I'm trying to build a CNN and got stuck with MaxPooling3D layers not working. Both layers get an input shape of (1, 5, 32) and I'd like to max-pool over the depth using poolsize (1, 1, 32) so the output becomes of shape (1, 5, 1). However this throws the error:
ValueError: Input 0 of layer max_pooling3d is incompatible with the
layer: expected ndim=5, found ndim=4. Full shape received: [None, 1,
5, 32]
I don't understand why a dimension of 5 is expected/required. If I instead use MaxPooling2D layers with poolsize (1,1) everything compiles correctly and I get the model below.
> Model: "functional_1"
> __________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
> ==================================================================================================
input_1 (InputLayer) [(None, 5, 5, 1)] 0
__________________________________________________________________________________________________
conv2d_1 (Conv2D) (None, 5, 1, 32) 192 input_1[0][0]
__________________________________________________________________________________________________
conv2d (Conv2D) (None, 1, 5, 32) 192 input_1[0][0]
__________________________________________________________________________________________________
reshape (Reshape) (None, 1, 5, 32) 0 conv2d_1[0][0]
__________________________________________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 1, 5, 32) 0 conv2d[0][0]
__________________________________________________________________________________________________
max_pooling2d_1 (MaxPooling2D) (None, 1, 5, 32) 0 reshape[0][0]
__________________________________________________________________________________________________
concatenate (Concatenate) (None, 1, 5, 64) 0 max_pooling2d[0][0]
max_pooling2d_1[0][0]
==================================================================================================
Total params: 384 Trainable params: 384 Non-trainable params: 0
__________________________________________________________________________________________________
Process finished with exit code 0
The code I used to build this:
n=5
inp_similarity = Input(shape=(n, n, 1))
conv11 = Conv2D(32, (n, 1))(inp_similarity)
conv12 = Conv2D(32, (1, n))(inp_similarity)
reshape1 = Reshape((1,5,32))(conv12)
maxpl11 = MaxPooling2D((1, 1))(conv11)
maxpl12 = MaxPooling2D((1, 1))(reshape1)
merge1 = Concatenate()([maxpl11, maxpl12])
model = Model(inp_similarity, merge1)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model.summary()
your aim is to operate a 'pooling' on the the feature dimensionality... this is not the scope of the pooling layer... they operate pooling only on the spatial dimensionalities. you need something more simple
n=5
inp_similarity = Input(shape=(n, n, 1))
conv11 = Conv2D(32, (n, 1))(inp_similarity)
conv12 = Conv2D(32, (1, n))(inp_similarity)
reshape1 = Reshape((1,5,32))(conv12)
maxpl11 = Lambda(lambda x: tf.reduce_max(x, axis=-1, keepdims=True))(conv11)
maxpl12 = Lambda(lambda x: tf.reduce_max(x, axis=-1, keepdims=True))(reshape1)
merge1 = Concatenate()([maxpl11, maxpl12])
model = Model(inp_similarity, merge1)
model.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['accuracy'])
model.summary()
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_4 (InputLayer) [(None, 5, 5, 1)] 0
__________________________________________________________________________________________________
conv2d_35 (Conv2D) (None, 5, 1, 32) 192 input_4[0][0]
__________________________________________________________________________________________________
conv2d_34 (Conv2D) (None, 1, 5, 32) 192 input_4[0][0]
__________________________________________________________________________________________________
reshape_2 (Reshape) (None, 1, 5, 32) 0 conv2d_35[0][0]
__________________________________________________________________________________________________
lambda_6 (Lambda) (None, 1, 5, 1) 0 conv2d_34[0][0]
__________________________________________________________________________________________________
lambda_7 (Lambda) (None, 1, 5, 1) 0 reshape_2[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 1, 5, 2) 0 lambda_6[0][0]
lambda_7[0][0]
==================================================================================================