Ablation experiment for SPP Layer

developer0hye commented 3 years ago

https://github.com/ultralytics/yolov5/blob/06372b1465f5a58463bf8c32bdf65fc679c17ebf/models/yolov5l.yaml#L23

@glenn-jocher

Hi, jocher!

Have you experimented ablation experiment for SPP Layer?

If so, can you share the results about the experiment?

I have seen this method in many papers(yolov4, ppyolo, ...). Do you think that its performance is acceptable for lightweight detector in terms of trade-off between speed and performance?

github-actions[bot] commented 3 years ago

👋 Hello @developer0hye, 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.

glenn-jocher commented 3 years ago

@developer0hye well, the simplest ablation experiment is YOLOv3 vs YOLOv3-SPP, where the SPP() layer is the only change. You can see this comparison in https://github.com/ultralytics/yolov3#pretrained-checkpoints

The layer itself profiles very quickly, so it is not adding excessive time or FLOPS to the forward pass. You can profile individual YOLO layers using yolo.py with the profile sections uncommented.

developer0hye commented 3 years ago

@glenn-jocher Thanks for your reply. I have one question. How is mAP on val set exactly same with mAP on test set??

github-actions[bot] commented 3 years ago

👋 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
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 ⭐!

ultralytics / yolov5