master-sau's Introduction

master-sau

This is a repository for the altered YOLOv5 codebase and scripts used in the Master Thesis - Improved Sheep Detection, written in the spring of 2022. The altered YOLOv5 model found in this repository makes it possible to run YOLOv5 with a fourth channel of information, in our case this was Infrared Radiation (IR) imagery.

The branch master only contains the standard model to process RGB images.

The branch four-input contains the model which combines RGB images and IR images as 4 channels before processing the image.

The branch generic-fusion contains the model which processes RGB images and IR images separetly in the backbone, and combines the results in a fusion module before the neck/head.

The data folder is ignored, but should look like this:

data/
- train/
  - images/*.jpg
  - ir/*.jpg
  - labels/*.txt
- validation/
  - images/*.jpg
  - ir/*.jpg
  - labels/*.txt
- test/
  - images/*.jpg
  - ir/*.jpg
  - labels/*.txt

master-sau's People

Contributors

Stargazers

Watchers

master-sau's Issues

What is the structure of Yolo V5 Generic Fusion?

First of all, thank you for this great program.

I am a beginner and have some questions.

Regarding the network structure of generic fusion, is it correct that the RGB and Ir processes are fused just before the head?

Also, I was looking at the Tensorboard graph and I am a little confused. Is the output from SPPF being input to the first layer simply because the same processing that is used for SPPF is used for the output from SPPF as for the first input?

4 channel data

Hi, I'm wondering how to train your yolo_four_input model while preparing RGB data and another infrared data. Could you please give me some hints?

how about val.py file!

How to use val.py the same way you introduced train.py?

What I mean can that be used for val.py? or just the same way as the official yolov5 after training you use val.py for validation ?
please help me out.

Problem with val.py. missing argument in val.py

Hi there!

I have been trying to run val.py which imports yolo_four_input

in the function _forward_augment

yi = self._forward_once(xi)[0] # forward
just one argument is passed to forward_once where it expects at least two. Why is x_ir missing? I think you don't want to augment IR images which is understood.

but how to resolve this.
Thank you!

Recommend Projects