training actually can not work about yolov5 HOT 8 CLOSED

Hello @jinfagang, thank you for your interest in our work! Please visit our Custom Training Tutorial to get started, and see our Google Colab Notebook, Docker Image, and GCP Quickstart Guide for example environments.

If this is a bug report, please provide screenshots and minimum viable code to reproduce your issue, otherwise we can not help you.

If this is a custom model or data training question, please note that Ultralytics does not provide free personal support. As a leader in vision ML and AI, we do offer professional consulting, from simple expert advice up to delivery of fully customized, end-to-end production solutions for our clients, such as:

• Cloud-based AI surveillance systems operating on hundreds of HD video streams in realtime.
• Edge AI integrated into custom iOS and Android apps for realtime 30 FPS video inference.
• Custom data training, hyperparameter evolution, and model exportation to any destination.

For more information please visit https://www.ultralytics.com.

from yolov5.

@jinfagang training operates correctly. See https://github.com/ultralytics/yolov5#reproduce-our-training

from yolov5.

@glenn-jocher Why am I training so low AP

from yolov5.

@jinfagang we've completed writing a custom data training tutorial here that may help. Make sure you check your labels by looking at train*.jpg after training starts.
https://docs.ultralytics.com/yolov5/tutorials/train_custom_data

from yolov5.

could you find the problem,I have a similar situation

from yolov5.

had similar problem and just found that I forgot to change the number of class in yolov5s.yaml when following the tutoiral.

from yolov5.

@annie7777 thanks for the comment! Recent updates have actually removed this requirement. Class counts for training are now inherited from the dataset.yaml nc in case of a difference.

The code changes often, so if anyone runs into a similar bug git pull to update your code to simply clone a fresh copy of the repo!

from yolov5.

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.

from yolov5.