Comments (2)
gasharper
commented on June 10, 2024
目前仓库给出的代码貌似不是最新版本。
第一个解决方案是忽略形状不匹配的权重，然后强制替换权重。
第二个解决方案是可以在训练过程保存下.pt文件，然后推理过程中加载。
from pyramidflow.
pribadihcr
commented on June 10, 2024
I tried second solution. save the pth but when loaded it still has the mismath
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for PyramidFlow:
size mismatch for nf.moduleslst.0.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 128, 128]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.1.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.2.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 256, 256]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.3.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.4.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 128, 128]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.5.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.6.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 256, 256]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.7.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.8.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 128, 128]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.9.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.10.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 256, 256]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.11.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.12.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 128, 128]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.13.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.14.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 256, 256]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
size mismatch for nf.moduleslst.15.affineParams.norm.running_mean: copying a param with shape torch.Size([1, 1, 64, 64]) from checkpoint, the shape in current model is torch.Size([1, 1, 1, 1]).
from pyramidflow.
Related Issues (17)
- 你好，PyramidFlow是one-class模型吗？需要针对每一类去训练一个模型去识别缺陷？ HOT 1
- feedback HOT 2
- About Training HOT 2
- 循环关于您的环境配置？ HOT 1
- AUPRO might be too high? HOT 2
- 为何数据集中还包括了ground truth HOT 2
- 可以告诉我怎么生成可视化图吗 HOT 2
- nvrtc-builtins64_118.dll
- 请问有测试代码嘛，单张图的测试代码
- why determinant of the Jacobian is not considered in loss? HOT 2
- ModuleNotFoundError: No module named 'autoFlow'
- How to inference HOT 2
- Difficult to reproduce paper results HOT 1
- Hello，your paper is excellent HOT 2
- 您好，train过程遇到的问题 HOT 1
- visualizing the localization results HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pyramidflow.