R Deep Learning Cookbook

How to do it...

1. Run the create_conv_layer function with the preceding input parameters:

# Convolutional Layer 1conv1 <- create_conv_layer(input=x_image,num_input_channels=num_channels,filter_size=filter_size1,num_filters=num_filters1,use_pooling=TRUE)

2. Extract the layers of the first convolution layer:

layer_conv1 <- conv1$layerconv1_images <- conv1$layer$eval(feed_dict = dict(x = train_data$images, y_true = train_data$labels))

3. Extract the final weights of the first convolution layer:

weights_conv1 <- conv1$weightsweights_conv1 <- weights_conv1$eval(session=sess)

4. Generate the first convolution layer plots:

drawImage_conv(sample(1:50000, size=1), images.bw = conv1_images, images.lab=images.lab.train)

5. Generate the first convolution ...