File size: 3,580 Bytes
387aa7a 8ff4a33 |
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 |
"""
MIT License
Copyright (c) 2021 Wilson Yan
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE.
This file is copied from https://github.com/wilson1yan/VideoGPT/blob/master/videogpt/utils.py
We adapted it to Hugging Face AutoModel for easier model loading.
"""
# Shifts src_tf dim to dest dim
# i.e. shift_dim(x, 1, -1) would be (b, c, t, h, w) -> (b, t, h, w, c)
def shift_dim(x, src_dim=-1, dest_dim=-1, make_contiguous=True):
n_dims = len(x.shape)
if src_dim < 0:
src_dim = n_dims + src_dim
if dest_dim < 0:
dest_dim = n_dims + dest_dim
assert 0 <= src_dim < n_dims and 0 <= dest_dim < n_dims
dims = list(range(n_dims))
del dims[src_dim]
permutation = []
ctr = 0
for i in range(n_dims):
if i == dest_dim:
permutation.append(src_dim)
else:
permutation.append(dims[ctr])
ctr += 1
x = x.permute(permutation)
if make_contiguous:
x = x.contiguous()
return x
# reshapes tensor start from dim i (inclusive)
# to dim j (exclusive) to the desired shape
# e.g. if x.shape = (b, thw, c) then
# view_range(x, 1, 2, (t, h, w)) returns
# x of shape (b, t, h, w, c)
def view_range(x, i, j, shape):
shape = tuple(shape)
n_dims = len(x.shape)
if i < 0:
i = n_dims + i
if j is None:
j = n_dims
elif j < 0:
j = n_dims + j
assert 0 <= i < j <= n_dims
x_shape = x.shape
target_shape = x_shape[:i] + shape + x_shape[j:]
return x.view(target_shape)
def tensor_slice(x, begin, size):
assert all([b >= 0 for b in begin])
size = [l - b if s == -1 else s
for s, b, l in zip(size, begin, x.shape)]
assert all([s >= 0 for s in size])
slices = [slice(b, b + s) for b, s in zip(begin, size)]
return x[slices]
import math
import numpy as np
import skvideo.io
def save_video_grid(video, fname, nrow=None):
b, c, t, h, w = video.shape
video = video.permute(0, 2, 3, 4, 1)
video = (video.cpu().numpy() * 255).astype('uint8')
if nrow is None:
nrow = math.ceil(math.sqrt(b))
ncol = math.ceil(b / nrow)
padding = 1
video_grid = np.zeros((t, (padding + h) * nrow + padding,
(padding + w) * ncol + padding, c), dtype='uint8')
for i in range(b):
r = i // ncol
c = i % ncol
start_r = (padding + h) * r
start_c = (padding + w) * c
video_grid[:, start_r:start_r + h, start_c:start_c + w] = video[i]
skvideo.io.vwrite(fname, video_grid, inputdict={'-r': '5'})
print('saved videos to', fname)
|