csyanbin / tpn-pytorch Goto Github PK
View Code? Open in Web Editor NEWPytorch Code for ICLR19 paper: Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning.
Pytorch Code for ICLR19 paper: Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learning.
How does the ratio work for? not find in the paper.
when I run the code I get the following error:
Traceback (most recent call last): File "train.py", line 280, in <module> main() File "train.py", line 210, in main loss, acc = model(inputs) File "/home/michalislazarou/anaconda3/envs/metal/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__ result = self.forward(*input, **kwargs) File "/home/michalislazarou/PhD/TPN-torch/models.py", line 170, in forward emb_all = self.encoder(inp).view(-1,1600) RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.
Hi, first of all congrats on your great work and thank you for sharing.
I'm trying to reproduce your results on tiered-ImageNet. I already trained the model. When running the testing code, which "iters" value should I load the trained model from to obtain your results displayed in your paper? That parameter is indicated for the testing phase on mini-Imagenet, but it is not for tiered-ImageNet.
Thank you for your answer.
Hello, it is really a good work!
I am confused of the value of diagonal when constructing the adjacency matrix, in your code, you didn't mask the diagonal, which will make the value of diagonal near to 1. does that limit the result of transductive (S is near to Identity matrix under this condition)?
I try to change the backbone from Conv64-4 to ResNet12, but it is harmful for the accuracy. Is this model not suitable for large networks like ResNet or there is a bug in my code? And I found that the 5-shot situation usually fails, even with Conv64-4.
solved
where is the code for transductive maml?
Hi, congrats on the work!
I got some problem when running TPN in semi-supervision setting on miniImagenet. I split each class into 40% : 60% for labeled and unlabeled data, and train with extra 5 unlabeled data for each support class (same as the setting in https://arxiv.org/abs/1803.00676). However, I only got accuracy of ~51.3, which is 1.5 lower than your paper. Do you know why this may happen?
Hello! Thanks for your great work!
I am wondering how to modify the public code to TPN-semi. Only one sentence in the paper is for this. I would appreciate it if you could give more hints.
Thanks!
Hello,Congratulations on your work and thank you for sharing.I want to reproduce your work.
I want to know How many epochs does it take to train this model before it converges?Because my configuration is not very high, it may take a long time.thank you.
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.