Lőrincz-Molnár Szabolcs-Botond

I see, thank you for the quick help. Maybe a warning / note could be added about this property, since I first assumed that by setting ``samples_per_gpu=4`` and ``cumulative_iters=4`` it...

Hi! Any updates on this? :) Thanks in advance!

Hi @xiexinch ! Ok, it's understandable, hopefully they will release pretrained weights soon. I followed the contribution guide, and used the pre-commit hooks as well, but didn't add docstrings yet...

Sure, I will try in the following days. Probably will need some help on the way, but hopefully we will manage to do it :). Best, Szabi

Hi, I have the first version of the implementation, but I am unsure whether it works or how to test it properly, what kind of tests should be written. Should...

Hi @xiexinch ! Ok, I will create a pull request soon. Unfortunately the authors didn't provide pretrained weights for now. Would you have the resources to train the networks from...

> Hi, thanks for your suggestion and PR. I think the description is not very precise. If we write `hook_cfg` in config files, mmcv will parse the config and we...

Sorry, I pushed commits by mistake to the original branch, and didn't know it will also appear here. The commits I added are trying to fix #400, I don't know...

> > Sorry, I pushed commits by mistake to the original branch, and didn't know it will also appear here. The commits I added are trying to fix #400, I...

Hi! Thanks for your quick reply! Just before calling `mmselfsup.apis.train_model`: ```python train_model( model, datasets, cfg, distributed=False, timestamp=time.strftime("%Y%m%d_%H%M%S", time.localtime()), meta=dict(), ) ``` Nevertheless, here https://github.com/open-mmlab/mmselfsup/blob/abcd43b4318e6fcef8111b10dce3146bc78019eb/mmselfsup/apis/train.py#L169-L173 it shows that the hook_cfg has...