weihuang
weihuang
I found that googlenet.py also occupies so many gpu memory that when I train it on ImageNet dataset , even 4 gpus with 20GB per gpu are not enough.
> > I found that googlenet.py also occupies so many gpu memory that when I train it on ImageNet dataset , even 4 gpus with 20GB per gpu are not...
@bbidong now the directory cub is empty,do you mean delete the directory and then manual add it?how can i manual add it?could you give more details? thank you
@keyu-tian I have tried this setting except that batch size is 2048, for the reason that 8 gpus cannot accommodate 4096 images. Unfortunately, my training losses became NaN. Does the...
@keyu-tian The args are: ``` (nstream_imagenet/main.py, line 29)=> initial args: {'base_lr': 0.002, 'batch_size_per_gpu': 256, 'best_val_acc': 0.0, 'bs': 2048, 'clip': -1, 'cmd': '--local_rank=0 --exp_name res50 --exp_dir ' './output//Spark_res50_official_finetune_default_lr2e-3_ld0_7_300e ' '--data_path=imagenet2012/ImageNet_ILSVRC2012 '...
@keyu-tian ConvNeXt-small seems normal so far.
@keyu-tian Have you found the resnet-50 fine-tuning problem? The ConvNeXt-small reaches 83.96 validation acc fine-tuning from your released pertaining weights.
hi~ I'm confused by the same issue with you ,have you figure out?
@Zzzzz1 I use the original batch size 512 on 8 2080ti. After re-ran the code, I got the following results:  It seems still unstable and much worse than the...
@JinYu1998 23min/epoch.