- 09 9月, 2021 4 次提交
-
-
由 Jean-Baptiste Martin 提交于
* Allow specifying multi_label option for NMS when using torch hub * Reformat Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 JD Costa 提交于
-
由 ELHoussineT 提交于
* adding get cropped functionality * Add target logic in existing functions * Crops cleanup * Add dictionary keys: conf, cls, box * Bug fixes - avoid return after first image Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
由 Glenn Jocher 提交于
* Add `user_config_dir` * Linux to .config
-
- 08 9月, 2021 5 次提交
-
-
由 Glenn Jocher 提交于
* Update `check_yaml()` comment * Cleanup
-
由 Glenn Jocher 提交于
Fix a bug when `file=''`
-
由 Glenn Jocher 提交于
* Add suffix checks * Cleanup * Cleanup2 * Cleanup3
-
由 Zhiqiang Wang 提交于
-
由 Kalen Michael 提交于
* added callbacks * added back callback to main * added save_dir to callback output * reduced code count * updated callbacks * added default callback class to main, added missing parameters to on_model_save * Glenn updates Co-authored-by:
Glenn Jocher <glenn.jocher@ultralytics.com>
-
- 06 9月, 2021 1 次提交
-
-
由 Glenn Jocher 提交于
-
- 05 9月, 2021 1 次提交
-
-
由 imyhxy 提交于
* Fixed 'meta' and 'hyp' may out of order when using evolve * Update gitignore
-
- 01 9月, 2021 4 次提交
-
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
Fix 3 for Arial.ttf redownloads with hub inference, follow-on to #4628.
-
由 Glenn Jocher 提交于
-
- 31 8月, 2021 2 次提交
-
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
* Remove assert * debug0 * trace=not opt.sync * sync to sync_bn fix * Cleanup
-
- 30 8月, 2021 8 次提交
-
-
由 Glenn Jocher 提交于
* Close plots * Replace fig.close() for plt.close()
-
由 Ayush Chaurasia 提交于
-
由 Glenn Jocher 提交于
-
由 Yukun Xia 提交于
Layer 21 includes the information of xsmall objects
-
由 Glenn Jocher 提交于
* Auto-download Arial.ttf on init * Fix ROOT
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
-
- 29 8月, 2021 8 次提交
-
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
* Add Annotator() class * Download Arial * 2x for loop * Cleanup * tuple 2 list * max_size=1920 * bold logging results to * tolist() * im = annotator.im * PIL save in detect.py * Smart asarray in detect.py * revert to cv2.imwrite * Cleanup * Return result asarray * Add `Profile()` profiler * CamelCase Timeout * Resize after mosaic * pillow>=8.0.0 * daemon imwrite * Add cv2 support * Remove plot_wh_methods and plot_one_box * pil=False for hubconf.py annotations * im.shape bug fix * colorstr common.py * join daemons * Update t.daemon * Removed daemon saving
-
由 Takumi Karasawa 提交于
-
由 Glenn Jocher 提交于
* Add `Profile()` profiler * CamelCase Timeout
-
由 Glenn Jocher 提交于
* Initial commit * Update
-
由 Glenn Jocher 提交于
* Add EarlyStopping feature * Add comment * Cleanup * Cleanup2 * debug * debug2 * debug3 * debug3 * debug4 * debug5 * debug6 * debug7 * debug8 * debug9 * debug10 * debug11 * debug12 * Cleanup * Add TODO for known DDP issue
-
- 27 8月, 2021 3 次提交
-
-
由 Glenn Jocher 提交于
-
由 Glenn Jocher 提交于
This PR brings alignment in AP computation practices with Detectron2 and MMDetection. Problem first noted by @yusiyoh in https://github.com/ultralytics/yolov5/issues/4546
-
由 Glenn Jocher 提交于
Auto-fix corrupt JPEGs PR introduced a bug whereby the f.seek() operation read all of the bytes in the image, resulting in the PIL image having nothing to read upon the .save() operation. Fix was to re-open the image using PIL before saving.
-
- 26 8月, 2021 2 次提交
-
-
由 Glenn Jocher 提交于
* Autofix corrupt JPEGs This PR automatically re-saves corrupt JPEGs and trains with the resaved images. WARNING: this will overwrite the existing corrupt JPEGs in a dataset and replace them with correct JPEGs, though the filesize may increase and the image contents may not be exactly the same due to lossy JPEG compression schemes. Results may vary by JPEG decoder and hardware. Current behavior is to exclude corrupt JPEGs from training with a warning to the user, but many users have been complaining about large parts of their dataset being excluded from training. * Clarify re-save reason
-
由 Glenn Jocher 提交于
Profiling fix copies input to Detect layer to circumvent inplace changes to the feature maps.
-
- 23 8月, 2021 2 次提交
-
-
由 Glenn Jocher 提交于
* Auto TFLite uint8 detection This PR automatically determines if TFLite models are uint8 quantized rather than accepting a manual argument. The quantization determination is based on @zldrobit comment https://github.com/ultralytics/yolov5/pull/1127#issuecomment-901713847 * Cleanup
-
由 Glenn Jocher 提交于
* Add `install=True` argument to `check_requirements` * Update general.py
-