using mobilenetv3 + yolov5

[lana211191]

Disclaimer: I am a bit of a novice , i started learning deep learning 7 month ago so i might have some knowledge gaps

Hello, i want to use Mobilenetv3 with yolov5, i adjusted the code but i have an issue.
I understand that now that i changed theh backbone to mobilenet i cannot use the yolov5 pretrained weights since there is no common/similar type of layers in the backbone.

i was wondering if i can use mobilenet v3 pretrained weights (downloaded from pytorch) and freeze a part of the layers ?

If yes how can i transform the .pth file of mobilenet to .pt (accepted by yolov5)
(error that i get: mobilenet_v3_large-8738ca79.pth acceptable suffix is ['.pt'])
Thank you

[github-actions]

👋 Hello @lana211191, 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 [email protected].

Requirements

Python>=3.7.0 with all requirements.txt installed including PyTorch>=1.7. To get started:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

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.

[glenn-jocher]

@lana211191 YOLOv5 doesn't recognize *.pth suffixes which is causing your error. You can simply rename your file to end with *.pt to avoid this.

Attempting to transfer weights is a different story, you'd have to implement this feature yourself in train.py here:

yolov5/train.py

Lines 117 to 132 in 601dbb8

	# Model
	check_suffix(weights, '.pt') # check weights
	pretrained = weights.endswith('.pt')
	if pretrained:
	with torch_distributed_zero_first(LOCAL_RANK):
	weights = attempt_download(weights) # download if not found locally
	ckpt = torch.load(weights, map_location='cpu') # load checkpoint to CPU to avoid CUDA memory leak
	model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create
	exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else [] # exclude keys
	csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
	csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect
	model.load_state_dict(csd, strict=False) # load
	LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}') # report
	else:
	model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create

[zhiqwang]

FYI @lana211191 and @glenn-jocher ,

We propose a new way to construct a YOLOv5 Lite model with TorchVision's pre-trained MobileNetV3-Large FPN backbone. Concretely we restructured the YOLOv5's model into following four sub-modules in the layout of TorchVision, so it could better load the pre-trained models published by TorchVision. Maybe this can also used as a plugin for YOLOv5. See zhiqwang/yolort#342 and zhiqwang/yolort#343 for more details.

• BackboneWithPAN
• YOLOHead
• PostProcess
• SetCriterion

The SetCriterion is almost same with YOLOv5's ComputeLoss, the only differences is the output type.

[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/hub
• 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 ⭐!