Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

finetune.py 改变结果 #50

Open
Liampour opened this issue Nov 7, 2024 · 1 comment
Open

finetune.py 改变结果 #50

Liampour opened this issue Nov 7, 2024 · 1 comment

Comments

@Liampour
Copy link

Liampour commented Nov 7, 2024

你好
祝贺你完成了出色的工作。
我尝试使用提供的微调模型,但不确定如何使用其结果。作为数据,我从 ./data/finetune 文件夹和difficult.pt 模型输入了 25 张图像。我使用 25 张图像的数据集进行训练和测试(finetune.py 中的第 65、67 行)。以下是 finetune.py 的参数:

--batch_size', type=int, default=1, help='batch size --steps', type=float, default=100, help='finetune steps --cuda', default=True, type=bool, help='Use CUDA to train model --gpu', type=str, default='0', help='gpu device id --lr', type=float, default=0.0005, help='learning rate --seed', type=int, default=2, help='random seed --save', type=str, default='results/finetune/', help='location of the data corpus --model', type=str, default='./weights/difficult.pt', help='location of the data corpus

结果出现了一些图像,但difficult.pt 模型的行为似乎没有改变。

  1. finetune.py 会改变 .pt 模型吗?
  2. 我使用相同的数据进行训练和测试是否会影响 finetune.py 结果?
  3. 我应该如何使用它的结果?
@tengyu1998
Copy link
Owner

tengyu1998 commented Nov 7, 2024 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants