The simplest, fastest repository for training/finetuning medium-sized GPTs.

Spatial Dynamic Wind Power Forecasting. This task has practical importance for the utilization of wind energy. Participants are expected to accurately estimate the wind power supply of a wind farm.

Forecast of aircraft parts failures and optimization of spare parts stock management

小型金融知识图谱构建流程

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Implementation of Vision Transformer from scratch and performance compared to standard CNNs (ResNets) and pre-trained ViT on CIFAR10 and CIFAR100.

A simplified version of incremental structure from motion to reconstruct the 3D structure of a scene from a sequence of 2D images

YOLOv5 in PyTorch > ONNX > CoreML > iOS

AutoML tools chain

PyTorch ,ONNX and TensorRT implementation of YOLOv4

SGAS: Sequential Greedy Architecture Search (CVPR'2020) https://www.deepgcns.org/auto/sgas

72.8% MobileNetV2 1.0 model on ImageNet and a spectrum of pre-trained MobileNetV2 models

A specially designed light version of Fast AutoAugment

Automated Deep Learning without ANY human intervention. 1'st Solution for AutoDL challenge@NeurIPS.

手把手撕LeetCode题目，扒各种算法套路的裤子。English version supported! Crack LeetCode, not only how, but also why.

Official Implementation of 'Fast AutoAugment' in PyTorch.

Codes for our paper "Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation"

🎥 一个简单的电影推荐系统