peggyxpxu

It is recommended to expose these parameters rather than hide them in the code, which can lead to training errors . > We do not use the same value in...

hi, sir > 24GB*4 needs use low-resource code. > > Note this change: > > Original: > > https://github.com/YuanGongND/ltu/blob/8c8f92446a8121fc78d2f7dece2a6e08dc2061b2/src/ltu/train_script/finetune_toy.sh#L18 > > Low resource: > > https://github.com/YuanGongND/ltu/blob/8c8f92446a8121fc78d2f7dece2a6e08dc2061b2/src/ltu/train_script/finetune_toy_low_resource.sh#L21 > > In general,...

> Yes, that is as expected. You need either 1X 48G GPU; or 4 X 24G GPUs (we used 4 X 48G). A single 32G GPU needs some additional work...

> hi there, thanks for the question. > > We mentioned this in the paper, page 6, Section 5.1, under subsection "audio classification": > > > We tested two prompts...

thanks for the help!

i use Eval_metrics in #29 , but also have error: ``` Traceback (most recent call last):   File "/home/aipf/work/code/ltu_all/ltu-main/src/ltu_as/eval/eval_audiocaps.py", line 82, in      res = evaluate_metrics(save_fold + '/sample_pred_audiocaps_{:d}.csv'.format(trial), save_fold + '/sample_truth_audiocaps_{:d}.csv'.format(trial), 5)   ...