Conv Layer filter_shape: [n_out_channel, n_height, n_width] self._input_shape: [batch_size, n_in_channel, n_height, n_width]

3D Convolution layer

3D Convolution layer with FC input and hidden unit

3D Unpooling layer for a convolutional network

Holds a binvox model. data is either a three-dimensional numpy boolean array (dense representation) or a two-dimensional numpy float array (c

Compute 1 - input_layer.output

Softmax with loss (n_batch, n_vox, n_label, n_vox, n_vox)

A simple timer.

Compute block diagonal matrix multiplication efficiently using broadcasting Last dimension will be used for matrix multiplication. prev

Convolution 3D LSTM layer Unlike a standard LSTM cell witch doesn't have a spatial information, Convolutional 3D LSTM has limited connection

Layer abstract class. support basic functionalities. If you want to set the output shape, either prev_layer or input_shape must be defined.