-
Hi Mike,
Thanks for the amazing piece of software you have provided us.
I have a raspberry pi 3 b and running version v2.03
I'm using the indieglo skin
Have about 2000 odd songs on it.
…
-
There is new links for beit models, it needs to be changed
https://unilm.blob.core.windows.net/beit/beit_large_patch16_224_pt22k_ft22k.pth
-
Hi, since BEIT has decoder for segmentaion task, then I want to change MAE as backbone with your pretrained model,
but I got some errors:
`The model and loaded state dict do not match exactly
un…
-
Hey,
Thank you publishing the paper for BEiT2.
I wonder know, in table 6 of the paper, what is Performance of teacher models means ?
-
### Feature request
Currently if I was to add any transforms in my training pipeline, it's not quite obvious how to do so. My usual process is to read through the source code and hope to find what I'…
-
## Our client
Dutch Softhouse, which serves a wide range of customers from different sectors. Looking for professionals to work allocated on projects in the Netherlands.
## Job description
For th…
-
Hello @NielsRogge and community,
I tried to combine ```microsoft/beit-base-patch16-224``` and ```cahya/roberta-base-indonesian-1.5G``` just by changing the following code which is in [Fine_tune_TrO…
-
请问如果想用图中的mapillary预训练模型（mask2former_beit_adapter_large_896_80k_mapillary.zip）做语义分割的话？confi…
-
**Describe the bug**
The performance of pre-trained beit_large_patch16_512 on imagenet is not as expected
**To Reproduce**
Steps to reproduce the behavior:
```
model = timm.create_model(beit_l…
-
Thanks for the great work! Did you try to use the imagenet-1k 384x384 finetuned backbones?