Python - 100天从新手到大师

Learn how to design, develop, deploy and iterate on production-grade ML applications.

此项目是机器学习(Machine Learning)、深度学习(Deep Learning)、NLP面试中常考到的知识点和代码实现，也是作为一个算法工程师必会的理论基础知识。

This repository contains the source code for the paper First Order Motion Model for Image Animation

Best Practices, code samples, and documentation for Computer Vision.

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

A curated list of applied machine learning and data science notebooks and libraries across different industries (by @firmai)

TensorFlow Basic Tutorial Labs

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

[CVPR 2022] Thin-Plate Spline Motion Model for Image Animation.

A denoising autoencoder + adversarial losses and attention mechanisms for face swapping.

深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI

验证码识别

MTCNN face detection implementation for TensorFlow, as a PIP package.

Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+

[CVPR 2022] Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer

Project for Digital Image Processing

Official PyTorch repo for GAN's N' Roses. Diverse im2im and vid2vid selfie to anime translation.

StyleGAN Encoder - converts real images to latent space

Official implementation of "Designing an Encoder for StyleGAN Image Manipulation" (SIGGRAPH 2021) https://arxiv.org/abs/2102.02766

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744

Deep Learning Examples

Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization

StyleGAN Encoder - converts real images to latent space

Fine-tuning StyleGAN2 for Cartoon Face Generation

猫狗大战

Statistics and Visualization of acceptance rate, main keyword of CVPR 2019 accepted papers for the main Computer Vision conference (CVPR)

风格迁移三部曲