-
I notice that you use sent attributes of CUB dataset, but we usually use att attributes on CUB, like CLSWGAN/TF-VAEGAN and so on. Could you please provide your result when using att attributes for fa…
-
eos_idx = tokenized[idx].argmax()
this gives me index number 3 on my custom words while using context length 16.
```
eos_idx = int(self.token_ids[0].argmax())
soft_embeddings = self.attr_dr…
-
Hey, just trying out your code. I'm running into this error after trying to input a file after "Please input a filename or URL:"
This is python 3.9 on Windows 10 using the powershell.
I tried dra…
-
Paper: https://arxiv.org/pdf/2101.07978
Code: https://github.com/uqzhichen/SDGZSL
-
TL;DR - ERC721s have a ton of creators and a few marketplaces, but no accepted means for transferring royalties from items being sold multiple times on secondary sales. This EIP is proposing a standar…
-
We knonw that in line 67-68 of 'NUS_WIDE_rank_Visual_Word_Attention.py', 'pickle.load(infile)[1]' means the word vectors of unseen classes.
So, i am a little confused why do you only use unseen cla…
-
ICCV2021 paper:
Title: FREE: Feature Refinement for Generalized Zero-Shot Learning
arXiv: https://arxiv.org/pdf/2107.13807.pdf
code: https://github.com/shiming-chen/FREE
topic: Zero-shot Learni…
-
* Lampert, Christoph H., Hannes Nickisch, and Stefan Harmeling. "[Learning to detect unseen object classes by between-class attribute transfer.](MISSING)" 2009 IEEE Conference on Computer Vision and P…
-
Hi,
is it possible to comment on how you obtained the dataset splits, in the specific case of CUB. You mention you follow the configuration of [53] (_Good, bad an ugly_), but there are 3 different…
-
Hi Akshitac,
Sorry to open a new issue since I get more questions about training.
Question 1: For each epoch during training, the model is trained with seen data and then evaluate the model (fro…