-
When using DistributedDataParallel, if N labeled training images and K GPUs are used, should we set num_labeled = N / K instead of N? since np.random.shuffle(idx) generate different idxs in different …
-
## Why
Machine Learning 輪講は最新の技術や論文を追うことで、エンジニアが「技術で解決できること」のレベルをあげていくことを目的にした会です。
prev. #46
## What
話したいことがある人はここにコメントしましょう！
面白いものを見つけた時点でとりあえず話すという宣言だけでもしましょう！
-
## Why
Machine Learning 輪講は最新の技術や論文を追うことで、エンジニアが「技術で解決できること」のレベルをあげていくことを目的にした会です。
prev. #33
## What
話したいことがある人はここにコメントしましょう！
面白いものを見つけた時点でとりあえず話すという宣言だけでもしましょう！
-
## Paste the link of the GitHub organisation below and submit
https://github.com/google-research
---
###### Please subscribe to this thread to get notified when a new repository is created
-
Hello, thanking for your pytorch implement of MPL. I think the dot_prodoct should be s_loss_old - s_loss_new but s_loss_new - s_loss_old for the reason here
just flip a coin
Am I wrong?
-
Thanks for your excellent work! Could you please tell me how to reimplement the fixmatch results in your paper (e.g. in Fig.3)?
-
Hello! Thanks for ur excellent work! But i did not see any introductions experiments on dataset of officeHome on this github project which u did in ur paper. So I'd ask could u offer some more detaile…
-
Hi @clott3,
Thanks for the repo :)
I'm facing an issue when running the repo with the following command
`python train_bayes_cifar.py --dataset=cifar10 --num_labeled=2000 --bayes --final_quan…
-
I am using the library to run Semi supervised models on my dataset
i used the custom dataset code given in google colab and converted my dataset images to csv
when i run the code to train the datase…
-
Thank you very much for your work. In the usb_cv results, I found that the differences in experimental results were a little big. fixmatch: 29.6+0.9 flexmatch:26.76+1.12, but random seeds had been fi…