- 19 11月, 2022 2 次提交
-
-
由 Glenn Jocher 提交于
* New global TQDM_BAR_FORMAT * [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
* Simplify dataloader tqdm descriptions @AyushExel this should help our tqdm dataloader messages fit better within a single line in our Colab notebooks and also help avoid confusion about missing/empty labels, now combined into 'backgrounds'. Signed-off-by:
Glenn Jocher <glenn.jocher@ultralytics.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update dataloaders.py Signed-off-by:
-
- 18 11月, 2022 5 次提交
-
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
* normalize_segments * round remove * swap axes fix
-
由 Ryan Echols 提交于
* fix: try 2 - prevent logging config clobbering Previous behavior: loading this repository with `torch.hub.load` clobbers the existing logging configuration by modifying the root logger's configuration. New behavior: loading this repository with `torch.hub.load` only clobbers the logging configuration for logger `yolov5` and its descendants. This is done in a way compatible with Google Colab Signed-off-by:
Ryan Echols <ryan@shadylakemedia.com> * chore: fill in comment no-op so a pre-commit hook can auto-format files Signed-off-by:
-
由 Glenn Jocher 提交于
* data.yaml `names.keys()` integer assert Signed-off-by:
-
- 17 11月, 2022 2 次提交
-
-
由 janus-zheng 提交于
* Apply make_divisible for onnx models in Autoshape At line 697 we have this `make_divisible` function for pytorch models. * Context: we want to run inference on varied input sizes instead of fixed image size. * When I test an image of size [720, 720] for a pytorch model (e.g., yolov5n.pt), we can see that it will be reshaped to [736, 736] by the function. This is as expected. * When I test the same image for the onnx model (e.g., yolov5n.onnx, exported with `--dynamic`), I got an error and it's due to the indivisible problem ``` onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running Concat node. Name:'Concat_143' Status Message: concat.cc:156 PrepareForCompute Non concat axis dimensions must match: Axis 3 has mismatched dimensions of 45 and 46 ``` The simple solution is to enable the `make_divisible` function for onnx model too. Signed-off-by:
janus-zheng <106574221+janus-zheng@users.noreply.github.com> * revise indent Signed-off-by:
-
由 Glenn Jocher 提交于
Revert "fix: prevent logging config clobbering (#10133)" This reverts commit 166b9f2f.
-
- 16 11月, 2022 3 次提交
-
-
由 tripleMu 提交于
FilterWarning for torch.distributed._all_gather_base Co-authored-by: -
由 Ryan Echols 提交于
Previous behavior: loading this repository with `torch.hub.load` clobbers the existing logging configuration by modifying the root logger's configuration. New behavior: loading this repository with `torch.hub.load` only clobbers the logging configuration for logger `yolov5` and its descendants. Signed-off-by:
-
由 Amol Dumrewal 提交于
Fix dataloader filepath modification to perform replace only once and not for all occurences of string (#10163) * Fix dataloader filepath modification to perform only once and not for all occurences of string * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * cleanup Signed-off-by:
-
- 15 11月, 2022 3 次提交
-
-
由 Glenn Jocher 提交于
* Update __init__.py Signed-off-by:
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Glenn Jocher 提交于
* Copy-Paste zero value fix Signed-off-by:
-
- 12 11月, 2022 2 次提交
-
-
由 Glenn Jocher 提交于
* Update HUB banner image Passed through tinypng for filesize reduction Signed-off-by:
-
由 Rubén Usamentiaga 提交于
Update benchmarks.py Signed-off-by:
Rubén Usamentiaga <rusamentiaga@uniovi.es> Signed-off-by:
-
- 11 11月, 2022 2 次提交
-
-
由 Glenn Jocher 提交于
* Add Ultralytics HUB section to README @pderrenger @kalenmike @AlanDimmer @AyushExel new Ultralytics HUB section in YOLOv5 README. Signed-off-by:
-
由 Glenn Jocher 提交于
Remove box area function and support expandable bbox_iou() calls. Signed-off-by:
-
- 10 11月, 2022 2 次提交
-
-
由 Victor Sonck 提交于
* Mapped project and name to ClearML * Add project and task name docs * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciCo-authored-by:
-
由 Glenn Jocher 提交于
* YouTube Usage example comments Signed-off-by:
-
- 09 11月, 2022 2 次提交
-
-
由 janus-zheng 提交于
Update common.py We have a division at line 694, and then a multiplication at line 695, so it makes `y*g` not an integer. And since `shape1` will be used at line 697 to ensure the size is divisible by the `stride`, this may lead to different image size. In my experiment, my image is [640, 640], it's divisible by the default stride 32, but I found that the result is changed to [672, 672] after line 697. So the final detection result is slightly different from that directly using the `detect.py` script, which does not call the AutoShape methods. Signed-off-by:
-
由 Glenn Jocher 提交于
-
- 08 11月, 2022 3 次提交
-
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Glenn Jocher 提交于
New 160-image MNIST subset composed of first 8 examples of each class. Suitable for fast CI. Signed-off-by:
-
由 pre-commit-ci[bot] 提交于
updates: - [github.com/asottile/pyupgrade: v2.38.2 → v3.2.0](https://github.com/asottile/pyupgrade/compare/v2.38.2...v3.2.0) Co-authored-by:
-
- 07 11月, 2022 1 次提交
-
-
由 Glenn Jocher 提交于
Signed-off-by:
-
- 06 11月, 2022 1 次提交
-
-
由 Glenn Jocher 提交于
IoU eps adjustment Unify h1 and h2 with eps values Signed-off-by:
-
- 04 11月, 2022 2 次提交
-
-
由 Glenn Jocher 提交于
* AutoCache * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * AutoCache * AutoCache * AutoCache * AutoCache Co-authored-by:
-
由 Glenn Jocher 提交于
* Update default `--epochs 100` @AyushExel @kalenmike updating default Detection and Segmentation trainings to 100 epochs Signed-off-by:
-
- 01 11月, 2022 5 次提交
-
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Glenn Jocher 提交于
* Improved check_online() robustness YOLOv5-wide improvement, not just in check_requirements() Signed-off-by:
-
由 Glenn Jocher 提交于
* Add `min_items` filter option @AyushExel @Laughing-q dataset filter Signed-off-by:
-
由 Glenn Jocher 提交于
Increased robustness to network failures Signed-off-by:
-
由 Glenn Jocher 提交于
@AyushExel @kalenmike Signed-off-by:
-
- 31 10月, 2022 3 次提交
-
-
由 Paul Guerrie 提交于
* Added a tutorial notebook for segmentation. * Updated header for segmentation tutorial and included other YOLOv5 sponsor sections. * Updated segmentation tutorial to match main object detection tutorial. * Update tutorial.ipynb Signed-off-by:
Ayush Chaurasia <ayush.chaurarsia@gmail.com> Co-authored-by:
-
由 Glenn Jocher 提交于
* Update README.md @taliabender updated spacing per our convo Signed-off-by:
-
由 Glenn Jocher 提交于
* Update tf.py Signed-off-by:
-
- 29 10月, 2022 2 次提交
-
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Kalen Michael 提交于
* fix: switched from suffix checks to archive checks * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Cleanup seems like both functions accept Path type input so removing str() * import always Co-authored-by:
-
![pre-commit-ci[bot]'s avatar](https://www.gravatar.com/avatar/131bb96d326461aea7edbfa1b0e095f7?s=72&d=identicon "pre-commit-ci[bot]")
