danczs / visformer Goto Github PK

你好，请问论文中所说的step-wise patch embedding的实现具体体现在哪里呢？是通过不同stage设置不同patch size的patch embedding来体现的吗？

You do not use NativeScaler and ModelEma for training?

Hi,
I understand the visformer accept input in the 3D format as in (3,244,244), can I feed data with more than 3 RGB channel into the model? like in (16, 244,244)?

Visformer have 7, 4, 4 blocks in stages S1, S2, S3, which is somewhat different from common configurations like ResNets. ResNets put the most blocks in stage 3 where the image size is 14x14, while Visformer put the most blocks in S1 where the image size is 28x28. Did you conduct some experiments and find your configuration better than ResNets in terms of performance and accuracy? I would appreciate it if you could provide these experiment results or your thoughts on it. Thank you!

作者你好，我注意到visformer_tiny在model.py和swin_model.py中都有给出，而visformer_tinyV2只在swin_model.py中给出，请问visformer_tinyV2的精度提升1个百分点是微调网络结构带来的，还是swin_model.py这种方式实现带来的精度提升。

Can you provide a training example for the base setting?

Hi, I want to extend the model on my own task, will you release pre-trained weights?

作者您好，请问这个模型的test测试文件有吗？
is there has a test.py to test this model?
thinks.

Can you provide a training example for the base setting?