in temporal stream code. ufc video's length is different from each other, which makes it produce different length of frames, let's say video...
I am using CNN-M model to train my own data，but the acc is low. Could you push your trained model? Thank you!
In my understanding after reading your codes, optical flows are calculated for the videos in 'trainVidID.txt' and 'testVidID.txt'. And for each video, optical flows are divided into blocks of 50...
Hi there, could you please show which version of TensorFlow and Keras you used? That would save much time for trying different versions and see which could work. ;) Thanks!
Hello - I was wondering what the difference between the two hyperparameters (chunks and batches)? I've been trying to wrap my head around this but can't seem to grasp it.
for chunk in chunks(keys,chunk_size): if flag
