- 25 9月, 2022 4 次提交
-
-
由 Glenn Jocher 提交于
* Add segment line predictions 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 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update Signed-off-by:
pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
-
https://pytorch.org/get-started/locally/由 David A. Macey 提交于
* Update Requirements with PyTorch CUDA Added --extra-index-url https://download.pytorch.org/whl/cu116 URL to requirements file for ease of creating venv with CUDA enabled PyTorch. Otherwise CPU PyTorch is installed an unable to use local GPUs. Signed-off-by:
David A. Macey <davidamacey@gmail.com> * Update requirements.txt Signed-off-by:
-
由 Glenn Jocher 提交于
* Update default GitHub assets Signed-off-by:
-
由 Forever518 提交于
* Try to fix DDP mAP drop by setting generator's seed to RANK * Fix default activation bug * Update dataloaders.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Update dataloaders.py Co-authored-by:
-
- 24 9月, 2022 3 次提交
-
-
由 Glenn Jocher 提交于
* Rename scale_coords to scale_boxes * add scale_segments
-
由 Gaz Iqbal 提交于
* update coco128-seg comments * Enables detect.py to use Triton for inference Triton Inference Server is an open source inference serving software that streamlines AI inferencing. https://github.com/triton-inference-server/server The user can now provide a "--triton-url" argument to detect.py to use a local or remote Triton server for inference. For e.g., http://localhost:8000 will use http over port 8000 and grpc://localhost:8001 will use grpc over port 8001. Note, it is not necessary to specify a weights file to use Triton. A Triton container can be created by first exporting the Yolov5 model to a Triton supported runtime. Onnx, Torchscript, TensorRT are supported by both Triton and the export.py script. The exported model can then be containerized via the OctoML CLI. See https://github.com/octoml/octo-cli#getting-started for a guide. * added triton client to requirements * fixed support for TFSavedModels in Triton * reverted change * Test CoreML update Signed-off-by:
Gaz Iqbal <giqbal@octoml.ai> Co-authored-by:
-
由 Glenn Jocher 提交于
Signed-off-by:
-
- 23 9月, 2022 2 次提交
-
-
由 zombob 提交于
* add screenshot as source * fix: screen number support * Fix: mutiple screen specific area * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * parse screen args in LoadScreenshots * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * sequence+ '_' as file name for save-txt save-crop * screenshot as stream * Update requirements.txt Signed-off-by:
xin <xin@zhiyoung.com> Co-authored-by:
-
由 Glenn Jocher 提交于
-
- 22 9月, 2022 3 次提交
-
-
由 Glenn Jocher 提交于
* TF.js fix May resolve https://github.com/ultralytics/yolov5/issues/9534Signed-off-by:
-
由 Glenn Jocher 提交于
* import re Signed-off-by:
-
由 Glenn Jocher 提交于
* Add `RandomResizedCrop(ratio)` * Update ratio * Update ratio * Update ratio * Update ratio * Update ratio * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Create augmentations.py Signed-off-by:
-
- 21 9月, 2022 6 次提交
-
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Glenn Jocher 提交于
Signed-off-by:
-
由 Glenn Jocher 提交于
* TFLite fix 2 Signed-off-by:
-
由 Glenn Jocher 提交于
* Update tf.py Signed-off-by:
-
- 20 9月, 2022 5 次提交
-
-
由 Glenn Jocher 提交于
* Remove `check_requirements('flatbuffers==1.12')` Signed-off-by: -
由 FeiGeChuanShu 提交于
* fix random_perspective param bug when mosaic=False Signed-off-by:
FeiGeChuanShu <774074168@qq.com> * Update dataloaders.py * Update dataloaders.py * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciSigned-off-by:
-
由 Glenn Jocher 提交于
* Segmentation `polygons2masks_overlap()` in `np.int32` May resolve https://github.com/ultralytics/yolov5/issues/9461 WARNING: Masks should be uint8 for fastest speed, change needs profiling results to determine impact. @AyushExel @Laughing-q Signed-off-by:
-
由 曾逸夫（Zeng Yifu） 提交于
* Update export.py Signed-off-by:
曾逸夫（Zeng Yifu） <41098760+Zengyf-CVer@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciSigned-off-by:
-
由 Glenn Jocher 提交于
Signed-off-by:
-
- 19 9月, 2022 6 次提交
-
-
由 Dhruv Nair 提交于
fix issues with image logging
-
由 mucunwuxian 提交于
* The following code is slow, "self.cap.set(cv2.CAP_PROP_POS_FRAMES, self.vid_stride * (self.frame + 1)) # read at vid_stride". * adjust... * Update dataloaders.py Signed-off-by:
-
由 Glenn Jocher 提交于
May resolve threaded inference issue in https://github.com/ultralytics/yolov5/pull/9425#issuecomment-1250802928 by avoiding memory sharing on init. Signed-off-by:
-
由 Glenn Jocher 提交于
May resolve https://github.com/ultralytics/yolov5/issues/9287#issuecomment-1250767031Signed-off-by:
-
由 Glenn Jocher 提交于
* TensorFlow SegmentationModel support * TensorFlow SegmentationModel support * TensorFlow SegmentationModel support * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * TFLite fixes * GraphDef fixes * Update ci-testing.yml Signed-off-by:
-
由 Glenn Jocher 提交于
Classify --save-txt Signed-off-by:
-
- 18 9月, 2022 10 次提交
-
-
由 Glenn Jocher 提交于
* TensorFlow macOS AutoUpdate * [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* Standardize warnings * [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
Update ClassificationModel default training imgsz=224 To match classify/val.py and classify/predict.py Helps https://github.com/ultralytics/yolov5/issues/9462Signed-off-by:
-
由 Glenn Jocher 提交于
Resolves https://github.com/ultralytics/yolov5/issues/9384Signed-off-by:
-
由 Glenn Jocher 提交于
* TensorRT SegmentationModel fix * TensorRT SegmentationModel fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * TensorRT SegmentationModel fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * TensorRT SegmentationModel fix * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * TensorRT SegmentationModel fix * TensorRT SegmentationModel fix * fix * sort output names * Update ci-testing.yml Signed-off-by:
-
由 Glenn Jocher 提交于
* Optimize imports * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Reformat * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciCo-authored-by:
-
由 Junjie Zhang 提交于
* fix cutout bug Signed-off-by:
Junjie Zhang <46258221+Oswells@users.noreply.github.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ciSigned-off-by:
-
由 Glenn Jocher 提交于
* Add `macos-latest` runner for CoreML benchmarks Signed-off-by:
-
由 Glenn Jocher 提交于
* Add Paddle exports to benchmarks Signed-off-by:
-
由 Glenn Jocher 提交于
* Detect() and Segment() fixes for CoreML and Paddle Signed-off-by:
-
- 17 9月, 2022 1 次提交
-
-
由 Glenn Jocher 提交于
Signed-off-by:
-
