ast

ast copied to clipboard

Unknown model (vit_deit_base_distilled_patch16_384)

3


BaronWang0130

some question about Deit's two [cls] token processing.

2

Hi, sorry to bother you. Why are the two special [CLS]tokens in DeiT said to be average as a single [CLS] token in the paper, but in the code I...

liyunlongaaa

The validation loss seems too high

4

Thanks for making such a wonderful repo. When I run the model, the validation loss is very high(around 0.6940), but the mAP is keep increasing normally. Could you please explain...

haoheliu

AST tiny and small pretrained models

1

Hi Yuan, I have tested your AST mode pretrained on Audioset on my own dataset and I noticed that it achieves similar performance as EfficientNet pretrained on Audioset using psla...

abaronetto

Avoid an incompatible torchvision dependency on torch 1.11.0 Fixes #68

almostimplemented

[Bug] ModuleNotFoundError: No module named 'torch.ao'

7

Following setup instructions at present will lead to an error on the model import. Specifically, `torchvision` needs to be pinned to a version. Otherwise, `pip` may install (e.g.) 0.12.0, which...

almostimplemented

Different train-(val/test) spectogram shape (recordings duration)

8

Hello! First of all, congratulations on your amazing work. I'm doing my MSc Thesis on audio classification (respiratory disease diagnosis from lung sounds). My main objective is to improve the...

danihinjos

[Question] Question about padding operation

3

Hi For audio of different lengths, the padding operation in dataset is taken on `fbank`. So why not padding on waveform first and then convert it to `fbank`.

Mountchicken

About start training: IndexError: tuple index out of range.

13

Hi, Dr.Gong, I use AST on my own dataset. I have created the .json file and .csv file according to the guide. However, when I run run.sh, an error occured...

TungyuYoung

Hi， YuanGong， Does it support distribution training with multi GPU on different machines? looking forward to you reply, thanks!

joewale