mean-teacher

mean-teacher copied to clipboard

Losses

4

Hi, thank you for your great project! I’m stuck with two problems while trying to test the mean teacher idea as described in your NIPS 2017 presentation with a MNIST...

rracinskij

Holmes2002

I would be very grateful if someone show me how to use this code

Holmes2002

applying mean teacher to my own dataset

4

hi, i have already achieve ~94% with 4000 labels on cifar10. But for my own three classification task, i have 160k labelled data and unlabelled data. i can not get...

liangzimei

How to train the model with unlabeled data?

1

I want to transfer the MT framework to a NLP task but I don't understand how to train it with unlabeled data. I have got the idea of the paper,...

broken-dream

Hi, The dataset preparation command in pytroch version of mean-teacher: `pip install git+ssh://[email protected]/pytorch/vision@c31c3d7e0e68e871d2128c8b731698ed3b11b119` is no longer exist. Hope you would update the dataset link later. Thank you!

TeleRagingFires

Question about DataLoader

4

Hi! Awesome work by the way. I am curious from which part of your code let you get (input, ema_input). The TwoStreamBatchSampler seem to return a single batch (not as...

jhb115

I am planning to apply mean-teacher for my problem of token classification. Since adding different noise for teacher and student is really important for the approach, i am confused about...

tarunbhatiaind

TypeError: can't serialize tensor(62, device='cuda:0')

5

I do not know why it happend. /home/lts/.conda/envs/PCL/bin/python /home/lts/PycharmProject/mean-teacher/pytorch/main.py INFO:main:=> creating model 'cifar_shakeshake26' INFO:main:=> creating EMA model 'cifar_shakeshake26' INFO:main: List of model parameters: ========================= module.conv1.weight 16 * 3 * 3...

ltc576935585

yanghu819