r"""Returns the mean of the scalars that were accumulated for the given statistic between the last two calls to `update()`, or NaN if

Make models eval mode

r"""Returns the mean of the scalars that were accumulated for the given statistic between the last two calls to `update()`, or NaN if

save the current content to the HMTL file

r"""Copies current values of the internal counters to the user-visible state and resets them for the next round. If `keep_previous=Tr

Flush, close possible files, and remove stdout/stderr mirroring.

Make models train mode

Write text to stdout (and a file) and optionally flush.

Write text to stdout (and a file) and optionally flush.

From Mimic3D -> 3D aware 2dconv [ C*3, H, W ] -> [ C*9, H, W ]

1x1 convolution

Return: face_shape -- torch.tensor, size (B, N, 3) pts @ rot + trans Parameters: face_shape -- t

r"""Returns the standard deviation of the scalars that were accumulated for the given statistic between the last two calls to `update(

Flush, close possible files, and remove stdout/stderr mirroring.

Non-maximum suppression. Arguments: boxes: a float numpy array of shape [n, 5], where each row is (xmin, ymin, xmax, ymax, sc

Wrapper for the underlying `conv2d()` and `conv_transpose2d()` implementations.

Wrapper for the underlying `conv2d()` and `conv_transpose2d()` implementations.

Transform bounding boxes to be more like true bounding boxes. 'offsets' is one of the outputs of the nets. Arguments: bboxes: a float