Semi-supervised-learning

Semi-supervised-learning copied to clipboard

I am not able to obtain the same accruacy as shown in train log using eval code. Do you have any suggestions ?

Bala93

--------------------------------------------------------------------------- AttributeError Traceback (most recent call last) [](https://localhost:8080/#) in 1 # define data loaders ----> 2 train_lb_loader = get_data_loader(config, lb_dataset, config.batch_size) 3 train_ulb_loader = get_data_loader(config, ulb_dataset, int(config.batch_size * config.uratio)) 4...

MRK4863

Hi, great work. Can you provide the training logs as well as the checkpoints for classic cv training?

beandkay

question about training time in classic_cv and use_amp

1

First thanks to your code base! It needs to be acknowledged that your USB_cv's ViT backbone is excellent and can get better result in shorter time than classic_cv, but I...

wyyfffff

Example for Custom Dataset Usage in NLP

3

## 🚀 Feature How can I use custom nlp dataset to try these algorithms on? I only saw example for CV custom dataset. Main part I am intereseted in is...

Rasmitha23

## 🚀 Feature Improvement of current EMA module should be made, for saving GPU memory and easier application of ema model. ### Motivation Current EMA model are on the same...

Hhhhhhao

Add Unimatch ?

1

## 🚀 Feature Add Unimatch semi supervised framework : https://github.com/LiheYoung/UniMatch ### Motivation This seem to be a SOTA semi supervised framework in many domains. Thanks

tcourat

there‘s a bug in the net resnet50，the self.fc(x) is missing

1

## Bug ### Reproduce the Bug ### Error Messages and Logs

Bkamie

som question about get_cosine_schedule_with_warmup

1

Hello , thanks for Semi-supervised-learning, [semilearn/core/utils/build.py:217:def get_cosine_schedule_with_warmup](https://github.com/microsoft/Semi-supervised-learning/blob/08334816951fef8e770e435b04a88de3c1427f2b/semilearn/core/utils/build.py#L217) I want to know why num_cycles set 7. / 16，have some referance？ And I checked the original algorithm of the [cosine Annealing algorithm](https://arxiv.org/abs/1704.00109)....

wenyuhaokikika

Semi-supervised-learning/semilearn/datasets/cv_datasets /cifar.py代码是否有误？

1

113行和114行完全一样？

YaxinHou