CODEWITHSUNDEEP
pythonkerasconv-neural-network
ayush
ayush

Reputation: 13

Performing Conv2D on 4D data in Keras

I have data of dimension 24*64*64*10 (excluding the batch size).

I want to split the input into 24 inputs of dimension 64*64*10, perform Conv2D on each of them and then concatenate them to get the 4D data again for further processing.

Any help regarding the implementation would be helpful. I am working with Keras.

Edit: I tried to the following code to perform the 2D convolution

num_ch= 24
input= Input(shape=(64,64,10,num_ch))
print(input.shape)
branch_out= []
for i in range(num_ch):
    out= Lambda(lambda x: x[:,:,:,:,i] )(input)
    print(out.shape)
    out= Conv2D(10, kernel_size=(3,3),strides= (1,1), padding='same', data_format= 'channels_last')(input)
    branch_out.append(out)

I got the following error:

(?, 64, 64, 10, 24)
(?, 64, 64, 10)
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-83-51977f4edbba> in <module>
      7     out= Lambda(lambda x: x[:,:,:,:,i] )(input)
      8     print(out.shape)
----> 9     out= Conv2D(10, kernel_size=(3,3),strides= (1,1), padding='same', data_format= 'channels_last')(input)
     10     branch_out.append(out)

~/anaconda3/lib/python3.7/site-packages/keras/engine/base_layer.py in __call__(self, inputs, **kwargs)
    412                 # Raise exceptions in case the input is not compatible
    413                 # with the input_spec specified in the layer constructor.
--> 414                 self.assert_input_compatibility(inputs)
    415 
    416                 # Collect input shapes to build layer.

~/anaconda3/lib/python3.7/site-packages/keras/engine/base_layer.py in assert_input_compatibility(self, inputs)
    309                                      self.name + ': expected ndim=' +
    310                                      str(spec.ndim) + ', found ndim=' +
--> 311                                      str(K.ndim(x)))
    312             if spec.max_ndim is not None:
    313                 ndim = K.ndim(x)

ValueError: Input 0 is incompatible with layer conv2d_25: expected ndim=4, found ndim=5

Upvotes: 0

Views: 591

Answers (2)

amin
amin

Reputation: 289

Too late to answer but for those who has the same question...
I think you can just pass it to the Conv layer (maybe I'm wrong!). The code below is an example from keras: link

>>> # With extended batch shape [4, 7]:  
>>> input_shape = (4, 7, 28, 28, 3)
>>> x = tf.random.normal(input_shape)
>>> y = tf.keras.layers.Conv2D(
... 2, 3, activation='relu', input_shape=input_shape[2:])(x)
>>> print(y.shape)
(4, 7, 26, 26, 2)

Or another way is to use TimeDistributed layer. look at this link:

model = Sequential()
model.add(TimeDistributed(Conv2D(5, (3,3), padding='same'), input_shape=(10, 100, 100, 3)))

model.summary()

model summary:

Layer (type)                 Output Shape              Param #   
=================================================================
time_distributed_2 (TimeDist (None, 10, 100, 100, 5)   140       
=================================================================
Total params: 140
Trainable params: 140
Non-trainable params: 0
_________________________________________________________________

Upvotes: 0

qscgy
qscgy

Reputation: 311

You have a typo in this line:

out= Conv2D(10, kernel_size=(3,3),strides= (1,1), padding='same', data_format= 'channels_last')(input)

Change it to:

out= Conv2D(10, kernel_size=(3,3),strides= (1,1), padding='same', data_format= 'channels_last')(out)

Upvotes: 2

Related Questions