mAP each class

[manhlab]

I don't know how to show mAP of each class. It's so helpfully if this function has in yolov5

[github-actions[bot]]

👋 Hello @manhlab, 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 glenn.jocher@ultralytics.com.

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.

[ptran1203]

I think it's already there

run file test.py

                all         885    4.79e+03        0.51        0.44       0.428       0.204
  Aortic enlargement         885         678       0.821       0.847       0.882       0.539
         Atelectasis         885          46       0.666       0.239        0.42       0.148
       Calcification         885         145        0.33        0.31       0.209      0.0775
        Cardiomegaly         885         473       0.831       0.918       0.919       0.632
       Consolidation         885          84       0.593       0.369       0.396       0.181
                 ILD         885         146       0.393       0.397       0.345       0.136
        Infiltration         885         197       0.534       0.371       0.368        0.15
        Lung Opacity         885         397       0.413       0.355       0.312      0.0974
         Nodule/Mass         885         392       0.536       0.459       0.432       0.192
        Other lesion         885         370       0.236       0.143        0.12      0.0442
    Pleural effusion         885         351       0.508       0.425       0.454       0.161
  Pleural thickening         885         829       0.406       0.299       0.261      0.0717
        Pneumothorax         885          24       0.458       0.667       0.543       0.329
  Pulmonary fibrosis         885         658       0.421       0.369       0.323       0.101
Speed: 90.5/1.6/92.1 ms inference/NMS/total per 640x640 image at batch-size 32
Results saved to runs/test/exp

[glenn-jocher]

@manhlab yes per class mAP is displayed at the end of training, or when running test.py directly.

If your dataset has more than 50 classes you need to use the --verbose flag to force a per class printout. If you are not seeing this then you should update your code (git pull or clone again).

python test.py --verbose

[Edwardmark]

@glenn-jocher Hi, would you please tell me how to test APl APm APs, which stands for AP large, AP medium, AP small as coco?Thanks.

[glenn-jocher]

@Edwardmark sorry buddy, we don't have this capability for custom datasets, only for COCO, which uses pycocotools to get these breakdowns.

[Edwardmark]

@glenn-jocker, thanks, buddy.

[github-actions[bot]]

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.