-
# FedFomo
* **Title:** Personalized Federated Learning with First Order Model Optimization
* **Venue:** ICLR 2021
* **Link to paper:** https://openreview.net/forum?id=ehJqJQk9cw
## Do you want to wo…
-
TLC代码中的cifar10不平衡数据集有个decay_stride = 2.1971 ，最终每个种类的样本数为 [5000, 3172, 2012, 1276, 810, 514, 326, 207, 131, 83]，而RIDE每个种类样本数为 [5000, 2997, 1796, 1077, 645, 387, 232, 139, 83, 50] ，最终的分类准确率也有80.6% ；也就是说…
-
https://github.com/NervanaSystems/distiller/wiki/Frequently-Asked-Questions-(FAQ)
-
Hi all,
I'm training on CIFAR-10 following the instructions but I found that in most cases the loss function explodes during the first few iterations.
This is how it behaved when it luckily didn't …
-
Thank you very much for sharing the code and patiently answering any questions you may have. But I have another question:
When searching based on NAS, the objective function should include the infe…
-
Hi, I am trying to fine-tune b16 model on CIFAR-10 with the following commands on Google Cloud VM with 1 V100 GPU. I got a segmentation fault error.
Command
```
python -m vit_jax.main --workdir=…
yjqiu updated
5 months ago
-
How to use multiple gpu for this code ?
-
I have some questions about the training arguments (hyper-parameters) of CIFAR10-LT.
Is it the same with CIFAR100-LT?
-
Dear author:
I met some problems when I run this code, I wondered wheather you can provide the data
-
Would it be possible to get discriminator based guidance from the paper "Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models" that was published at ICML'23.
Pap…