tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for 'MaxPool_1' (op: 'MaxPool') with input shapes: [?,1,112,128]. about human-action-recognition-with-keras HOT 4 OPEN

Try Theano backend.

from human-action-recognition-with-keras.

It works, but another error happened:
Using Theano backend.
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
(Subtensor{int64}.0, Elemwise{add,no_inplace}.0, Elemwise{add,no_inplace}.0, Subtensor{int64}.0)
Traceback (most recent call last):
File "HumanActionRecognition.py", line 110, in
model.layers[k].set_weights(weights)
File "/Library/Frameworks/Python.framework/Versions/3.5/lib/python3.5/site-packages/keras/engine/topology.py", line 985, in set_weights
'provided weight shape ' + str(w.shape))
ValueError: Layer weight shape (3, 3, 224, 64) not compatible with provided weight shape (64, 3, 3, 3)

model problem? or keras problem?

from human-action-recognition-with-keras.

i have read the keras's topology.py code, it say that only no parms use provided weight shape, but the model is download from offcial.what i miss?

from human-action-recognition-with-keras.

Hi,
I noticed that in row 36 the pre-trained model whole_model.h5 is used. I can't find it in your depository. Anyone ones where to find it? Thanks.

from human-action-recognition-with-keras.