Zhiyuan Zhao

config file as follows: img_norm_cfg = dict( mean=[103.53, 116.28, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True), dict( type='Resize', img_scale=[(1333, 480), (1333, 512), (1333, 544), (1333, 576),...

Same problem here

> I have solved the problem by modifying the `train_configs/minigpt4_stage2_finetune.yaml` as below: > > ```yaml > iters_per_epoch: 20 > batch_size_train: 2 > batch_size_eval: 4 > num_workers: 2 > warmup_steps: 20...

> https://hyper.ai/datasets/21605 try this? Also not available?

> > > https://hyper.ai/datasets/21605 try this? > > > > > > Also not available? > > yes, no seed at all You can download from OpenDataLab, here is the...

> > > > > https://hyper.ai/datasets/21605 try this? > > > > > > > > > > > > Also not available? > > > > > > >...

same OOM here

> > same OOM here > > Hi @JulioZhao97 , I wonder what do you mean by here, did you succeed in pretraining stage? No, I directly run the second...

Same question, can one perform object detection fine-tuning?

> Did not try with this task by finetuning seriously. We'll figure our a solution in the near future. hello, sorry to bother, any progress?