Qian Li

长文本截断，比如身份证，请问有什么办法解决么

Excuse me, compared to bakcbone, CBN is better than S, why is there no CBN in all experiments in the end, but there is S？ table is from yolov4 paper(i.e.,tabke4)...

CA is suitable for standard vgg or resnet?

1

How much better can CA improve performance on common network architectures such as VGG and ResNet ? Thanks!

 In each row the first tensor is pred and the second tensor is gt. Why are the Euler angles so different? Thanks!

Hello，for lightweight networks (e.g., mobilenet, efficient), which is better compared to MoCo-v3？ Thanks!

[unimim] mismatched positional_embed about vit-large/14 for input resolution with 196

1

hello, for CLIP knowledge distilation paper, i.e.,A Unified View of Masked Image Modeling: when the teacher is CLIP vit-large/14 for 196's input resolution, and the student is vit-base/16 for 224's...

Hello，can you share the fine-tuned model on ImageNet-1K？ Thanks very much！

How to get every tree according to the attribute?

1

Can you tell me how to the tree (Visual,Geometrical,Lexical and so on) for parent, you use the static npy file.  Thanks!

details about the base model and the fine-tuned

11

I use two gpus, the other configurations is the same as the author, why is my performance poor? - The following figure is the eval of 500 epochs for base...

Hello, you can share the code about evaluating on COCOdatasets? Thanks