머신러닝 · GitHub

Differentiable architecture search for convolutional and recurrent networks

Implementation of EfficientNet model. Keras and TensorFlow Keras.

Photographs to a textured mesh on one 8 GB NVIDIA card, offline. Built on TRELLIS.2, with a four view path, and the photographs' own pixels projected onto the texture so printed text stays readable.

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models

• Convolutional sequence-to-sequence model with attention for text-to-speech synthesis
• Multi-speaker and single speaker versions of DeepVoice3

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

Pytorch implementation of "Fully-Convolutional Siamese Networks for Object Tracking"

Residual networks implementation using Keras-1.0 functional API

Neural network visualization toolkit for keras

Crater is a cloud-native AI training & inference platform.

CS231n notes, CS231n lecture notes — Stanford CS231n 2025: deep learning for computer vision notes

Build a World Model from Scratch — the Vizuara AI lecture series: slides, from-scratch code, and Colab notebooks

This repository is for all those AI enthusiastics who actually loves to read books and learn.

A Real-time Mario Kart 64 AI using ConvNets.

[ICCV 2017] Torch code for Grad-CAM