model3.ConvLayer

class model3.ConvLayer(size, outchn, dilation_rate=1, stride=1, pad='SAME', activation=-1, batch_norm=False, usebias=True, values=None)

High-level convolution 2D layer

__init__(size, outchn, dilation_rate=1, stride=1, pad='SAME', activation=-1, batch_norm=False, usebias=True, values=None)

Parameters:

• size (int or list[int]) – Indicate the size of convolution kernel.
• outchn (int) – Number of output channels
• stride (int or list[int]) – Stride number. Can be either integer or list of integers
• pad (String) – Padding method, must be one of ‘SAME’, ‘VALID’, ‘SAME_LEFT’. ‘VALID’ does not use auto-padding scheme. ‘SAME’ uses tensorflow-style auto-padding and ‘SAME_LEFT’ uses pytorch-style auto-padding.
• dilation_rate (int or list[int]) – Dilation rate. Can be either integer or list of integers. When dilation_rate is larger than 1, stride should be 1.
• usebias (bool) – Whether to add bias term in this layer.
• values (list[np.array]) – If the param ‘values’ is set, the layer will be initialized with the list of numpy array.
• activation – Same candidates as layers3.activate
• batch_norm (bool) – Whether to use batch normalization in this layer.

call(x)

Parameters:x – Input tensor or numpy array. The object will be automatically converted to tensor if the input is np.array. Note that other arrays in args or kwargs will not be auto-converted. Returns:Tensor or a list of tensor.