zzzjzzz / compositionalhumanparsing Goto Github PK
View Code? Open in Web Editor NEW(ICCV2019) Learning Compositional Neural Infomation Fusion for Human Parsing
compositionalhumanparsing's People
Contributors
Stargazers
Watchers
compositionalhumanparsing's Issues
AttributeError: 'Namespace' object has no attribute 'num_classes' / Missing and Unexpected keys in state_dict
I assume I have all the correct dependencies since I had errors before and resolved them by installing cuda 9.0 with gcc-5 and g++-5, but now I can not seem to solve this issue.
When I run the evaluate.py script I get the following error:
Traceback (most recent call last):
File "evaluate.py", line 234, in <module>
main()
File "evaluate.py", line 37, in main
model = get_model(num_classes=args.num_classes)
AttributeError: 'Namespace' object has no attribute 'num_classes'
If I change the num_classes to anything but 7 I get the following err (this example is without putting in a parameter):
Traceback (most recent call last):
File "evaluate.py", line 234, in <module>
main()
File "evaluate.py", line 41, in main
model.load_state_dict(saved_state_dict, strict=False)
File "/home/lukak/anaconda3/envs/CompositionalHumanParsing/lib/python3.6/site-packages/torch/nn/modules/module.py", line 719, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Stream:
size mismatch for decoder.layer_dsn.3.weight: copying a param of torch.Size([20, 512, 1, 1]) from checkpoint, where the shape is torch.Size([7, 512, 1, 1]) in current model.
size mismatch for decoder.layer_dsn.3.bias: copying a param of torch.Size([20]) from checkpoint, where the shape is torch.Size([7]) in current model.
When I change the num_classes to 7 I get the following err with long list of missing keys and unexpected keys:
Traceback (most recent call last):
File "evaluate.py", line 234, in <module>
main()
File "evaluate.py", line 41, in main
model.load_state_dict(saved_state_dict)
File "/home/lukak/anaconda3/envs/CompositionalHumanParsing/lib/python3.6/site-packages/torch/nn/modules/module.py", line 719, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Stream:
Missing key(s) in state_dict: "decoder.layer5.b0.0.weight", "decoder.layer5.b0.1.weight", "decoder.layer5.b0.1.bias", ...
.
.
.
Unexpected key(s) in state_dict: "decoder.layer6.alpha", "decoder.layer6.conv0.0.weight", "decoder.layer6.conv0.1.weight", ...
.
.
.
I have searched the internet for answers but found nothing that helped and as I am not an experienced software engineer any help would be appreciated.
AttributeError: 'Namespace' object has no attribute 'num_classes' / Missing and Unexpected Key(s) in state_dict
I assume I have all the correct dependencies since I had errors before and resolved them by installing cuda 9.0 with gcc-5 and g++-5, but now I can not seem to solve this issue.
When I run the evaluate.py script I get the following error:
Traceback (most recent call last):
File "evaluate.py", line 234, in <module>
main()
File "evaluate.py", line 37, in main
model = get_model(num_classes=args.num_classes)
AttributeError: 'Namespace' object has no attribute 'num_classes'
If I change the num_classes to anything but 7 I get the following err (this example is without putting in a parameter):
Traceback (most recent call last):
File "evaluate.py", line 234, in <module>
main()
File "evaluate.py", line 41, in main
model.load_state_dict(saved_state_dict, strict=False)
File "/home/lukak/anaconda3/envs/CompositionalHumanParsing/lib/python3.6/site-packages/torch/nn/modules/module.py", line 719, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Stream:
size mismatch for decoder.layer_dsn.3.weight: copying a param of torch.Size([20, 512, 1, 1]) from checkpoint, where the shape is torch.Size([7, 512, 1, 1]) in current model.
size mismatch for decoder.layer_dsn.3.bias: copying a param of torch.Size([20]) from checkpoint, where the shape is torch.Size([7]) in current model.
When I change the num_classes to 7 I get the following err with long list of missing keys and unexpected keys:
Traceback (most recent call last):
File "evaluate.py", line 234, in <module>
main()
File "evaluate.py", line 41, in main
model.load_state_dict(saved_state_dict)
File "/home/lukak/anaconda3/envs/CompositionalHumanParsing/lib/python3.6/site-packages/torch/nn/modules/module.py", line 719, in load_state_dict
self.__class__.__name__, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for Stream:
Missing key(s) in state_dict: "decoder.layer5.b0.0.weight", "decoder.layer5.b0.1.weight", "decoder.layer5.b0.1.bias", ...
.
.
.
Unexpected key(s) in state_dict: "decoder.layer6.alpha", "decoder.layer6.conv0.0.weight", "decoder.layer6.conv0.1.weight", ...
.
.
.
I have searched the internet for answers but found nothing that helped and as I am not an experienced software engineer any help would be appreciated.
model
大佬，这个有没有开源的模型啊
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.