The use of SPPF

[Weixueying]

❔Question

How to use SPPF on the network? I directly use SPPF to replace SPP. The following error occurs:
Traceback (most recent call last):
File "/home/zwc/project/yolov5-master-828/train.py", line 602, in
main(opt)
File "/home/zwc/project/yolov5-master-828/train.py", line 500, in main
train(opt.hyp, opt, device)
File "/home/zwc/project/yolov5-master-828/train.py", line 119, in train
model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
File "/home/zwc/project/yolov5-master-828/models/yolo.py", line 98, in init
self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
File "/home/zwc/project/yolov5-master-828/models/yolo.py", line 265, in parse_model
m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args) # module
File "/home/zwc/project/yolov5-master-828/models/common.py", line 187, in init
self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
TypeError: unsupported operand type(s) for //: 'list' and 'int'

Additional context

[glenn-jocher]

@Weixueying SPPF usage is fully documented in PR #4420

[Weixueying]

Hello, may I ask what is the principle of SPPF design? After I trained with my own dataset, the inference time in the test basically remained unchanged, which was not reduced as you said.
SPP: Speed: 0.1ms pre-process, 11.8ms inference, 1.5ms NMS per image at shape (8, 3, 512, 512)
SPPF:Speed: 0.1ms pre-process, 11.7ms inference, 1.5ms NMS per image at shape (8, 3, 512, 512)

[glenn-jocher]

@Weixueying SPPF profiling results are documented in PR #4420 (comment)

SPPF is about 1/3 faster than SPP while producing mathematically identical results. Your results are for an entire model, of which SPPF is but a small change.

[github-actions]

👋 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 ⭐!