LeViT_UNet

For medical image segmentation

Our model is based on LeViT (https://github.com/facebookresearch/LeViT). You'd better gitclone its codes. Thanks for its great job.
There are three models which can be build directly. They are LeViT_UNet_128s, LeViT_UNet_192, and LeViT_UNet_384. You can build one of the models as it follows:

model = Build_LeViT_UNet_192(num_classes=9, pretrained=True)

model.eval()

output = model(torch.randn(1, 1, 224, 224))

If you use this code for a paper please cite:

@article{LeViT-UNet,
  author    = {Guoping Xu and
               Xingrong Wu and
               Xuan Zhang and
               Xinwei He},
  title     = {LeViT-UNet: Make Faster Encoders with Transformer for Medical Image
               Segmentation},
  journal   = {CoRR},
  volume    = {abs/2107.08623},
  year      = {2021},
  url       = {https://arxiv.org/abs/2107.08623},
  eprinttype = {arXiv},
  eprint    = {2107.08623},
  timestamp = {Thu, 22 Jul 2021 11:14:11 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2107-08623.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

For medical image segmentation

Related tags

Overview

LeViT_UNet

Owner

PyTorch implementation and pretrained models for XCiT models. See XCiT: Cross-Covariance Image Transformer

tensorrt int8 量化yolov5 4.0 onnx模型

Sample code and notebooks for Vertex AI, the end-to-end machine learning platform on Google Cloud

NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.

Fast Axiomatic Attribution for Neural Networks (NeurIPS*2021)

Unbalanced Feature Transport for Exemplar-based Image Translation (CVPR 2021)

CS50's Introduction to Artificial Intelligence Test Scripts

Lunar is a neural network aimbot that uses real-time object detection accelerated with CUDA on Nvidia GPUs.

Datasets, Transforms and Models specific to Computer Vision

An official implementation of the Anchor DETR.

GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV'18 Oral) [PyTorch]

Official code for 'Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentationon Complex Urban Driving Scenes'

Visualizer for neural network, deep learning, and machine learning models

Making self-supervised learning work on molecules by using their 3D geometry to pre-train GNNs. Implemented in DGL and Pytorch Geometric.

Object DGCNN and DETR3D, Our implementations are built on top of MMdetection3D.

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

Automatically erase objects in the video, such as logo, text, etc.

Using VapourSynth with super resolution models and speeding them up with TensorRT.

Boundary-aware Transformers for Skin Lesion Segmentation

Implementation for Shape from Polarization for Complex Scenes in the Wild