add ghostbottleneck module to yolov5s.yaml

[leoncch]

❔Question

when I add ghostbottleneck module to yolov5s.yaml

Additional context

parameters

nc: 2 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple

anchors

anchors:

• [10,13, 16,30, 33,23] # P3/8
• [30,61, 62,45, 59,119] # P4/16
• [116,90, 156,198, 373,326] # P5/32

YOLOv5 backbone

backbone:

[from, number, module, args]

[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, GhostBottleneck, [128, 3, 1]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, GhostBottleneck, [256, 3, 1]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, GhostBottleneck, [512, 3, 1]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, GhostBottleneck, [1024, 3, 1]], # 9
]

YOLOv5 head

head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2]],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, GhostBottleneck, [512, 3, 1]], # 13

[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2]],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, GhostBottleneck, [256, 3, 1]], # 17 (P3/8-small)

[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, GhostBottleneck, [512, 3, 1]], # 20 (P4/16-medium)

[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, GhostBottleneck, [1024, 3, 1]], # 23 (P5/32-large)

[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]

[github-actions]

👋 Hello @leoncch, 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
$ cd yolov5
$ 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), validation (val.py), inference (detect.py) and export (export.py) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.

[leoncch]

can someone tell me the correct way to replace YOLOv5 bottleneckcps to ghostbottleneck, thanks！

[glenn-jocher]

@leoncch good news 😃! Your original issue may now be fixed ✅ in PR #4412. This PR adds a new yolov5s-ghost.yaml file to data/hub models. You can start training this with:

python train.py --cfg yolov5s-ghost.yaml --weights yolov5s.pt

To receive this update:

• Git – git pull from within your yolov5/ directory or git clone https://github.com/ultralytics/yolov5 again
• PyTorch Hub – Force-reload with model = torch.hub.load('ultralytics/yolov5', 'yolov5s', force_reload=True)
• Notebooks – View updated notebooks
• Docker – sudo docker pull ultralytics/yolov5:latest to update your image

Thank you for spotting this issue and informing us of the problem. Please let us know if this update resolves the issue for you, and feel free to inform us of any other issues you discover or feature requests that come to mind. Happy trainings with YOLOv5 🚀!

[fabiozappo]

@glenn-jocher is yolov5s-ghost more indicated for deploy on embedded devices? Did you run any test about number of parameters and flops?

[glenn-jocher]

@fabiozappo see PR #4412