[proto] Added RandomCrop transform and tests #6271
Merged
Conversation
This file contains hidden or 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
vfdev-5
commented
Jul 14, 2022
| def fn( | ||
| id: Tuple[Any, ...], input: Any | ||
| ) -> Optional[Tuple[Tuple[Any, ...], Union[PIL.Image.Image, torch.Tensor, features.Image]]]: | ||
| if type(input) in {torch.Tensor, features.Image} or isinstance(input, PIL.Image.Image): | ||
| if type(input) == torch.Tensor or isinstance(input, (PIL.Image.Image, features.Image)): |
There was a problem hiding this comment.
@pmeier I suggest to check for image-like types in the following way. This helps to use mocker with spec type.
vfdev-5
commented
Jul 14, 2022
| raise TypeError("No image was found in the sample") | ||
|
|
||
|
|
||
| # vfdev-5: let's use tree_flatten instead of query_recursively and internal fn to make the code simplier |
There was a problem hiding this comment.
Let's simplify the code using tree_flatten instead of home-made methods.
vfdev-5
force-pushed
the
proto-transforms-api-randomcrop
branch
from
564767a to
93e1cfb
Compare
vfdev-5
commented
Jul 14, 2022
Comment on lines
+468
to
+495
| def _forward(self, flat_inputs: List[Any]) -> List[Any]: | ||
| if self.padding is not None: | ||
| flat_inputs = [F.pad(flat_input, self.padding, self.fill, self.padding_mode) for flat_input in flat_inputs] | ||
|
|
||
| image = query_image(flat_inputs) | ||
| _, height, width = get_image_dimensions(image) | ||
|
|
||
| # pad the width if needed | ||
| if self.pad_if_needed and width < self.size[1]: | ||
| padding = [self.size[1] - width, 0] | ||
| flat_inputs = [F.pad(flat_input, padding, self.fill, self.padding_mode) for flat_input in flat_inputs] | ||
| # pad the height if needed | ||
| if self.pad_if_needed and height < self.size[0]: | ||
| padding = [0, self.size[0] - height] | ||
| flat_inputs = [F.pad(flat_input, padding, self.fill, self.padding_mode) for flat_input in flat_inputs] | ||
|
|
||
| params = self._get_params(flat_inputs) | ||
|
|
||
| return [F.crop(flat_input, **params) for flat_input in flat_inputs] | ||
|
|
||
| def forward(self, *inputs: Any) -> Any: | ||
| from torch.utils._pytree import tree_flatten, tree_unflatten | ||
|
|
||
| sample = inputs if len(inputs) > 1 else inputs[0] | ||
|
|
||
| flat_inputs, spec = tree_flatten(sample) | ||
| out_flat_inputs = self._forward(flat_inputs) | ||
| return tree_unflatten(out_flat_inputs, spec) |
There was a problem hiding this comment.
Here, we can't just override _transform method as we need to access image data and generate params on transformed sample.
Proposed solution is to 1) flatten sample structure into a list, 2) apply crop+pad logic, 3) unflatten output into input sample structure
vfdev-5
added a commit
that referenced
this pull request
Jul 28, 2022
* [proto] Added few transforms tests, part 1 (#6262) * Added supported/unsupported data checks in the tests for cutmix/mixup * Added RandomRotation, RandomAffine transforms tests * Added tests for RandomZoomOut, Pad * Update test_prototype_transforms.py * Added RandomCrop transform and tests (#6271) * [proto] Added GaussianBlur transform and tests (#6273) * Added GaussianBlur transform and tests * Fixing code format * Copied correctness test * [proto] Added random color transforms and tests (#6275) * Added random color transforms and tests * Disable smoke test for RandomSolarize, RandomAdjustSharpness * Added RandomPerspective and tests (#6284) - replaced real image creation by mocks for other tests * Added more functional tests (#6285) * [proto] Added elastic transform and tests (#6295) * WIP [proto] Added functional elastic transform with tests * Added more functional tests * WIP on elastic op * Added elastic transform and tests * Added tests * Added tests for ElasticTransform * Try to format code as in #5106 * Fixed bug in affine get_params test * Implemented RandomErase on PIL input as fallback to tensors (#6309) Added tests * Added image_size computation for BoundingBox.rotate if expand (#6319) * Added image_size computation for BoundingBox.rotate if expand * Added tests * Added erase_image_pil and eager/jit erase_image_tensor test (#6320) * Updates according to the review Co-authored-by: Vasilis Vryniotis <[email protected]>
facebook-github-bot
pushed a commit
that referenced
this pull request
Aug 2, 2022
Summary: * [proto] Added few transforms tests, part 1 (#6262) * Added supported/unsupported data checks in the tests for cutmix/mixup * Added RandomRotation, RandomAffine transforms tests * Added tests for RandomZoomOut, Pad * Update test_prototype_transforms.py * Added RandomCrop transform and tests (#6271) * [proto] Added GaussianBlur transform and tests (#6273) * Added GaussianBlur transform and tests * Fixing code format * Copied correctness test * [proto] Added random color transforms and tests (#6275) * Added random color transforms and tests * Disable smoke test for RandomSolarize, RandomAdjustSharpness * Added RandomPerspective and tests (#6284) - replaced real image creation by mocks for other tests * Added more functional tests (#6285) * [proto] Added elastic transform and tests (#6295) * WIP [proto] Added functional elastic transform with tests * Added more functional tests * WIP on elastic op * Added elastic transform and tests * Added tests * Added tests for ElasticTransform * Try to format code as in #5106 * Fixed bug in affine get_params test * Implemented RandomErase on PIL input as fallback to tensors (#6309) Added tests * Added image_size computation for BoundingBox.rotate if expand (#6319) * Added image_size computation for BoundingBox.rotate if expand * Added tests * Added erase_image_pil and eager/jit erase_image_tensor test (#6320) * Updates according to the review Reviewed By: NicolasHug Differential Revision: D38351755 fbshipit-source-id: 4b52b530f93c3dfa92326e01803665cb44003a63 Co-authored-by: Vasilis Vryniotis <[email protected]>
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.
Description: