-
Hi.
Thank you for sharing the code, It's wonderful.
The difference between 1-shot and 5-shot setting's **sampling** is only [here](https://github.com/leokarlin/LaSO/blob/master/oneshot/alfassy/dat…
-
# Ask a Question
### Question
I want to convert Prototypical Networks for Few-shot Learning to onnx.
torch.onnx.export(model,(example_query_images, example_query_labels, x_pred), "super_resoluti…
-
I have tried prototypical networks on my data. It looks to be working fine as the eval loss is decreasing consistently.
But do you have any piece of code to get a prediction from the model on the ne…
-
### Description
I have enjoyed using org-roam thus far and been using that quite extensively. Though I can't help noticing that the mode becomes sluggish very quickly when there are a few hundred n…
-
I've tried two versions of prototypical-networks source code. Both of them get me this result, train loss is bigger and train accuracy is lower.
-
On calling network.create_variables() for my agent (using a DDPG agent), my GPU memory gets used 100% instantly and never clears up.
I can control it by using a virtual memory cap, but I need memory …
-
### Subtitle : Matching Networks, Prototypical Networks, Siamese Networks, Relation Networks
- Date/Time : 11/2(Mon), 20:00
**Description**
Few shot classification with metric based meta lear…
vrvrv updated
4 years ago
-
Thank you very much for developing such a great project and publishing it to the public. When I was reading your code, I have some questions and would like to ask you. Because I am new to meta-learnin…
-
I want to point out that your prototype is so similar to the category anchor in 'Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation'.
Could you please show me the diff…
-
Hi,
Thanks for the detailed documentation -- It was very helpful!
I have a question regarding the re-implementation of Protonet with the Resnet-12 backbone. How many ways were used to train for bo…
ars22 updated
4 years ago