-
Thanks for your error report and we appreciate it a lot.
**Checklist**
1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.
…
-
Hi,
The paper 'Image as a Foreign Language: BEIT Pretraining for All Vision and Vision-Language Tasks' is very interesting!
But I cannot find the code in this project yet.
Could you please releas…
-
Hi awesome work! I was wondering about the details of using Beit3 for finetuning. It is mentioned that for downstream tasks like retrieval biet3 is first finetuned using a contrastive objective in or…
-
Hi, I am currently looking for the initialization of BEiT. The default setting for output projection and FFN weights are scaled by 1 / sqrt(2*N), where N is the current layer id. When I see the paper …
-
**Describe**
Model I am using (UniLM, MiniLM, LayoutLM ...): BEIT
I am try to reproducing self-supervised pre-training BEiT-base on ImageNet-1k and then fine-tuning on ADE20K, in your paper it will …
-
Hi, I have two questions about the test.py file.
1. I'm trying to use test.py in the same way that I got image_demo.py working. I've noticed that test.py doesn't have an image directory argument si…
-
Hello, when I read and reproduce your work, there is a consistent question about VQ-KD. When training MIM, it can be regarded as an offline teacher or Tokenizer, but can't it perform Imagenet classifi…
-
微博内容精选
-
Hi, thanks for the great work and releasing the code!
I want to finetune ViT-adapter but am running into `RuntimeError: CUDA error: an illegal memory access was encountered`.
Inference works fin…
-
**Describe**
Model I am using BEIT, and I wonder how to reproduce acc@1 88.60 on the imagenet1k.
I used hyperparameter in the [get_started_for_image_classification.md](https://github.com/microsoft/u…