- 02 Jun, 2022 3 commits
-
-
tripleMu authored
* Add typehint in such files * Update mmcv/video/processing.py Co-authored-by:
Zaida Zhou <58739961+zhouzaida@users.noreply.github.com> * Fix np.ndarray str * Fix * Update mmcv/video/processing.py Co-authored-by:
Jiazhen Wang <47851024+teamwong111@users.noreply.github.com> Co-authored-by:
-
WINDSKY45 authored
* [Enhance] Add type hint in `focal_loss.py`. * Use torch.LongTensor as type of target. * Fixed the missing type hint. * Removed some unnecessary type hint. * Add missing type hint and fix the type hint of `target`. * Fix the format of typehint. * minor refinement * minor fix Co-authored-by: -
ShawnHu authored
* Add type hints in resnet.py * using lint while commit * using lint while commit * using lint while commit * reslove typehints * add pre-defined type hints * Add type hints for other methods in mmcv/cnn/resnet.py * Fix type hints
-
- 01 Jun, 2022 2 commits
-
-
ShawnHu authored
* Add type hints in mmcv/ops/carafe.py * Add type hints in mmcv/ops/corner_pool.py * Add type hints in mmcv/ops/diff_iou_rotated.py * Add type hints for other methods for mmcv/ops/corner_pool.py * Add type hints for other methods in mmcv/ops/carafe.py * Add type hints for symbolic method
-
WINDSKY45 authored
* [Enhance] Add type hint in 'utils.py'. * [Enhance] Add type hint in 'default_constructor.py'. * Fixed undefined name. * minor refinement Co-authored-by:
-
- 31 May, 2022 1 commit
-
-
gy77 authored
* add typehint in mmcv/ops/pixel_group.py * fix indent * fix indent * improve format Co-authored-by:
-
- 30 May, 2022 4 commits
-
-
Zaida Zhou authored
-
tripleMu authored
* Add typehint in mmcv/fileio/* * Update mmcv/fileio/io.py Co-authored-by:
-
ShawnHu authored
-
tripleMu authored
* Fix * Fix
-
- 29 May, 2022 3 commits
- 28 May, 2022 5 commits
-
-
tripleMu authored
-
ShawnHu authored
* add typehints in ops-active-rotated-filter * resolve typehints in ops-active-rotated-filter
-
gy77 authored
* add typehint in mmcv/ops/points_sampler.py * Update mmcv/ops/points_sampler.py Co-authored-by:
-
gy77 authored
* add type hint in mmcv/ops/points_in_boxes.py * fix lint
-
gy77 authored
-
- 27 May, 2022 9 commits
-
-
WINDSKY45 authored
* [Enhance] Add type hint in `lr_updater.py`. * Fix circle import
-
gy77 authored
* add type hints in iou3d.py * fix lint * Add a missing item in iou3d.py
-
Zaida Zhou authored
-
kira authored
* Update alexnet.py * Update alexnet.py * Update mmcv/cnn/alexnet.py Co-authored-by:
-
zengxiang68 authored
* add type hints for mmcv/ops/... * add type hints for mmcv/ops/... * add type hints for mmcv/ops/...
-
Yvette Zhao authored
-
tripleMu authored
* Add typehint in mmcv/utils* * Update mmcv/utils/registry.py Co-authored-by:
-
gy77 authored
* add type hints in iou3d.py * fix lint
-
Range King authored
* Add type hints in bbox.py * Add type hints in box_iou_rotated.py * Update ball_query.py * Revert "Add type hints in bbox.py" This reverts commit 102566488e3aa9328b1c6e1159e2699d40f9f9f5. * Update bbox.py * Revert "Update bbox.py" This reverts commit d34b2c6ed54ba024b9674c948493001a8b4ff864. * Update bbox.py
-
- 26 May, 2022 1 commit
-
-
Zaida Zhou authored
-
- 25 May, 2022 7 commits
-
-
Zaida Zhou authored
-
Zaida Zhou authored
-
Wencheng Wu authored
* [Fix] Fix the problem that the instance cannot reuse when overwriting the file client. * Remove _overridden_backends and _overridden_prefixes, and pop the old instance when overwriting the file client. * add unittest * fix prefix error * modify clear_backend to overridden_backend * Delete redundant comments.
-
wlf-darkmatter authored
* Imporve ability to view usage data during training The wrong labeling of the dataset may cause problems such as gradient explosion during the training process. The wrong labeling can be found by setting up a hook function. **Problem**: However, when a for loop is used to traverse the iterator of the pytorch `DataLoader` class, the hook cannot obtain the information of the currently read image, and thus cannot determine the source of the error. **Solution**: Load the data_batch information into the `runner` during the train process, and then pass it to the hook function to solve the problem. * Update epoch_based_runner.py * Update iter_based_runner.py * strict the scope of runner.data_batch * strict the scope of runner.data_batch * strict the scope of runner.data_batch
-
Alex Yang authored
-
whcao authored
* fix is_module_wrapper * test is_module_wrapper * fix code style
-
Danila Rukhovich authored
* add iou3d * revert deprecated python function * fix lint * replace 3d iou/nms calls for bev iou/nms
-
- 20 May, 2022 2 commits
-
-
del-zhenwu authored
* skip test_rotated_feature_align.py for parrots Signed-off-by:
del-zhenwu <dele.zhenwu@gmail.com> * fix lint Co-authored-by:
zhouzaida <zhouzaida@163.com>
-
JarvisKevin authored
* Fix the bug met in using nasfpn Fix the bug met in using nasfpn which is mentioned at https://github.com/open-mmlab/mmdetection/issues/5987 . Avoid the strong restrictions of _resize function in BaseMergeCell: 1. When Downsampling the feature map, the feature map's shape must be divisible by the target size. We pad zero around feature map before max_pool2d opt to make it always divisible. (line 102 ~ 107) 2. Considering the different downsampling scale of H and W, shape[-2] and shape[-1] are involed in the definition of kernel_size. (line 110) * Update merge_cells.py check flake8 & isort * Update merge_cells.py * Update merge_cells.py yapf * Update mmcv/ops/merge_cells.py X_pad rename to padding_x Co-authored-by:
Mashiro <57566630+HAOCHENYE@users.noreply.github.com> * Update merge_cells.py format the code style after renameing the X_pad to padding_x * Update test_merge_cells.py Mainly test the downsampling resize in BaseMergeCell. The smaller target size is set to (14, 7), the classical feature map's size in the last few stages of the backbone, which will product different downsampling scales in different dims. * Update test_merge_cells.py add "# Copyright (c) OpenMMLab. All rights reserved." * Update merge_cells.py format the variable name * Update test_merge_cells.py Testing divisible and indivisible situations simultaneously * Update mmcv/ops/merge_cells.py fix the bug when h is indivisible and w is divisible, the pad_w will be padded unreasonable. Co-authored-by:
-
- 18 May, 2022 1 commit
-
-
Zaida Zhou authored
* add pyupgrade * add options for pyupgrade * minor refinement
-
- 17 May, 2022 1 commit
-
-
Zaida Zhou authored
* [Docs] Fix failed links in docs/zh_cn/faq.md * fix links
-
- 16 May, 2022 1 commit
-
-
Zaida Zhou authored
* Use mdformat pre-commit hook * allows consecutive numbering * improve .mdformat.toml * test mdformat * format markdown * minor fix * fix codespecll * fix circleci * add linkify-it-py dependency for cicleci * add comments * replace flake8 url * add mdformat-myst dependency * remove mdformat-myst dependency * update contributing.md
-
