ROI Pooling on GPU and CPU #584
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Add LinearTransformation to docs - Arrange the transforms alphabetically * Add missing transforms to docs
* Add case in test_to_tensor for PIL Images mode '1' * Add support in ToTensor for PIL Images mode '1' * Fix pep8 issues
…ations … (pytorch#481) * fix for PyTorch v0.4 (remove .data and add _ for the initializations in nn.init) * fix m.**.**() style to nn.init.**(**) style * remove .idea * fix lines and indents * fix lines and indents * change to use `kaming_normal_` * add `.data` for safety * add nonlinearity='relu' for sure * fix indents
Remove test with variables
nit: replace 4 by expansion
* Added Progress Bar to the dataset downloading utility * Updated progressbar to update by blcoks * Added progressbar2 to the requirements * fixed style issues * Shifted from progressbar to tqdm
Improve `test_pad_with_non_constant_padding_modes` to avoid data multiplication in `transforms.ToPILImage()` on float data: ```python img = torch.zeros(3, 27, 27) # Float32 img[:, :, 0] = 1 # we add 1 and not 255 img = transforms.ToPILImage()(img) # This converts 1 to 255 due to [pic = pic.mul(255).byte()](https://github.com/pytorch/vision/blob/master/torchvision/transforms/functional.py#L107) ``` and thus test's correct values are [..., 200, 1, 0]
* cifar10.meta['label_names'] * cifar100.meta['fine_label_names'] * cifar100.meta['coarse_label_names']
pytorch#506) This reverts commit 972b80c.
* Add classes metadata to MNIST and FashionMNIST * Add `targets` property to MNIST and FashionMNIST * Add class metadata to CIFAR10/CIFAR100 * Add `targets` property to CIFAR10/CIFAR100 * Add targets attribute to DatasetFolder
* fix a bug described in issue pytorch#488 * improve doc described in issue pytorch#488 * add arguments in RandomCrop as proposed by vfdev-5 in PR pytorch#489
* Fix PIL link * Make normalize more efficient
* make vision depend on pillow-simd if already installed * actually make pillow-simd optional
* Addresses issue pytorch#145 as per @fmessa's suggestion. * Removed blank line for styling.
- Fix broken update calculation - Make progress bar use the neat `unit_scale` feature of tqdm
* reduce tqdm version to 4.19 for py2.7 to avoid spurious error * Update setup.py * Missed = * Update wrong version string
… and code formatting
|
@fmassa can you please rebase off the master branch so that only our commits are displayed on this PR? |
|
@fmassa I decided to create different PRs for each of the 3 layers (ROI Pooling, ROI Align and NMS) to make reviews easier. I'm closing this PR. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
ROI Pooling with both CPU and GPU implementations as well as test for #477.