Error in action classification bit

[christinedekock11]

Hi there,

Thanks for this implementation! I realise you're likely not working on this anymore, but I wanted to check if there is an error in the model setup, or if I have misunderstood something. Your action classification bit is as follows:

# Action classification - classify the manouever
        main_output = TimeDistributed(
            Dense(self.dense_units, activation='softmax', kernel_initializer=self.kernel_initializer),
            name='aux_classifier'
        )(aux_output)

From my understanding, the output of the model would be a softmax operation over a 128 dim vector. Based on your sketch, it seems like this should be a standard dense layer with tanh activation, followed by another dense layer with softmax over the 5 categories.

Hope my interpretation is correct - if I have misunderstood something, please let me know!

[michetonu]

Hi @christinedekock11, you are absolutely right, good catch! I made a mistake when refactoring my code to upload it: I set all Dense layer sizes to the same value, but the main output should have a size of 5. Would you like to do a PR to correct it? :)