alien9427 / xai4sar-pgil Goto Github PK
View Code? Open in Web Editor NEWThe physics guided and injected learning NN for SAR image patch-wise classification
The physics guided and injected learning NN for SAR image patch-wise classification
In the "lad_topic_model.py" file, I made a modification to the line:
temp = OneHotEncoder(sparse=False, handle_unknown='ignore', categories=np.arange(vocab_size).reshape([1, vocab_size]))
.fit_transform(word_labels.reshape([-1,1])) * word_scores
I modified it to:
temp = OneHotEncoder(sparse=False, handle_unknown='ignore', categories=[np.arange(vocab_size)])
.fit_transform(word_labels.reshape([-1, 1])) * word_scores
This change seems to be an attempt to fix an issue. However, I mentioned that there is still an error in the "loss.py" file, specifically in the line:
loss = -attr * loss_mask.cuda() * func.log_softmax(feat, 1)
but I don't know how to modify.
Looking forward your reply.
net = torch.load('../model/resnet18_tsx.pth')
can you offer resnet18_tsx.pth
I know the cate_num
sent as ResNet18_PGIL(config['cate_num'])
to create model_CNN
represents the number of target classes.
But I don't understand how to decide the value of topic_num
sent as ResNet18_PGN(config['topic_num'])to create
model_CompNet`.
What does topic_num
represent?
from unsup_comp_attr_ICE import get_BoT,I couldn't locate the 'unsup_comp_attr_ICE' module. Can you provide guidance on how to solve?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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. 📊📈🎉
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 ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.