IOU Threshold and Anchor Box sizes

[wajhh]

Hi I wanna ask that how can we find the iou threshold of our results and how do we get to see the anchor box sizes ? Please guide or leave your email se I can personally contact you thanks

[github-actions]

👋 Hello @wajhh, 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 Glenn Jocher at glenn.jocher@ultralytics.com.

Requirements

Python>=3.6.0 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.

[glenn-jocher]

@wajhh YOLOv5 🚀 anchors are saved as Detect() layer attributes on model creation, and updated as necessary by AutoAnchor before training starts. Their exact location is here:

yolov5/models/yolo.py

Line 45 in f17c86b

self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)

You can examine the anchors of any trained YOLOv5 model like this:

Input

import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False)  # official model
model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt',  autoshape=False)  # custom model

# Anchors
m = model.model[-1]  # Detect() layer
print(m.anchors * m.stride.view(-1, 1, 1))  # print anchors

Output

YOLOv5 🚀 2021-11-22 torch 1.10.0+cu111 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)
#           x     y
tensor([[[ 10.,  13.],
         [ 16.,  30.],
         [ 33.,  23.]],  # P3/8-small

        [[ 30.,  61.],
         [ 62.,  45.],
         [ 59., 119.]],  # P4/16-medium

        [[116.,  90.],
         [156., 198.],
         [373., 326.]]], dtype=torch.float16)  # P5/32-large

Good luck 🍀 and let us know if you have any other questions!

[wajhh]

@glenn-jocher thank you for your reply, I will definitely look into this and get back to you if this was helpful. Can you please let me know that iou threshold is the only one in detect.py or do we get any other iou threshold after the outcomes ?

[jaideep11061982]

@wajhh YOLOv5 🚀 anchors are saved as Detect() layer attributes on model creation, and updated as necessary by AutoAnchor before training starts. Their exact location is here:

yolov5/models/yolo.py

Line 45 in f17c86b

self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)

You can examine the anchors of any trained YOLOv5 model like this:

Input

import torch

# Model
model = torch.hub.load('ultralytics/yolov5', 'yolov5s', autoshape=False)  # official model
model = torch.hub.load('ultralytics/yolov5', 'custom', 'path/to/best.pt',  autoshape=False)  # custom model

# Anchors
m = model.model[-1]  # Detect() layer
print(m.anchors * m.stride.view(-1, 1, 1))  # print anchors

Output

YOLOv5 🚀 2021-11-22 torch 1.10.0+cu111 CUDA:0 (Tesla V100-SXM2-16GB, 16160MiB)
#           x     y
tensor([[[ 10.,  13.],
         [ 16.,  30.],
         [ 33.,  23.]],  # P3/8-small

        [[ 30.,  61.],
         [ 62.,  45.],
         [ 59., 119.]],  # P4/16-medium

        [[116.,  90.],
         [156., 198.],
         [373., 326.]]], dtype=torch.float16)  # P5/32-large

Good luck 🍀 and let us know if you have any other questions!

@glenn-jocher
1)how does these anchors change wrt anchors_T hyper param.

2. Does this value used while building them ?
3. default is 4 ,if i inrease it to say 8 how does anchors size will vary

[glenn-jocher]

@jaideep11061982 I don't know. Why don't you just change the hyperparameter and observe the effect on AutoAnchor?

[github-actions]

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.

Access additional YOLOv5 🚀 resources:

• Wiki – https://github.com/ultralytics/yolov5/wiki
• Tutorials – https://docs.ultralytics.com/yolov5
• Docs – https://docs.ultralytics.com

Access additional Ultralytics ⚡ resources:

• Ultralytics HUB – https://ultralytics.com/hub
• Vision API – https://ultralytics.com/yolov5
• About Us – https://ultralytics.com/about
• Join Our Team – https://ultralytics.com/work
• Contact Us – https://ultralytics.com/contact

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLOv5 🚀 and Vision AI ⭐!