huizhang2017 Goto Github PK

the-gan-zoo

A list of all named GANs!

tooth-and-alveolar-bone-segmentation-from-cbct

tpu

Reference models and tools for Cloud TPUs.

transferlearning

Everything about Transfer Learning and Domain Adaptation--迁移学习

trimesh

Python library for loading and using triangular meshes.

triplet_recommendations_keras

An example of doing MovieLens recommendations using triplet loss in Keras

tsgcnet

tsgcnet-1

udacity_vechile_detection

ultra-gans

ULTRA-GAN: Generative Adversarial Network for bio-Medical Image Segmentation

unet-keras

U-Net model for Keras

unet-version

unet-zoo

A collection of UNet and hybrid architectures in PyTorch for 2D and 3D Biomedical Image segmentation

unet3d

PyTorch version of UNet3D for CT segmentation. The code also includes visdom for training visualization.

unet3d-1

A 3D Unet for Pytorch for video and 3D model segmentation

unet_brain_tumor_segmentation

Deep learning Brain tumor segmentation, BRATS2019

unetplusplus

Official Keras Implementation for UNet++ in IEEE Transactions on Medical Imaging and DLMIA 2018

uniformer

[ICLR2022] official implementation of UniFormer

vcmeshconv

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.

vitae-transformer

The official repo for [NeurIPS'21] "ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias" and [IJCV'22] "ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond"

vnet

vnet-tensorflow

Tensorflow implementation of the V-Net architecture for medical imaging segmentation.

vnet.pytorch

A PyTorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

voxelgan

3D Medical Image Semantic Segmentation

vrcnet

[CVPR 2021 Oral] Variational Relational Point Completion Network

vrn

:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"

wechat-zhihu-csdnblog-code

WeChat Official Accounts, zhihu and CSDN'blog code

weighted-voxel

Implementation of Weighted Voxel (Xie et al. 2018).

yolo-reproduce-summary

YOLO reproduce summary (now based on YOLOv3)

zihao_course

同济子豪兄的公开课