Dassl.pytorch

Dassl.pytorch copied to clipboard

Feature Request: Implementation of SSDA like data loaders

2

Hi, Is there any plan to introduce the semi-supervised domain adaptation data loaders in the code? There are UDA and SSL loaders, but for SSDA, we might need different target...

shreejalt

Run SimCLR using Dassl

1

Hi Kaiyang Can you please point me to how can I implement a two-view dataloader for training using the SimCLR loss. Basically, I want the train dataloader to return two...

AadSah

Dynamic Instance Domain Adaptation

1

Impressive work. Can' t wait to get the code. so when?!

BoltenWang-Meta

about DAEL

1

Hi, thanks for sharing your code. I want to use your DAEL model, but can ADEL support the scene that multi-source with different categories (such as category-shift problem solved in...

cquzys

Installing this repository with pip

2

Hi there, when installing this repository with ```pip install -r requirements.txt``` (where the *requirements.txt* file contains ```git+https://github.com/KaiyangZhou/Dassl.pytorch.git```), the ```import numpy as np``` in *setup.py* throws a ModuleNotFoundError, because numpy is...

NilsHulzebosch

Low accuracy on SelfEnsembling; mnist -> mnist_m;

1

Hi, thanks for sharing your code. I tried it out trainer=SelfEnsembling, source_domain=mnist and traget_domain=mnist_m and I was expecting to get around 95% accuracy on the test subset, target_domain. But I...

georgepachitariu

Hi everyone, It seems that PAWS is state of the art in semi-supervised learning https://github.com/facebookresearch/suncet https://arxiv.org/abs/2104.13963 It would be interesting to add it to the framework. I created the PR...

jmarrietar

We have improved the implementation of MixStyle to make it more flexible. Recall that MixStyle has two versions: random mixing and cross-domain mixing. The former randomly shuffles the batch dimension...

KaiyangZhou

Replication Parameters and How to use MixStyle and EFDM

1

Dear Kaiyang Really appreciate the open-source domain generalization framework. It is really amazing. I'm currently working on replicating the results and extending my work on the current framework. Do you...

VirtueZhao

How can I change the vision encoder and text encoder to custom pretrained clip vision encoder and text encoder?

dumbelldore