Change the device of the data inplace. Example: >>> self = SamplingResult.random() >>> print(f'self = {self.to(None)}

Loads the warmup scheduler's state. Arguments: state_dict (dict): warmup scheduler state. Should be an object returned

Performs a single optimization step. Arguments: closure (callable, optional): A closure that reevaluates the model

Returns the device that the model is on.

StereoNet uses leaky relu (alpha = 0.2)

Args: filepath (str): a string that contains the absolute path, including the file name, where the visualized ima

Returns the state of the warmup scheduler as a :class:`dict`. It contains an entry for every variable in self.__dict__ which is not t

1x1 convolution

Creates a dataset with the specified parameters. Args: dataset_str: A dataset string description (e.g. ImageNet:split=TRAIN).

Applies the mish function element-wise: mish(x) = x * tanh(softplus(x)) = x * tanh(ln(1 + exp(x))) See additional documentation for mi