openmixup

openmixup copied to clipboard

AutoMix tutorial that is independent of MMClassification

1

Dear Authors, Inspiring work! Could you please provide a simplified demo/tutorial of how to use **AutoMix** in general PyTorch training? I have no experience of using OpenMMLab-style framework. A small...

lofrienger

[Feature] Can we load ImageNet data using LMDB?

3

### Describe the feature Current ImageNet data loader can only support pillow, cv2 backends to load images. By some reasone, I need to use LMDB to load dataset which is...

wang-tf

Pre-trained model of A2MIM

7

Hi, when will the pre-trained model of A2MIM be released in the [webpage](https://github.com/Westlake-AI/openmixup/tree/main/configs/selfsup/a2mim/)? The work is so meaningful！ Thank you!

zugofn

i want to train my custom dataset, how can??

2

i want use adautomix with my custom dataset. and i want to use adautomix in my independent environment. how can?? please tell me about some guide

KUKUDAS95

[Bug] Docker Build Fails

1

### Describe the bug Dear authors, thanks for this great and comrpehensive work. I am having troubles replicating the conda environment, thus I have switched to the docker file. Disclaimer,...

stsavian

# Welcome update to OpenMMLab 2.0 I am Vansin, the technical operator of OpenMMLab. In September of last year, we announced the release of OpenMMLab 2.0 at the World Artificial...

vansin

[Feature] Migration to OpenMMLab 2.0 framework.

1

### Describe the feature Hi, OpenMixup Team. We have release the OpenMMLab 2.0 framework, and release the new version of [MMClassification](https://github.com/open-mmlab/mmclassification/tree/dev-1.x/mmcls) and [MMSelfSup](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x). We also introduce the new features in...

tonysy

Implement migratory A2MIM

1

Can you provide a simple code for A2MIM? The current situation is that changing the design of A2MIM requires a deep reading of the code of openmixup, which is inefficient...

zhenyuZ-HUST

### Describe the bug training with sh file: tools\single_train.sh would report a runtime-error: RuntimeError: Default process group has not been initialized, please make sure to call init_process_group. it made that...

Lxml-q