Closed developer0hye closed 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.
Python 3.8 or later with all requirements.txt dependencies installed, including torch>=1.7
. To install run:
$ pip install -r requirements.txt
YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):
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.
@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.
@glenn-jocher Thanks for your reply. I have one question. How is mAP on val set exactly same with mAP on test set??
👋 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:
Access additional Ultralytics ⚡ resources:
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 ⭐!
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?