3 Pull requests merged by 2 people

• Ultralytics Code Refactor https://ultralytics.com/actions

  #13153 merged Jun 30, 2024

• Ultralytics Code Refactor https://ultralytics.com/actions

  #13152 merged Jun 30, 2024

• Bump docker/build-push-action from 5 to 6 in /.github/workflows

  #13123 merged Jun 30, 2024

3 Pull requests opened by 3 people

• a change

  #13148 opened Jun 29, 2024

• modify default value of stride to 64 in the function letterbox

  #13150 opened Jun 29, 2024

• Update tensorflow requirement from <=2.16.1 to <=2.16.2

  #13155 opened Jul 1, 2024

19 Issues closed by 5 people

• The accuracy of the .pt model will decrease after being converted to .engine model.

  #12996 closed Jul 1, 2024

• Does YOLO perform object detection on jp2 image format?

  #13031 closed Jul 1, 2024

• How to reduce the size of best.pt

  #13034 closed Jul 1, 2024

• Parameter performance indicators

  #13033 closed Jul 1, 2024

• 🚀 Feature Request: Simplified Method for Changing Label Names in YOLOv5 Model

  #13036 closed Jul 1, 2024

• where is yolov5 v7.0 --trian in export.py?

  #13037 closed Jul 1, 2024

• How to close the amp?

  #12903 closed Jun 30, 2024

• How to change training input image size?

  #12966 closed Jun 30, 2024

• May I ask yolov5 how to port the method of calculating P, R, AP, MAP in val.py to adapt to detect.py, what code need to be packed?

  #12986 closed Jun 30, 2024

• Issue when try to validate openvino format model

  #13019 closed Jun 30, 2024

• Custom object detection by retaining the original classes of yolo

  #13025 closed Jun 30, 2024

• REQUIREMENTS.TXT FILE ERROR WITHIN YOLOV5

  #13024 closed Jun 29, 2024

• YOLOv5 receptive range size

  #13127 closed Jun 28, 2024

• ModuleNotFoundError: No module named 'models.yolo' on custom trained weight. Is it a bug?

  #12999 closed Jun 28, 2024

• Is there a problem with the way I fine-tuned the YOLOv5?

  #13020 closed Jun 28, 2024

• No module named 'models'

  #13021 closed Jun 28, 2024

• cls loss

  #13016 closed Jun 27, 2024

• low precision

  #13098 closed Jun 26, 2024

• How can I test/evaluate my custom model and custom dataset when my model is loaded via torch.hub?

  #13136 closed Jun 26, 2024

10 Issues opened by 10 people

• metric question

  #13162 opened Jul 3, 2024

• How can I process the features during inference?

  #13161 opened Jul 3, 2024

• Hello, I have some questions about the parse_model. Could you please help me answer them?

  #13159 opened Jul 3, 2024

• combining two or more weights into one

  #13158 opened Jul 2, 2024

• how to get mIoU and mPA in yolov5_seg?

  #13154 opened Jul 1, 2024

• Mosaic

  #13145 opened Jun 29, 2024

• How to increase FPS camera capture inside the Raspberry Pi 4B 8GB with best.onnx model

  #13144 opened Jun 27, 2024

• neck

  #13143 opened Jun 27, 2024

• I observe that the validation phase is much slower than the training phase on large validation sets and multi-GPU machines

  #13142 opened Jun 27, 2024

• how to convert pt to onnx to trt

  #13141 opened Jun 27, 2024

28 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Added warning message when `--single-cls` is used incorrectly by [#13028](https://github.com/ultralytics/yolov5/issues/13028)

  #13032 commented on Jul 1, 2024 • 4 new comments

• Model distillation for yolov5

  #13124 commented on Jul 3, 2024 • 4 new comments

• ultralytics>=8.0.232 does not install on Yolov5

  #12857 commented on Jul 3, 2024 • 4 new comments

• Yolov5s versus Yolov5s-cls

  #13128 commented on Jun 28, 2024 • 2 new comments

• NVIDIA Jetson Nvidia Jetson Nano, Xavier NX, Orin Deployment tutorial

  #9627 commented on Jun 28, 2024 • 2 new comments

• A Problem Concerning the Custom Dataset for Object Detection Using YOLOv5

  #13113 commented on Jun 28, 2024 • 2 new comments

• limit the detection of classes in YOLOv5 by manipulating the code

  #13092 commented on Jul 1, 2024 • 2 new comments

• Android uses YOLOv5 segmentation

  #13056 commented on Jul 2, 2024 • 1 new comment

• about physical memory and virtual memory

  #13058 commented on Jul 2, 2024 • 1 new comment

• Unable to train model on VisDrone

  #13054 commented on Jul 1, 2024 • 1 new comment

• Author, do you have a complete Python version that reads the engine model of Tensorrt to infer strength segmentation code, which is a simple version of the official inference code. It can be run in just one file without calling too many Python files or libraries

  #13055 commented on Jul 1, 2024 • 1 new comment

• Parameters Fusion

  #13050 commented on Jun 29, 2024 • 1 new comment

• A question about bbox normalization

  #13051 commented on Jun 29, 2024 • 1 new comment

• Is yolov5 sensitive to the size of defects and what structural improvements are needed to increase its sensitivity to defects?

  #13027 commented on Jun 28, 2024 • 1 new comment

• Confusion Matrix

  #13035 commented on Jun 27, 2024 • 1 new comment

• Refactor YOLOv5 code for readability, maintainability, and efficiency

  #13117 commented on Jun 30, 2024 • 0 new comments

• Colab

  #13048 commented on Jun 30, 2024 • 0 new comments

• Highlight the closest target with a different color in predictions

  #13018 commented on Jun 30, 2024 • 0 new comments

• New Feature: added cmd line arg for saving only positives

  #13005 commented on Jun 30, 2024 • 0 new comments

• Updated detect.py to save images in images/ directory when save_txt is True

  #12914 commented on Jun 30, 2024 • 0 new comments

• Removed manual accounting of field's count

  #12842 commented on Jun 30, 2024 • 0 new comments

• Fix: NotImplementedError: cannot instantiate 'PosixPath' on your system on Windows platform

  #12785 commented on Jun 30, 2024 • 0 new comments

• CORS Updated

  #12706 commented on Jun 30, 2024 • 0 new comments

• translucent line for visibility

  #12610 commented on Jun 30, 2024 • 0 new comments

• Copy-Paste augmentation

  #12599 commented on Jun 30, 2024 • 0 new comments

• fix bug for trt inference

  #12209 commented on Jun 30, 2024 • 0 new comments

• Mise en place dossier vidéo

  #11869 commented on Jun 30, 2024 • 0 new comments

• added lighter yolov5 config files

  #11813 commented on Jun 30, 2024 • 0 new comments