CODEWITHSUNDEEP
machine-learningkerasdeep-learningconv-neural-network
chinmay gandi
chinmay gandi

Reputation: 63

In CNN model How can we find the initialized values of the filters that we have used

I have the cnn model code. 

classifier = Sequential()
classifier.add(Convolution2D(32,3,3, input_shape = 
(256,256,3),activation = "relu"))
classifier.add(MaxPooling2D(pool_size = (2,2)))

So now i need to find what values the 32 filters were initialized with ? Any code that helps in printing the values of the filters

Upvotes: 0

Views: 197

Answers (2)

Suba Selvandran
Suba Selvandran

Reputation: 314

Get the corresponding layer from the model

layer = classifier.layers[0]  # 0th layer is the convolution in your architecture

There will be two variables for each convolution layer (Filter kernels and Bias). Get the corresponding one

filters = layer.weights[0]  # kernel is the 0th index

Now filters contain the values you are looking for and it is a tensor. To get the values of the tensor, use get_value() function of Keras backend

import keras.backend as K
print(K.get_value(wt))

This will print an array of shape (3, 3, 3, 32) which translates to 32 filters of kernel size 3x3 for 3 channels.

Upvotes: 1

Pierre-Nicolas Piquin
Pierre-Nicolas Piquin

Reputation: 745

Here is the default keras Conv2d initialization : kernel_initializer='glorot_uniform' (or init='glorot_uniform' for older version of keras).

You can look at what this initializer does here : Keras initializers

Finally, here is one way to access the weights of your first layer :

classifier = Sequential()
classifier.add(Convolution2D(32,3,3, input_shape = 
(256,256,3),activation = "relu"))
classifier.add(MaxPooling2D(pool_size = (2,2)))

first_layer = classifier.layers[0]
print(first_layer.get_weights()) # You may need to process this output tensor to get a readable output and not just a raw tensor

Upvotes: 2

Related Questions