Confusion Matrix with weird scale

Search before asking

I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

Hello!

I executed the val.py command, and received the following results:

And when I checked my Confusion Matrix, it's showing some weird results and a weird scale:

I don't get it why TP is 1.0 and FP is 1.0, can someone help me how can I interpret these results? And somehow fix the scale?

I tried to use conf_thres=0.25 and iou_thres=0.45 to see if my val.py results matches somehow the TP, since it's informed here (#1665) as the default values for Confusion Matrix.

Additional

FYI: my class is ALL (Acute Lymphoblastic Leukemia) 😅

@llucasreis

👋 Hello @llucasreis, 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://ultralytics.com or email support@ultralytics.com.

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

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), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

Ok apparently my Confusion Matrix is right, I checked all predicted images and my model doesn't predicted FNs, only FPs, and since I have only one class, everything went to background FP 🤔

So I think I only have the problem with the scale in Confusion Matrix now

This code reproduces this behavior:

import seaborn as sn
import matplotlib.pyplot as plt
import numpy as np
import warnings

matrix = np.array([[112, 34], [0,0]])

normalize = True

array = matrix / ((matrix.sum(0).reshape(1, -1) + 1E-6) if normalize else 1)  # normalize columns
array[array < 0.005] = np.nan  # don't annotate (would appear as 0.00)

names = ['ALL']
nc = 1

fig = plt.figure(figsize=(12, 9), tight_layout=True)
sn.set(font_scale=1.0 if nc < 50 else 0.8)  # for label size
labels = (0 < len(names) < 99) and len(names) == nc  # apply names to ticklabels

with warnings.catch_warnings():
    warnings.simplefilter('ignore')  # suppress empty matrix RuntimeWarning: All-NaN slice encountered
    sn.heatmap(array, annot=nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
                xticklabels=names + ['background FP'] if labels else "auto",
                yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
fig.axes[0].set_xlabel('True')
fig.axes[0].set_ylabel('Predicted')
fig.savefig('confusion_matrix.png', dpi=250)
plt.close()

@llucasreis

@llucasreis thanks for the code. I am able to reproduce. Will investigate.

Fix ConfusionMatrix scale `vmin=0.0`

Fix ConfusionMatrix scale `vmin=0.0` (#6638)

@llucasreis

@llucasreis good news 😃! Your original issue may now be fixed ✅ in PR #6638. Nan values were preventing a correct lower threshold for the Seaborn Heatmap colorbar, after update:

To receive this update:

Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
PyTorch Hub – Force-reload model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
Notebooks – View updated notebooks
Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

@glenn-jocher

Thank you very much! 😄 @glenn-jocher

Update Neuralmagic-YoloV5 integration to v6.1 (#29)

Fix ConfusionMatrix scale `vmin=0.0` (ultralytics#6638)

Fix ConfusionMatrix scale `vmin=0.0` (#6638)

Navigation Menu

Repository navigation

Confusion Matrix with weird scale #6626

Search before asking

Question

Additional

Requirements

Environments

Status

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Confusion Matrix with weird scale #6626

Description

Search before asking

Question

Additional

Activity

github-actions commented on Feb 12, 2022

Requirements

Environments

Status

llucasreis commented on Feb 12, 2022

llucasreis commented on Feb 13, 2022

glenn-jocher commented on Feb 14, 2022

glenn-jocher commented on Feb 14, 2022

llucasreis commented on Feb 15, 2022

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions