resume 恢复训练出现问题

[hashiqi-233]

❔Question

训练100个epoch,在50个epoch时中断，此时map=0.83然后使用python3 train.py --resume时，map突然下降到0.04，继续训练map变化不大。作者实现的resume似乎是有问题的。

Additional context

作者继续训练加载模型参数时排除了model.24.anchors，model.24.anchor_grid，不知道为啥

[github-actions]

👋 Hello @hashiqi-233, thank you for your interest in 🚀 YOLOv5! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for simple tasks like Custom Data Training all the way to advanced concepts like Hyperparameter Evolution.

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 training ❓ Question, please provide as much information as possible, including dataset images, training logs, screenshots, and a public link to online W&B logging if available.

For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at [email protected].

Requirements

Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7. To install run:

$ pip install -r requirements.txt

Environments

YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):

• Google Colab and Kaggle notebooks with free GPU:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training (train.py), testing (test.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[hashiqi-233]

已经找到问题，是我进化训练的时候把超参数文件中的anchors注释取消了。

[glenn-jocher]

@hashiqi-233 we just fixed a bug related to --resume with custom anchors about 20 days ago. See #2361

You may be using an older version of the code before this PR. Please git pull or git clone a new version to receive these updates.

[github-actions]

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.