gabarlacchi

Hi, I used the standard way by applying grad-cam to each frame within the sequence. Since the CNN+LSTM network internally predict the class for each frame, you can then apply...

@teabolt Thanks for the reply. I managed to make what desired with CONV-LSTM and visualize the activations through the time.

Any updates on this? I am using a network such : `inc = InceptionV3( weights=imagenet, include_top=False, pooling=max, input_shape=(shape[0], shape[1], 3) ) for layer in inc.layers: layer.trainable = False model =...

Hi! I am facing exactly the same situation: CNN for features extraction + LSTM for classification (I label a sequence, not each frame). Did you find a way to visualize...

Hi to all, I have the following network in order to classify video sequences composed bu 30 frames. `video = Input(shape=(30,299,299,3)) inc = InceptionV3( weights='imagenet', include_top=False, input_shape=(299, 299, 3) )...

Thanks for the quickly answer! Unluckily I cannot share the videos for privacy reason, I'll try to find a way in next days if there'll always be need. I hope...