Sort boxes and associated fields according to a scalar field. A common use case is reordering the boxes according to descending scores. Args:

Use torch.multiprocessing.spawn to launch distributed processes

Decay the learning rate

Warmup the learning rate

Args: windows: (B*num_windows, window_size, window_size, C) window_size (tuple[int]): Window size H (int): Height of imag

Create the criterion. Parameters num_classes: number of object categories, omitting the special no-object category ma

Create the criterion. Parameters: num_classes: number of object categories, omitting the special no-object category m