stylish.transform¶

The image transformation network is a deep residual convolutional neural network parameterized by weights.

The network body consists of five residual blocks. All non-residual convolutional layers are followed by an instance normalization and ReLU non-linearities with the exception of the output layer, which instead uses a scaled “tanh” to ensure that the output image has pixels in the range [0, 255]. Other than the first and last layers which use 9 × 9 kernels, all convolutional layers use 3 × 3 kernels.

See also

Ulyanov et al. (2017). Instance Normalization: The Missing Ingredient for Fast Stylization. CoRR, abs/1607.08022.

stylish.transform.network(input_node)[source]¶

Apply the image transformation network.

The last node of the graph will be returned. The network will be applied to the current Tensorflow graph.

Example:

>>> g = tf.Graph()
>>> with g.as_default(), tf.Session() as session:
...     ...
...     network(input_node)

input_node should be a 4-D Tensor representing a batch list of images. It will be the input of the network.

stylish.transform.residual_block(input_node, operation_name, in_channels, out_channels, kernel_size, strides)[source]¶

Apply a residual block to the network.

input_node will be the input of the block.

in_channels should be the number of channels at the input of the block.

out_channels should be the number of channels at the output of the block.

kernel_size should be the width and height of the convolution matrix used within the block.

strides should indicate the stride of the sliding window for each dimension of input_node.

stylish.transform.conv2d_layer(input_node, operation_name, in_channels, out_channels, kernel_size, strides, activation=False)[source]¶

Apply a 2-D convolution layer to the network.

input_node will be the input of the layer.

in_channels should be the number of channels at the input of the layer.

out_channels should be the number of channels at the output of the layer.

kernel_size should be the width and height of the convolution matrix used within the block.

strides should indicate the stride of the sliding window for each dimension of input_node.

activation should indicate whether a ‘relu’ node should be added after the convolution layer.

stylish.transform.conv2d_transpose_layer(input_node, operation_name, in_channels, out_channels, kernel_size, strides, activation=None)[source]¶

Apply a transposed 2-D convolution layer to the network.

input_node will be the input of the layer.

in_channels should be the number of channels at the input of the layer.

out_channels should be the number of channels at the output of the layer.

kernel_size should be the width and height of the convolution matrix used within the block.

strides should indicate the stride of the sliding window for each dimension of input_node.

activation should indicate whether a ‘relu’ node should be added after the convolution layer.

stylish.transform.instance_normalization(input_node, channels)[source]¶

Apply an instance normalization to the network.

input_node will be the input of the layer.