-
-
Hi, I want to reproduce this work, but I don't know the meaning of the parameter ot_weight. Could you tell me the meaning of ot_weight?
-
Hi @filipradenovic ,
For your experiment on networks with whitening learned end-to-end, with triplet loss, trained on the Google Landmarks dataset 2018: could you share to which value the GeM pooli…
-
1. [Intro/survey on Deep Metric Learning](https://www.mdpi.com/2073-8994/11/9/1066/htm) ([blogpost](https://hav4ik.github.io/articles/deep-metric-learning-survey))
2. [Improved Deep Metric Learning w…
-
Hi lucidrains,
Try this and it will NaN within 100 steps (latest Github code). The loss looks fine before NaN.
```
import torch
torch.backends.cudnn.allow_tf32 = True
torch.backends.cuda.matm…
-
Hello, I have read your paper 《Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation 》and find it interesting. I noticed that you said in the abstract
> The code w…
-
### Metadata
- Authors: Avishek Joey Bose, huan ling, Yanshuai Cao
- Organization: Borealis AI & University of Toronto
- Conference: ACL 2018
- Paper: http://aclweb.org/anthology/P18-1094
- Blog:…
-
I have millions of graph data that cannot be labeled by human efforts. I need it to be classified by unsupervised technique, not semi and not the node level. Is it possible?
-
I have a question regarding the weights used in CAV-MAE. It seems like the $\lambda_c$ could play an important role in the optimization. I understand it is due to the gradient scale but It is surprisi…
-
Good day, I see in the inference branch that you use several models, like
0809_sched_v2_fixed_Flip(fixed)_weight0.1_val.h5
0809_reverse_sched_v2_fixed_Flip(fixed)_weight0.1_val
0809_reverse_sched_…