Skip to content

Add pad_value argument to make_grid and save_image #142

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Apr 7, 2017
Merged

Add pad_value argument to make_grid and save_image #142

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7ff2da6
add pad_value argument
DmitryUlyanov Apr 5, 2017
7fae66b
add argument to save_image
DmitryUlyanov Apr 5, 2017
39dcf37
fix space
DmitryUlyanov Apr 6, 2017
914cb18
requested change of order
DmitryUlyanov Apr 6, 2017
36d1646
update docs
DmitryUlyanov Apr 7, 2017
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions README.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -388,7 +388,7 @@ For example:
Utils
=====

make\_grid(tensor, nrow=8, padding=2, normalize=False, range=None, scale\_each=False)
make\_grid(tensor, nrow=8, padding=2, normalize=False, range=None, scale\_each=False, pad\_value=0)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Given a 4D mini-batch Tensor of shape (B x C x H x W),
Expand All @@ -404,9 +404,11 @@ normalize the image.
scale_each=True will scale each image in the batch of images separately rather than
computing the (min, max) over all images.

pad_value=<float> sets the value for the padded pixels.

`Example usage is given in this notebook` <https://gist.github.com/anonymous/bf16430f7750c023141c562f3e9f2a91>

save\_image(tensor, filename, nrow=8, padding=2, normalize=False, range=None, scale\_each=False)
save\_image(tensor, filename, nrow=8, padding=2, normalize=False, range=None, scale\_each=False, pad\_value=0)
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Saves a given Tensor into an image file.
Expand Down
10 changes: 6 additions & 4 deletions torchvision/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@


def make_grid(tensor, nrow=8, padding=2,
normalize=False, range=None, scale_each=False):
normalize=False, range=None, scale_each=False, pad_value=0):
"""
Given a 4D mini-batch Tensor of shape (B x C x H x W),
or a list of images all of the same size,
Expand All @@ -19,6 +19,8 @@ def make_grid(tensor, nrow=8, padding=2,
scale_each=True will scale each image in the batch of images separately rather than
computing the (min, max) over all images.

pad_value=<float> sets the value for the padded pixels.

[Example usage is given in this notebook](https://gist.github.com/anonymous/bf16430f7750c023141c562f3e9f2a91)
"""
# if list of tensors, convert to a 4D mini-batch Tensor
Expand Down Expand Up @@ -65,7 +67,7 @@ def norm_range(t, range):
xmaps = min(nrow, nmaps)
ymaps = int(math.ceil(float(nmaps) / xmaps))
height, width = int(tensor.size(2) + padding), int(tensor.size(3) + padding)
grid = tensor.new(3, height * ymaps + 1 + padding // 2, width * xmaps + 1 + padding // 2).fill_(0)
grid = tensor.new(3, height * ymaps + 1 + padding // 2, width * xmaps + 1 + padding // 2).fill_(pad_value)
k = 0
for y in irange(ymaps):
for x in irange(xmaps):
Expand All @@ -79,7 +81,7 @@ def norm_range(t, range):


def save_image(tensor, filename, nrow=8, padding=2,
normalize=False, range=None, scale_each=False):
normalize=False, range=None, scale_each=False, pad_value=0):
"""
Saves a given Tensor into an image file.
If given a mini-batch tensor, will save the tensor as a grid of images by calling `make_grid`.
Expand All @@ -88,7 +90,7 @@ def save_image(tensor, filename, nrow=8, padding=2,
"""
from PIL import Image
tensor = tensor.cpu()
grid = make_grid(tensor, nrow=nrow, padding=padding,
grid = make_grid(tensor, nrow=nrow, padding=padding, pad_value=pad_value,
normalize=normalize, range=range, scale_each=scale_each)
ndarr = grid.mul(255).clamp(0, 255).byte().permute(1, 2, 0).numpy()
im = Image.fromarray(ndarr)
Expand Down