Residual Network : Operands could not be broadcast together with shapes (128, 128, 16) (126, 126, 16)

Question

I am trying to code ResNet-12 in Keras based on this paper . But I have an error in the 8 Layer, and in my code below the probelem is in the function Layer_Type3.

I can not see where the problem is, can anyone help ? thanks in advance.

The Error is :

ValueError: Operands could not be broadcast together with shapes (128, 128, 16) (126, 126, 16)

def Layer_Type1(n_output):
    # n_output: number of feature maps in the block
    # upscale: should we use the 1x1 conv2d mapping for shortcut or not

    # keras functional api: return the function of type
    # Tensor -> Tensor
    def f(x):

        # convolution
        h = Conv2D(kernel_size=3, filters=n_output,  strides=1, padding='SAME',kernel_regularizer=regularizers.l2(0.01))(x)

        # second pre-activation
        h = BatchNormalization()(h)
        h = Activation(relu)(h)

        return h

    return f


def Layer_Type2(n_output):
    # n_output: number of feature maps in the block
    # upscale: should we use the 1x1 conv2d mapping for shortcut or not

    # keras functional api: return the function of type
    # Tensor -> Tensor
    def f(x):


        # first convolution
        h = Layer_Type1(n_output)(x)

        # second convolution
        h = Conv2D(kernel_size=3, filters=n_output , strides=1, padding='SAME',kernel_regularizer=regularizers.l2(0.01))(h)

        # second pre-activation
        h = BatchNormalization()(h)


        # F_l(x) = f(x) + H_l(x):
        return add([x, h])

    return f


def Layer_Type3(n_output):

    def f(x):

        # first convolution
        h = Layer_Type1(n_output)(x)

        # second convolution
        h = Conv2D(kernel_size=3 ,filters=n_output, strides=1,kernel_regularizer=regularizers.l2(0.01))(h)

        # second pre-activation
        h = BatchNormalization()(h)
        h = AveragePooling2D(pool_size=(3,3), strides=2)(h)

        # short cut
        d = Conv2D(kernel_size=1, filters=n_output, strides=2)(x)
        d =BatchNormalization()(d)

        return add([d, h])

    return f


def Layer_Type4(n_output):

    def f(x):

        # first convolution
        h = Layer_Type1(n_output)(x)

        # second convolution
        h = Conv2D(kernel_size=3, filters=n_output, strides=1, kernel_regularizer=regularizers.l2(0.01))(h)

        # second pre-activation
        h = BatchNormalization()(h)
        h = GlobalAveragePooling2D()(h)




        return h

    return f


input_tensor = Input((256,256,1))
## 2 Layers of type1 :
x= Layer_Type1(64)(input_tensor)
x= Layer_Type1(16)(x)

# 5 layers pf type 2:
for i in range(5) :
  x = Layer_Type2(16)(x)

## 4 layers of type 3
x= Layer_Type3(16)(x) #1  # ########## Error here 
x=Layer_Type3(64)(x) #2
x=Layer_Type3(128)(x) #3
x=Layer_Type3(256)(x) # 4

# 1 layer of type 4 :
x=Layer_Type4(512)(x)


x = Dropout(0.2)(x)
# last softmax layer
x = Dense(units=2, kernel_regularizer=regularizers.l2(0.01))(x)
x = Activation(softmax)(x)

model = Model(inputs=input_tensor, outputs=x)
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

Answer 1

The error message come from Numpy library. Maybe it appears when operating on numpy arrays but their shapes are not compatible. From your code, I guess it occurs when you try to add two convolution maps (feature maps) (one is (126,126,126) and another is (128,128,1)). Try to review layers with padding, pool size and stride carefully.