- 06 4月, 2021 2 次提交
-
-
由 Glenn Jocher 提交于
Fix 2 for 'Model predict with forward will fail if PIL image does not have filename attribute' #2702
-
由 Glenn Jocher 提交于
Proposed fix for 'Model predict with forward will fail if PIL image does not have filename attribute' #2702
-
- 02 4月, 2021 4 次提交
-
-
由 Glenn Jocher 提交于
Requested in https://github.com/ultralytics/yolov5/issues/2686
-
由 Glenn Jocher 提交于
Slight speedup.
-
由 Glenn Jocher 提交于
* PyTorch Hub model.save() increment as runs/hub/exp This chane will align PyTorch Hub results saving with the existing unified results saving directory structure of runs/ /train /detect /test /hub /exp /exp2 ... * cleanup
-
由 Ayush Chaurasia 提交于
* Set resume flag to false * Check existance of val dataset
-
- 01 4月, 2021 4 次提交
-
-
由 Ding Yiwei 提交于
* yolotr * transformer block * Remove bias in Transformer * Remove C3T * Remove a deprecated class * put the 2nd LayerNorm into the 2nd residual block * move example model to models/hub, rename to -transformer * Add module comments and TODOs * Remove LN in Transformer * Add comments for Transformer * Solve the problem of MA with DDP * cleanup * cleanup find_unused_parameters * PEP8 reformat Co-authored-by:
DingYiwei <846414640@qq.com> Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Glenn Jocher 提交于
* Update README with Tips for Best Results tutorial * Update README.md
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
-
- 31 3月, 2021 2 次提交
-
-
由 Ayush Chaurasia 提交于
-
由 Glenn Jocher 提交于
-
- 30 3月, 2021 1 次提交
-
-
由 Phat Tran 提交于
* Add label smoothing option * Correct data type * add_log * Remove log * Add log * Update loss.py remove comment (too versbose) Co-authored-by:
phattran <phat.tranhoang@cyberlogitec.com> Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
- 29 3月, 2021 6 次提交
-
-
由 Benjamin Fineran 提交于
Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Youngjin Shin 提交于
* Add opencv-contrib-python to requirements.txt * Update requirements.txt Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
* Speed profiling improvements * Update torch_utils.py deepcopy() required to avoid adding elements to model. * Update torch_utils.py
-
由 zzttqu 提交于
When using tqdm, sometimes it can't print in one line and roll to next line.
-
由 Glenn Jocher 提交于
I think this should help speed up CUDA inference, as currently models may be running in FP32 inference mode on CUDA devices unnecesarily.
-
- 28 3月, 2021 7 次提交
-
-
由 Glenn Jocher 提交于
Fix for #2630 raised by @Pro100rus32
-
由 Glenn Jocher 提交于
Add stderr=subprocess.STDOUT to catch error messages.
-
由 Ayush Chaurasia 提交于
* W&B resume ddp from run link fix * Native DDP W&B support for training, resuming
-
由 Ayush Chaurasia 提交于
-
由 Glenn Jocher 提交于
Catch 'fatal: not a git repository' returns and return '' instead (observed in GCP Hub checks).
-
由 Glenn Jocher 提交于
Update Docker FROM nvcr.io/nvidia/pytorch:21.03-py3
-
由 Glenn Jocher 提交于
Attempt to resolve tensorboard Docker error in https://github.com/ultralytics/yolov5/issues/2573
-
- 27 3月, 2021 2 次提交
-
-
由 Glenn Jocher 提交于
```python self.n = len(self.pred) # number of images (batch size) ```
-
由 Ayush Chaurasia 提交于
* Fix Indentation in test.py * CI fix * Comply with PEP8: 80 characters per line
-
- 26 3月, 2021 6 次提交
-
-
由 Glenn Jocher 提交于
* Update detections() self.t = tuple() Fix multiple results.print() bug. * Update experimental.py * Update yolo.py
-
由 Glenn Jocher 提交于
Updated device selection string with fallback for non-git directories. ```python def select_device(device='', batch_size=None): # device = 'cpu' or '0' or '0,1,2,3' s = f'YOLOv5
🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string ... ``` -
由 maxupp 提交于
Co-authored-by:
Max Uppenkamp <max.uppenkamp@inform-software.com>
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
Cython should be a dependency of the remaining packages in requirements.txt, so should be installed anyway even if not a direct requirement.
-
由 Glenn Jocher 提交于
-
- 25 3月, 2021 4 次提交
-
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
This updates the default detect.py behavior to automatically save all inference images/videos/webcams unless the new argument --nosave is used (python detect.py --nosave) or unless a list of streaming sources is passed (python detect.py --source streams.txt)
-
由 Max Kolomeychenko 提交于
guide describes YOLOv5 apps collection in Supervisely Ecosystem
-
由 Glenn Jocher 提交于
Improved user-feedback following requirements auto-update.
-
- 24 3月, 2021 2 次提交
-
-
由 Glenn Jocher 提交于
Prints 'Please restart runtime or rerun command for update to take effect.' following package auto-install to inform users to restart/rerun.
-
由 Glenn Jocher 提交于
* YOLOv5 PyTorch Hub models >> check_requirements() Update YOLOv5 PyTorch Hub requirements.txt path to cache path. * Update hubconf.py
-