Markus Hiller

Hi @caoql98, I'll take a look whether there's been a mixup with the uploaded checkpoint, since the results you're getting seem quite a bit off. --> I assume you've tried...

Additional question: What are you obtaining regarding validation acc when fine-tuning?

> By the way, by transferring --optim_steps_online from 5 to 15,there is an improvement， I could obtain Test Acc 67.3822 + 0.8750 for 1shot 5way in miniImagenet. Maybe you provide...

> Additionally, according to the train_metatrain_FewTURE.py, the --epochs in the readme file need to rewrite as --num_epochs. The --chkpt_epoch 1599 should be --chkpt_epoch 1600 since the provided weights are xxxx1600.pth....

Have you had a chance to repeat the finetuning for 5-way 5-shot with 15 or 20 steps?

No worries! -> I've updated the Readme instructions regarding the meta-finetuning, thanks for pointing these out! (especially the 'epochs' vs 'num_epochs' argument)

I'll take a closer look tomorrow and see if I can find the logs; In the meantime, you could try lowering the similarity temp slightly: similarity_temp_init = 0.0421 Or activate...

Hi @caoql98, I've run 2 more meta-finetuning runs with **ViT and 15 optimisation steps** on miniImageNet -- one using the default temperature, and one with the lowered one I've mentioned...

Hi, Thanks for letting us know. We'll look into it and get back to you! (I assume you're getting an 'Error 404'?)

@yxyangxu : Our scripts were linking to a 3rd party drive, and the owner unfortunately took the data offline. -> We'll check out different options and adapt our scripts to...