Layer (type)                 Output Shape              Param #
=================================================================
conv1 (Conv3D)               (None, 16, 112, 112, 64)  5248
_________________________________________________________________
pool1 (MaxPooling3D)         (None, 16, 56, 56, 64)    0
_________________________________________________________________
conv2 (Conv3D)               (None, 16, 56, 56, 128)   221312
_________________________________________________________________
pool2 (MaxPooling3D)         (None, 8, 28, 28, 128)    0
_________________________________________________________________
conv3a (Conv3D)              (None, 8, 28, 28, 256)    884992
_________________________________________________________________
conv3b (Conv3D)              (None, 8, 28, 28, 256)    1769728
_________________________________________________________________
pool3 (MaxPooling3D)         (None, 4, 14, 14, 256)    0
_________________________________________________________________
conv4a (Conv3D)              (None, 4, 14, 14, 512)    3539456
_________________________________________________________________
conv4b (Conv3D)              (None, 4, 14, 14, 512)    7078400
_________________________________________________________________
pool4 (MaxPooling3D)         (None, 2, 7, 7, 512)      0
_________________________________________________________________
conv5a (Conv3D)              (None, 2, 7, 7, 512)      7078400
_________________________________________________________________
conv5b (Conv3D)              (None, 2, 7, 7, 512)      7078400
_________________________________________________________________
zero_padding3d_1 (ZeroPaddin (None, 2, 9, 9, 512)      0
_________________________________________________________________
pool5 (MaxPooling3D)         (None, 1, 4, 4, 512)      0
_________________________________________________________________
flatten_1 (Flatten)          (None, 8192)              0
_________________________________________________________________
fc6 (Dense)                  (None, 4096)              33558528
_________________________________________________________________

video = Input(shape=(frames,h, w,c))
cnn_base = VGG16(input_shape=(h,w,c), weights="imagenet", include_top=False)
cnn_out = GlobalAveragePooling2D()(cnn_base.output)
cnn = Model(input=cnn_base.input, output=cnn_out)
cnn.trainable = False
encoded_frames = TimeDistributed(cnn)(video)
encoded_sequence = LSTM(30)(encoded_frames)
hidden_layer = Dense(output_dim=1024, activation="relu")(encoded_sequence)
outputs = Dense(output_dim=classes, activation="sigmoid")(hidden_layer)
model = Model([video], outputs)