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

LED_Deploy_SID_SonyA7S2_CVPR20_Setting_Ratio100-300.pth 模型测试报错 #6

Closed
kaka36 opened this issue Sep 19, 2023 · 3 comments
Closed

Comments

@kaka36
Copy link

kaka36 commented Sep 19, 2023

用image_process或python scripts/benckmark.py
-t test
-p pretrained/network_g/LED_Deploy_SID_SonyA7S2_CVPR20_Setting_Ratio100-300.pth
--dataset SID SonyA7S2
加载LED_Deploy_SID_SonyA7S2_CVPR20_Setting_Ratio100-300.pth 报错,错误为Missing key(s) in state_dict: "conv1_1.weight", "conv1_1.bias", "conv1_2.weight", "conv1_2.bias", "conv2_1.weight", "conv2_1.bias", "conv2_2.weight", "conv2_2.bias", "conv3_1.weight", "conv3_1.bias", "conv3_2.weight" ·······,是不是得从参数化之后采用用?

@kaka36
Copy link
Author

kaka36 commented Sep 20, 2023

对了,因为报错ModuleNotFoundError: No module named 'led.version',我把version相关的都屏蔽掉了

@Srameo
Copy link
Owner

Srameo commented Sep 20, 2023

您好!

Q1: 使用脚本加载预训练模型时出现 Missing keys error,是否需要重参数化?
A1: 是的,加载模型需要使用重参数化的模型。但请参考我们的 Readme 文档

LED/README.md

Line 158 in ca6b709

--led if you are using a checkpoint fine-tuned by our led.

在运行脚本时增加 --led 选项便可加载重参数化后的网络模型。

Q2: ModuleNotFoundError: No module named 'led.version'
A2: 请问可以知道您安装 LED 时候执行了我们的脚本 install.sh 吗?如果没有的话,请问可否提供下您配置环境时的具体操作吗?这可能对我们找出bug有很大帮助。

感谢您对LED的关注!

@kaka36
Copy link
Author

kaka36 commented Sep 25, 2023

谢谢,Q1可以加载了,抱歉对Python不是很熟悉。
Q2:没有按照 install.sh脚本进行环境配置,之前安装的环境,提示缺什么就装什么,没有具体的步骤,屏蔽掉version可以用不影响好像。

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