- 25 Jan, 2021 1 commit
-
-
Vasilis Vryniotis authored
Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
- 22 Jan, 2021 3 commits
-
-
Ștefan Săftescu authored
The video reader suppressed code 61 (ENODATA on Linux) that occured at the end of a stream and logged an INFO message. On macOS ENODATA has a different code (96), which resulted in an error message being logged. This small patch replaces the hard-coded value with the ENODATA constant to suppress the macOS warning. Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Nicolas Hug authored
-
Matti Picus authored
Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
- 21 Jan, 2021 1 commit
-
-
Anirudh authored
-
- 20 Jan, 2021 5 commits
-
-
Aditya Oke authored
* Fixes utils * don't use any * slightly simplify logic Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Alessio Falai authored
Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Max Frei authored
* Fixed warning. UserWarning: The default behavior for interpolate/upsample with float scale_factor changed in 1.6.0 to align with other frameworks/libraries, and now uses scale_factor directly, instead of relying on the computed output size. If you wish to restore the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details. * Aligned _resize_image_and_masks_onnx. Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
Philip Meier authored
* upgrade status badge from Travis CI to CircleCI * remove CircleCI status badge Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
Vasilis Vryniotis authored
Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
- 19 Jan, 2021 2 commits
-
-
Vasilis Vryniotis authored
* Tag fasterrcnn mobilenetv3 model with 320, add new inference config that makes it 2x faster sacrificing a bit of mAP. * Add a high resolution fasterrcnn mobilenetv3 model. * Update tests and expected values.
-
Vasilis Vryniotis authored
* Simplify code and remove used vars. * Simplify expressions and remove used parenthesis. * Jit fixes. * Making check more readable. * fixing styles
-
- 18 Jan, 2021 1 commit
-
-
Vasilis Vryniotis authored
* Minor refactoring of a private method to make it reusuable. * Adding a FasterRCNN + MobileNetV3 with & w/o FPN models. * Reducing Resolution to 320-640 and anchor sizes to 16-256. * Increase anchor sizes. * Adding rpn score threshold param on the train script. * Adding trainable_backbone_layers param on the train script. * Adding rpn_score_thresh param directly in fasterrcnn_mobilenet_v3_large_fpn. * Remove fasterrcnn_mobilenet_v3_large prototype and update expected file. * Update documentation and adding weights. * Use buildin Identity. * Fix spelling.
-
- 15 Jan, 2021 2 commits
-
-
Sofya Lipnitskaya authored
* Make download_url() follow redirects Fix bug related to the incorrect processing of redirects. Follow the redirect chain until the destination is reached or the number of redirects exceeds the max allowed value (by default 10). * Parametrize value of max allowed redirect number Make max number of hops a function argument and assign its default value to 10 * Propagate the max number of hops to download_url() Add the maximum number of redirect hops parameter to download_url() * check file existence before redirect * remove print * remove recursion * add tests * Reducing max_redirect_hops Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com> Co-authored-by:
Philip Meier <github.pmeier@posteo.de> Co-authored-by:
Vasilis Vryniotis <vvryniotis@fb.com>
-
Ren Pang authored
* 'make_dataset' as staticmethod of 'DatasetFolder' * a better fix Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
- 14 Jan, 2021 3 commits
-
-
Vasilis Vryniotis authored
-
Vasilis Vryniotis authored
* Add MobileNetV3 Architecture in TorchVision (#3182) * Adding implementation of network architecture * Adding rmsprop support on the train.py * Adding auto-augment and random-erase in the training scripts. * Adding support for reduced tail on MobileNetV3. * Tagging blocks with comments. * Adding documentation, pre-trained model URL and a minor refactoring. * Handling better untrained supported models.
-
Vasilis Vryniotis authored
* Introduce small score threshold on rpn * Adding docs and fixing keypoint and mask. * Making value 0.0 by default for BC. * Fixing for onnx. * Update threshold. * Removing non-default threshold from reference scripts. Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
- 11 Jan, 2021 1 commit
-
-
Josh Bradley authored
* initial commit of widerface dataset * comment out old code * improve parsing of annotation files * code cleanup and fix docstring comments * speed up check for quota exceeded * cleanup print statements * reformat code and remove print statements * minor code cleanup and reformatting * add more comments * reuse variable * reverse formatting changes * fix flake8 errors * add type annotations * fix mypy errors * add a base_folder to root directory * some formatting fixes * GDrive threshold does not throw 403 error * testing new download logic * cleanup logic for download and integrity check * use a better variable name * format fix * reorder list in docstring * initial widerface unit test - fails on MD5 check * use list of dictionaries to store dataset * fix docstring formatting * remove unnecessary error checking * fix type checker error * revert typo fix * rename var constants, use file context manager, verify str args * fix flake8 error * fix checking target_type argument values * create uncompressed dataset folders * cleanup unit tests for widerface * use correct os function * add more info to docstring * disable unittests for windows * fix _check_integrity logic * update docstring * remove citation * remove target_type option * fix formatting issue Co-authored-by:
Philip Meier <github.pmeier@posteo.de> * remove comment and add more info to docstring * update type annotations * restart CI jobs Co-authored-by:
Joshua Bradley <jgbrad3@evoforge.org> Co-authored-by:
Philip Meier <github.pmeier@posteo.de> Co-authored-by:
vfdev <vfdev.5@gmail.com>
-
- 08 Jan, 2021 2 commits
-
-
Vince authored
* Update README.rst * Commit suggested changes Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com> * Commit suggested changes Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com> Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Vasilis Vryniotis authored
* Fixing trainable_layers bug. * minor doc fixes
-
- 07 Jan, 2021 2 commits
-
-
Ben Weinstein authored
* remove unused imports after manual review * Update torchvision/datasets/voc.py Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com> * remove two more instances Co-authored-by:
Ben Weinstein <benweinstein@Bens-MacBook-Pro.local> Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Zhengyang Feng authored
* adjust_hue * adjust_* * colorjitter
-
- 05 Jan, 2021 1 commit
-
-
Federico Baldassarre authored
* Exposing LevelMapper params in MultiScaleRoIAlign Ability to set the `canonical_scale` and `canonical_level` of LevelMapper from the init method of MultiScaleRoIAlign. Not sure if this is the right place to expose those parameters. Also, additional tests should be written. Discussion in issue #3129 * MultiScaleRoIAlign keyword-only parameters + docs (pytorch#3129) * Linter fix (trailing whitespace) Co-authored-by:Francisco Massa <fvsmassa@gmail.com>
-
- 04 Jan, 2021 4 commits
-
-
Vasilis Vryniotis authored
* Adding TORCH_SELECTIVE_* macros on op registration. * Adding torchvision namespace.
-
Vasilis Vryniotis authored
* Speedup test_ucf101 (#2623 * Speedup Cmake builds (#3186) * Speedup test_autoaugment (#3190) * Speedup DeformConvTester (#3191) * Speedup InceptionV3 and GoogleNet on Windows (#3196)
-
Hamid Zare authored
Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Yuxin Wu authored
`find_package(Python3 COMPONENTS Development)` is used in this `CMakeLists.txt`. This feature is supported only after cmake 3.12.
-
- 23 Dec, 2020 2 commits
-
-
Zhengyang Feng authored
* Initial doc clean-up * Remove all private docs * Rename files * Highlight backend inconsistencies * Sequence and number * [Need checking] AutoAugment related doc change * Revert name changes
-
Vasilis Vryniotis authored
* Patches required for FBCode merge. * Patching quantization model imports. * import QuantizableMobileNetV2 * Adding newline to avoid lit errors
-
- 22 Dec, 2020 2 commits
-
-
Samuel Marks authored
Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Vasilis Vryniotis authored
-
- 20 Dec, 2020 1 commit
-
-
Siddhant Bansal authored
* Update ImageReadMode error messages, add newline at the end of image_read_mode.h, replace define with const in image_read_mode.h, add documentation to ImageReadMode enum * Update readpng_cpu and readjpeg_cpu error messages * Update image.py documentation
-
- 17 Dec, 2020 1 commit
-
-
Vasilis Vryniotis authored
* Moving mobilenet.py to mobilenetv2.py * Adding mobilenet.py for BC. * Extending ConvBNReLU for reuse. * Reduce import scope on mobilenet to only the public and versioned classes and methods.
-
- 16 Dec, 2020 1 commit
-
-
Vasilis Vryniotis authored
* Fixing incorrect doc example in MNASNet. * Fixing incorrect output.
-
- 15 Dec, 2020 2 commits
-
-
Avijit Dasgupta authored
* added the helper method for dimension checks * unit tests for dimensio check function in functional_tensor * code formatting and typing * moved torch image check after tensor check * unit testcases for test_assert_image_tensor added and refactored * separate unit testcase file deleted * assert_image_tensor added to newly created 6 methods * test cases added for new 6 mthohds * removed wrongly pasted posterize method and added solarize method for testing Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com> Co-authored-by:
Vasilis Vryniotis <datumbox@users.noreply.github.com>
-
Zhiqiang Wang authored
* Replacing all torch.jit.annotations with typing * Replacing remaining typing
-
- 14 Dec, 2020 2 commits
-
-
Vasilis Vryniotis authored
* Invert Transform (#3104) * Adding invert operator. * Make use of the _assert_channels(). * Update upper bound value. * Remove private doc from invert, create or reuse generic testing methods to avoid duplication of code in the tests. (#3106) * Create posterize transformation and refactor common methods to assist reuse. (#3108) * Implement the solarize transform. (#3112) * Implement the adjust_sharpness transform (#3114) * Adding functional operator for sharpness. * Adding transforms for sharpness. * Handling tiny images and adding a test. * Implement the autocontrast transform. (#3117) * Implement the equalize transform (#3119) * Implement the equalize transform. * Turn off deterministic for histogram. * Fixing test. (#3126) * Force ratio to be float to avoid numeric overflows on blend. (#3127) * Separate the tests of Adjust Sharpness from ColorJitter. (#3128) * Add AutoAugment Policies and main Transform (#3142) * Separate the tests of Adjust Sharpness from ColorJitter. * Initial implementation, not-jitable. * AutoAugment passing JIT. * Adding tests/docs, changing formatting. * Update test. * Fix formats * Fix documentation and imports. * Apply changes from code review: - Move the transformations outside of AutoAugment on a separate method. - Renamed degenerate method for sharpness for better clarity. * Update torchvision/transforms/functional.py Co-authored-by:
vfdev <vfdev.5@gmail.com> * Apply more changes from code review: - Add InterpolationMode parameter. - Move all declarations away from AutoAugment constructor and into the private method. * Update documentation. * Apply suggestions from code review Co-authored-by:
Francisco Massa <fvsmassa@gmail.com> * Apply changes from code review: - Refactor code to eliminate as any to() and clamp() as possible. - Reuse methods where possible. - Apply speed ups. * Replacing pad. Co-authored-by:
vfdev <vfdev.5@gmail.com> Co-authored-by:
Francisco Massa <fvsmassa@gmail.com>
-
Vasilis Vryniotis authored
* Removing VISION_API from backward() methods and adding a ops.h * Fixing clang format.
-
- 12 Dec, 2020 1 commit
-
-
Jay Zhang authored
* Fix an issue that ShuffleNetV2 model is exported to a wrong ONNX file if dynamic_axes field was provided. * Add a ut for the bug fix. * Fix flake8 issue. * Don't access each element in x.shape, use x.size() instead. Co-authored-by:Vasilis Vryniotis <datumbox@users.noreply.github.com>
-