-
Dear author(s),
Can this algorithm be used in another context different than image classification?
Thank you in advance for your help,
Best regards,
san89 updated
5 years ago
-
In framework.eval()
->support, query, label = eval_dataset.next_batch(B, N, K, Q, noise_rate=noise_rate)
how to get support set from test dataset without labels.
-
Hi, I have a question regarding your augmentation methods. In your code, scaling and center crop is still applied when augmentation is False in both training and validation stage. In the repo jakesnel…
ghost updated
5 years ago
-
Hi
I have a question about image loading in omniglot_dataset.py
Why use 1 - array & why use transpose and reshape as below?
`https://github.com/orobix/Prototypical-Networks-for-Few-shot-Learn…
-
For the practical application, how to use it predict the test set without labels ?
-
Just to hold the place...I'm working on this currently, but wanted to get this out there so people know it is happening. I'd assign it to myself, but it doesn't look like I can do so.
Things that sh…
sivel updated
5 years ago
-
Dear Chen,
I noticed that you used cross-entropy loss function in your code, but the author of the paper tried to minimize the distance between query and support data who share the same lable, which …
-
1. [Optimizer's Curse: Skepticm and Postdecision Surprise in Decision Analysis](https://faculty.fuqua.duke.edu/~jes9/bio/The_Optimizers_Curse.pdf)
2. [Issues in Using Function Approximation for Reinf…
-
I ran Proto-MiniImagenet and I got followings
[epoch 93/100, episode 100/100] => loss: 2.99573, acc: 0.05000
[epoch 94/100, episode 50/100] => loss: 2.99573, acc: 0.05000
[epoch 94/100, episode 10…
-
It's a great work on comparison among softmax, siameses and triplets networks, I am wondering what kind of metric do you think is possible to compare different methods fairly in stead of only qualitat…