CODEWITHSUNDEEP
tensorflowkerasneural-networkconv-neural-network
InfinityAndBeyond
InfinityAndBeyond

Reputation: 36

Patch size in keras.layers.Conv2D?

I am trying to implement the one paper I recently read. On this paper network looks like this.

enter image description here

As in the picture, the first layer has 11x11 patch size. But I don't see any patch size parameter in keras.layers.Conv2d documentation.

How to add these layers in keras.Sequential() ?

Upvotes: 0

Views: 528

Answers (1)

SaifDeen
SaifDeen

Reputation: 872

The patch size is also referred as kernel size:

keras.layers.Conv2D(filters, kernel_size, strides=(1, 1), padding='valid', data_format=None, dilation_rate=(1, 1), activation=None, use_bias=True, kernel_initializer='glorot_uniform', bias_initializer='zeros', kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None, kernel_constraint=None, bias_constraint=None)

You can use the kernel_size parameter.

Upvotes: 2

Related Questions