zoubohao/Use-Diversity-Convolution-Blocks-To-Simulate-Transformer-Feature-Extraction zoubohao/Use-Diversity-Convolution-Blocks-To-Simulate-Transformer-Feature-Extraction

  • Stars
    star
    1
  • Language
    Python
  • Created almost 6 years ago
  • Updated almost 6 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
zoubohao/Use-Diversity-Convolution-Blocks-To-Simulate-Transformer-Feature-Extraction
github

zoubohao

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

This net is created by myself , and named diversity convolution blocks to simulate transformer with FPN . This is an Test for one of unit of this net . It gets powerful result !

More Repositories

1

DenoisingDiffusionProbabilityModel-ddpm-

This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
Python
1,486
star
2

Deepurify

Deepurify is a tool to filter the contaminated contigs in a MAG with a language model.
Python
8
star
3

ResNeXt_FPN

Use the frame of ResNeXt-50 and FPN model to do classification.
Python
1
star
4

Objection-Detection-using-MaskRCNN-and-FasterRCNN

This is an objection detection project. I have builded the MaskRCNN and FasterRCNN by using pytorch.
Python
1
star