cyh1112 / graphnormalization Goto Github PK
View Code? Open in Web Editor NEWLearning Graph Normalization for Graph Neural Networks
Home Page: https://arxiv.org/abs/2009.11746.pdf
License: Other
Learning Graph Normalization for Graph Neural Networks
Home Page: https://arxiv.org/abs/2009.11746.pdf
License: Other
Hi,
I'm trying to understand and run training on SROIE dataset. Based on my understanding currently index based encoding is used based on alphabet string. How can i change to something like work2vec or tfidf?
How can i train on other languages like German?
One more question, We have around 200 labeled invoices, is this data enough for training or is it possible to use transfer learning?
Hello, thank you very much for your work. I noticed num_features in your code. I want to know what it means and how it is set in use.Thank you for your reply.
train.py runs ok.
and changed to resume from checkpoint runs ok too.
but test.py throws the following error.
Traceback (most recent call last):
File "test.py", line 270, in
main()
File "test.py", line 201, in main
model = load_gate_gcn_net(device, checkpoint_path)
File "test.py", line 187, in load_gate_gcn_net
model.load_state_dict(checkpoint)
site-packages/torch/nn/modules/module.py", line 847, in load_state_dict
self.class.name, "\n\t".join(error_msgs)))
RuntimeError: Error(s) in loading state_dict for GatedGCNNet:
Missing key(s) in state_dict: "layers.4.A.weight", "layers.4.A.bias", "layers.4.B.weight", "layers.4.B.bias", "layers.4.C.weight", "layers.4.C.bias", "layers.4.D.weight", "layers.4.D.bias", "layers.4.E.weight", "layers.4.E.bias", "layers.4.bn_node_h.gamma", "layers.4.bn_node_h.beta", "layers.4.bn_node_e.gamma", "layers.4.bn_node_e.beta", "layers.5.A.weight", "layers.5.A.bias", "layers.5.B.weight", "layers.5.B.bias", "layers.5.C.weight", "layers.5.C.bias", "layers.5.D.weight", "layers.5.D.bias", "layers.5.E.weight", "layers.5.E.bias", "layers.5.bn_node_h.gamma", "layers.5.bn_node_h.beta", "layers.5.bn_node_e.gamma", "layers.5.bn_node_e.beta", "dense_layers.4.bn.weight", "dense_layers.4.bn.bias", "dense_layers.4.linear.weight", "dense_layers.4.linear.bias", "dense_layers.5.bn.weight", "dense_layers.5.bn.bias", "dense_layers.5.linear.weight", "dense_layers.5.linear.bias".
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.