Spaces:
Sleeping
Sleeping
File size: 3,924 Bytes
45d16e9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
"""
Copyright (c) 2022, salesforce.com, inc.
All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
"""
import warnings
import torch
def _is_tensor_video_clip(clip):
if not torch.is_tensor(clip):
raise TypeError("clip should be Tensor. Got %s" % type(clip))
if not clip.ndimension() == 4:
raise ValueError("clip should be 4D. Got %dD" % clip.dim())
return True
def crop(clip, i, j, h, w):
"""
Args:
clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W)
"""
if len(clip.size()) != 4:
raise ValueError("clip should be a 4D tensor")
return clip[..., i : i + h, j : j + w]
def resize(clip, target_size, interpolation_mode):
if len(target_size) != 2:
raise ValueError(
f"target size should be tuple (height, width), instead got {target_size}"
)
return torch.nn.functional.interpolate(
clip, size=target_size, mode=interpolation_mode, align_corners=False
)
def resized_crop(clip, i, j, h, w, size, interpolation_mode="bilinear"):
"""
Do spatial cropping and resizing to the video clip
Args:
clip (torch.tensor): Video clip to be cropped. Size is (C, T, H, W)
i (int): i in (i,j) i.e coordinates of the upper left corner.
j (int): j in (i,j) i.e coordinates of the upper left corner.
h (int): Height of the cropped region.
w (int): Width of the cropped region.
size (tuple(int, int)): height and width of resized clip
Returns:
clip (torch.tensor): Resized and cropped clip. Size is (C, T, H, W)
"""
if not _is_tensor_video_clip(clip):
raise ValueError("clip should be a 4D torch.tensor")
clip = crop(clip, i, j, h, w)
clip = resize(clip, size, interpolation_mode)
return clip
def center_crop(clip, crop_size):
if not _is_tensor_video_clip(clip):
raise ValueError("clip should be a 4D torch.tensor")
h, w = clip.size(-2), clip.size(-1)
th, tw = crop_size
if h < th or w < tw:
raise ValueError("height and width must be no smaller than crop_size")
i = int(round((h - th) / 2.0))
j = int(round((w - tw) / 2.0))
return crop(clip, i, j, th, tw)
def to_tensor(clip):
"""
Convert tensor data type from uint8 to float, divide value by 255.0 and
permute the dimensions of clip tensor
Args:
clip (torch.tensor, dtype=torch.uint8): Size is (T, H, W, C)
Return:
clip (torch.tensor, dtype=torch.float): Size is (C, T, H, W)
"""
_is_tensor_video_clip(clip)
if not clip.dtype == torch.uint8:
raise TypeError(
"clip tensor should have data type uint8. Got %s" % str(clip.dtype)
)
return clip.float().permute(3, 0, 1, 2) / 255.0
def normalize(clip, mean, std, inplace=False):
"""
Args:
clip (torch.tensor): Video clip to be normalized. Size is (C, T, H, W)
mean (tuple): pixel RGB mean. Size is (3)
std (tuple): pixel standard deviation. Size is (3)
Returns:
normalized clip (torch.tensor): Size is (C, T, H, W)
"""
if not _is_tensor_video_clip(clip):
raise ValueError("clip should be a 4D torch.tensor")
if not inplace:
clip = clip.clone()
mean = torch.as_tensor(mean, dtype=clip.dtype, device=clip.device)
std = torch.as_tensor(std, dtype=clip.dtype, device=clip.device)
clip.sub_(mean[:, None, None, None]).div_(std[:, None, None, None])
return clip
def hflip(clip):
"""
Args:
clip (torch.tensor): Video clip to be normalized. Size is (C, T, H, W)
Returns:
flipped clip (torch.tensor): Size is (C, T, H, W)
"""
if not _is_tensor_video_clip(clip):
raise ValueError("clip should be a 4D torch.tensor")
return clip.flip(-1)
|