Workaround for ModelEma._load_checkpoint to accept an already-loaded object

Clamp tensor input to (min, max). input: input tensor to be clamped

Download a file from a url and place it in root. Args: url (str): URL to download file from root (str): Directory to place downlo

x: single-precision value to be quantized k: bit-setting for x x_min: lower bound for quantization range x_max=None

Get Inception feature maps Parameters ---------- inp : torch.autograd.Variable Input tensor of shape Bx3xHxW. Val

get random sample dataloader dataset: name of the dataset batch_size: the batch size of random data for_inception: whether the data

Get dataloader of testset dataset: name of the dataset batch_size: the batch size of random data path: the path to the data for

List all directories at a given root Args: root (str): Path to directory whose folders need to be listed prefix (bool, optional):

List all files ending with a suffix at a given root Args: root (str): Path to directory whose folders need to be listed suffix (s

loss function measured in L_p Norm

Warning: does not synchronize the deque!

test a model on a given dataset