CIntToPy */

__GNUC__ */

Return the item at the given index

The main thread gives a list of indices to load a batch. Each worker is going to work in parallel to load a different list of indices

The main thread gives a list of indices to load a batch. Each worker is going to work in parallel to load a different list of indices

Initialize training parameters and reload previous model for restore/finetune :param net: network object :param config: co

Initialize training parameters and reload previous model for restore/finetune :param net: network object :param config: co

Initialize parameters of the dataset here.

Initialize a batch normalization block. If network does not use batch normalization, replace with biases. :param in_dim: dimension

Initialize a standard unary block with its ReLU and BatchNorm. :param in_dim: dimension input features :param out_dim: dim

Initialize a simple convolution block with its ReLU and BatchNorm. :param in_dim: dimension input features :param out_dim:

Initialize a resnet bottleneck block. :param in_dim: dimension input features :param out_dim: dimension input features

Initialize a global average block with its ReLU and BatchNorm.

Initialize a nearest upsampling block with its ReLU and BatchNorm.

Initialize a max pooling block with its ReLU and BatchNorm.

Yield next batch indices here. In this dataset, this is a dummy sampler that yield the index of batch element (input sphere) in epoch

Yield next batch indices here. In this dataset, this is a dummy sampler that yield the index of batch element (input sphere) in epoch

Return the length of data here

Return the length of data here

The number of yielded samples is variable

Return the length of data here

The number of yielded samples is variable