- 24 5月, 2022 5 次提交
-
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
* Apple Metal Performance Shader (MPS) device support Following https://pytorch.org/blog/introducing-accelerated-pytorch-training-on-mac/ Should work with Apple M1 devices with PyTorch nightly installed with command `--device mps`. Usage examples: ```bash python train.py --device mps python detect.py --device mps python val.py --device mps ``` * Update device strategy to fix MPS issue
-
由 xylieong 提交于
* Bug Fixed: OpenVINO metadata * Bug Fixed: OpenVINO metadata * Update export.py * Update export.py Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Glenn Jocher 提交于
* Rename OpenVINO meta.yaml to model name * Rename OpenVINO meta.yaml to model name * Rename OpenVINO meta.yaml to model name * fix
-
由 xylieong 提交于
* Write .yaml file when exporting model to openvino Write .yaml file automatically when exporting model to openvino to be used during inference * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update export.py * Update export.py * Load metadata on inference * Update common.py Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
- 23 5月, 2022 3 次提交
-
-
由 Glenn Jocher 提交于
Resolves Ultralytics HUB CI errors.
-
由 Glenn Jocher 提交于
Adjust to 5%, fixes failing Colab AMP check with V100 (1.5% different) with 200% safety margin.
-
-
- 22 5月, 2022 4 次提交
-
-
由 Glenn Jocher 提交于
* Code refactor for general.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update restapi.py Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
由 Glenn Jocher 提交于
* Add PyTorch AMP check * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Cleanup * Cleanup * Cleanup * Robust for DDP * Fixes * Add amp enabled boolean to check_train_batch_size * Simplify * space to prefix Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
由 Glenn Jocher 提交于
Locate file in subdirectories.
-
- 20 5月, 2022 3 次提交
-
-
由 Glenn Jocher 提交于
* Add DWConvTranspose2d() module * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add DWConvTranspose2d() module * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix * Fix Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
-
由 Anton Lebedev 提交于
* Improve mAP0.5-0.95 Two changes provided 1. Added limit on the maximum number of detections for each image likewise pycocotools 2. Rework process_batch function Changes #2 solved issue #4251 I also independently encountered the problem described in issue #4251 that the values for the same thresholds do not match when changing the limits in the torch.linspace function. These changes solve this problem. Currently during validation yolov5x.pt model the following results were obtained: from yolov5 validation Class Images Labels P R mAP@.5 mAP@.5:.95: 100%|██████████| 157/157 [01:07<00:00, 2.33it/s] all 5000 36335 0.743 0.626 0.682 0.506 from pycocotools Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.685 These results are very close, although not completely pass the competition issue #2258. I think it's problem with false positive bboxes matched ignored criteria, but this is not actual for custom datasets and does not require an additional solution. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Remove line to retain pycocotools results * Update val.py * Update val.py * Remove to device op * Higher precision int conversion * Update val.py Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com> Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
- 19 5月, 2022 2 次提交
-
-
由 xylieong 提交于
* Added Windows cmd to count GPU devices * Cleanup Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Jaewon Lee 提交于
* Removed shell=True from subprocess commands that require user inputs. Also removed unused arguments * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Added check=True * Revert line add Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
- 18 5月, 2022 1 次提交
-
-
由 Glenn Jocher 提交于
To appear on Docker Hub in top down order: - latest - latest-cpu - latest-arm64
-
- 17 5月, 2022 9 次提交
-
-
由 Glenn Jocher 提交于
* Update Dockerfile-arm64 * Update docker.yml
-
由 Glenn Jocher 提交于
Enabled grouped non c1 == c2 convolutions in TF YOLOv5 models.
-
由 Glenn Jocher 提交于
* Update Dockerfile-cpu install `libpython3.8-dev` Fix OpenVINO export * Update Dockerfile-arm64
-
由 Glenn Jocher 提交于
* Create docker.yml * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update docker.yml * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update docker.yml * Update docker.yml * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Cleanup * Cleanup2 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciCo-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
由 Glenn Jocher 提交于
* Update README.md * Update greetings.yml
-
由 Glenn Jocher 提交于
* Update Dockerfile-cpu `--no-install-recommends` Per https://ubuntu.com/blog/we-reduced-our-docker-images-by-60-with-no-install-recommends * Update Dockerfile-M1 * Update Dockerfile * Update Dockerfile-M1 * Update Dockerfile-cpu
-
由 Glenn Jocher 提交于
-
由 Nanohana 提交于
* Uses OpenVINO runtime instead of openvino-dev * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * export with openvino package * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Revert export.py * Update common.py Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Glenn Jocher 提交于
-
- 16 5月, 2022 5 次提交
-
-
由 Glenn Jocher 提交于
* New TensorFlow `TFCrossConv()` module * Move from experimental to common * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add C3x * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add to C3x to yolo.py * Add to C3x to tf.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * TFC3x bug fix * TFC3x bug fix * TFC3x bug fix * Add TFDWConv g==c1==c2 check * Add comment * Update tf.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciCo-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
由 dependabot[bot] 提交于
Bumps [cirrus-actions/rebase](https://github.com/cirrus-actions/rebase) from 1.6 to 1.7. - [Release notes](https://github.com/cirrus-actions/rebase/releases) - [Commits](https://github.com/cirrus-actions/rebase/compare/1.6...1.7) --- updated-dependencies: - dependency-name: cirrus-actions/rebase dependency-type: direct:production update-type: version-update:semver-minor ... Signed-off-by:
dependabot[bot] <support@github.com> Co-authored-by:
dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
-
由 Glenn Jocher 提交于
* New TensorFlow `TFDWConv()` module Analog to DWConv() module: https://github.com/ultralytics/yolov5/blob/8aa2085a7e7ae20a17a7548edefbdb2960f2b29b/models/common.py#L53-L57 * Fix and new activations() function * Update tf.py
-
由 Glenn Jocher 提交于
Resolves bug report #7817
-
由 Glenn Jocher 提交于
-
- 15 5月, 2022 2 次提交
-
-
由 Glenn Jocher 提交于
* Update torch_utils.py * Additional code refactoring * tuples to sets * Cleanup
-
由 Glenn Jocher 提交于
-
- 14 5月, 2022 1 次提交
-
-
由 Glenn Jocher 提交于
* Add `@threaded` decorator * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciCo-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
- 13 5月, 2022 5 次提交
-
-
由 Glenn Jocher 提交于
-
由 Yonghye Kwon 提交于
* add random_interpolation option to make model robust to interpolation methods * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix precommit error * Update augmentations.py * Update augmentations.py * Update augmentations.py * Update datasets.py * Update datasets.py Co-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Glenn Jocher 提交于
* Add Dockerfile-M1 * Update * Update * Update Dockerfile-M1
-
由 Glenn Jocher 提交于
@sergiossm
-
由 Glenn Jocher 提交于
* Implement DDP `static_graph=True` Experimental implementation of new PyTorch 1.11.0 DDP feature. * Add 1.11.0 check * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciCo-authored-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-