Prediction from backbone

[goo-goo-goo-joob]

Search before asking

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

Question

Hello,

How can I get the prediction from backbone layer from already trained model?

Thank you!

Additional

No response

[github-actions]

👋 Hello @goo-goo-goo-joob, 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.

[glenn-jocher]

@goo-goo-goo-joob the 'backbone' of YOLOv5 models don't produce any predictions, they run convolutions and sequentially downsample the image to larger strides. They have output feature grids (like all layers). Detections (at each of the different scales, i.e. P3, P4, P5 etc) are only produced in the final Detect() layer at the end of the model. You can see the model architectures in each model yaml, i.e.:

yolov5/models/yolov5s.yaml

Lines 12 to 48 in 3bb233a

	# YOLOv5 v6.0 backbone
	backbone:
	# [from, number, module, args]
	[[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
	[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
	[-1, 3, C3, [128]],
	[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
	[-1, 6, C3, [256]],
	[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
	[-1, 9, C3, [512]],
	[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
	[-1, 3, C3, [1024]],
	[-1, 1, SPPF, [1024, 5]], # 9
	]
	# YOLOv5 v6.0 head
	head:
	[[-1, 1, Conv, [512, 1, 1]],
	[-1, 1, nn.Upsample, [None, 2, 'nearest']],
	[[-1, 6], 1, Concat, [1]], # cat backbone P4
	[-1, 3, C3, [512, False]], # 13
	[-1, 1, Conv, [256, 1, 1]],
	[-1, 1, nn.Upsample, [None, 2, 'nearest']],
	[[-1, 4], 1, Concat, [1]], # cat backbone P3
	[-1, 3, C3, [256, False]], # 17 (P3/8-small)
	[-1, 1, Conv, [256, 3, 2]],
	[[-1, 14], 1, Concat, [1]], # cat head P4
	[-1, 3, C3, [512, False]], # 20 (P4/16-medium)
	[-1, 1, Conv, [512, 3, 2]],
	[[-1, 10], 1, Concat, [1]], # cat head P5
	[-1, 3, C3, [1024, False]], # 23 (P5/32-large)
	[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
	]

[goo-goo-goo-joob]

@glenn-jocher Is there a possibility to get raw output vector (feature grids) from backbone?

[glenn-jocher]

@goo-goo-goo-joob there's a possibility to do anything you want if you put the work in.

[glenn-jocher]

@goo-goo-goo-joob you can visualize these feature grids by the way with detect.py --visualize. If you follow the visualize code you can see where to access the feature grids. See #3920 for example.