How to freeze backbone when finetune on custom dataset

[lzyuan168]

Before Asking

• I have read the README carefully. 我已经仔细阅读了README上的操作指引。

• I want to train my custom dataset, and I have read the tutorials for finetune on your data carefully and organize my dataset correctly; 我想训练自定义数据集，我已经仔细阅读了训练自定义数据的教程，以及按照正确的目录结构存放数据集。

• I have pulled the latest code of main branch to run again and the problem still existed. 我已经拉取了主分支上最新的代码，重新运行之后，问题仍不能解决。

Search before asking

• I have searched the DAMO-YOLO issues and found no similar questions.

Question

Hi, I would like to know if there is an option to freeze backbone when finetuning on custom dataset. Because according to the the tutorial, there is only a line to add "self.train.finetune_path" which points to the pretrained .pth weights. However, if I run the train.py file without freezing the backbone, isn't that equal to training from scratch?

Thank you.

Additional

No response

[ksv87]

DAMO-YOLO/damo/detectors/detector.py

Lines 12 to 25 in 319572e

	class Detector(nn.Module):
	def __init__(self, config):
	super().__init__()
	self.backbone = build_backbone(config.model.backbone)
	self.neck = build_neck(config.model.neck)
	self.head = build_head(config.model.head)
	self.config = config
	def init_bn(self, M):

you can freeze backbone here