corecai163 / odgnet Goto Github PK
View Code? Open in Web Editor NEW[AAAI24] Orthogonal Dictionary Guided Shape Completion Network for Point Cloud
[AAAI24] Orthogonal Dictionary Guided Shape Completion Network for Point Cloud
Hello:
Thank you for your excellent work. I encountered the following error when using your pretrained model on the KITTI dataset to reproduce your code:
2024-06-17 22:55:28,236 - UpTrans - INFO - Loading weights from ckpts/UpTrans/KITTI_models/ckpt-best.pth...
Traceback (most recent call last):
File "main.py", line 69, in <module>
main()
File "main.py", line 63, in main
test_net(args, config)
File "/home/brj/ODGNet/tools/runner.py", line 347, in test_net
builder.load_model(base_model, args.ckpts, logger=logger)
File "/home/brj/ODGNet/tools/builder.py", line 129, in load_model
base_model.load_state_dict(base_ckpt)
File "/home/brj/anaconda3/envs/IGEV_Stereo/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1604, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for UpTrans:
Missing key(s) in state_dict: "feat_extractor.refine_1.dict_embed.weight", "feat_extractor.refine_1.query.weight", "feat_extractor.refine_1.query.bias", "feat_extractor.refine_1.key.weight", "feat_extractor.refine_1.key.bias", "feat_extractor.refine_2.dict_embed.weight", "feat_extractor.refine_2.query.weight", "feat_extractor.refine_2.query.bias", "feat_extractor.refine_2.key.weight", "feat_extractor.refine_2.key.bias".
Unexpected key(s) in state_dict: "feat_extractor.refine_1.0.dict_embed.weight", "feat_extractor.refine_1.0.query.weight", "feat_extractor.refine_1.0.query.bias", "feat_extractor.refine_1.0.key.weight", "feat_extractor.refine_1.0.key.bias", "feat_extractor.refine_1.1.dict_embed.weight", "feat_extractor.refine_1.1.query.weight", "feat_extractor.refine_1.1.query.bias", "feat_extractor.refine_1.1.key.weight", "feat_extractor.refine_1.1.key.bias", "feat_extractor.refine_2.0.dict_embed.weight", "feat_extractor.refine_2.0.query.weight", "feat_extractor.refine_2.0.query.bias", "feat_extractor.refine_2.0.key.weight", "feat_extractor.refine_2.0.key.bias", "feat_extractor.refine_2.1.dict_embed.weight", "feat_extractor.refine_2.1.query.weight", "feat_extractor.refine_2.1.query.bias", "feat_extractor.refine_2.1.key.weight", "feat_extractor.refine_2.1.key.bias".
This error indicates that the keys in the model's state_dict do not match those in the weight file. How can I resolve this issue?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.