機械学習 · GitHub

モデルの学習・評価・推論に使うフレームワークを探し、注目度を比較できます。

GitHot

便利なGitHubプロジェクト

7,589 プロジェクトUpdated --

4177

SRCNN-Tensorflow

tegg89

614スター

Image Super-Resolution Using Deep Convolutional Networks in Tensorflow https://arxiv.org/abs/1501.00092v3

機械学習PythonMITGitHub

4178

TeleFuser

Tele-AI

36スター

High-performance runtime for real-time multimodal generation and world models—streaming inference, stateful sessions, and distributed GPU execution.

one-shot image generation
offline video generation

機械学習PythonApache-2.0GitHub

4179

FeatherCNN

Tencent

1,229スター

FeatherCNN is a high performance inference engine for convolutional neural networks.

機械学習C++GitHub

4180

Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.

機械学習PythonGitHub

4181

ncnn

Tencent

24,050スター

ncnnはモバイルプラットフォーム向けに最適化された高性能ニューラルネットワーク推論フレームワークです。

No third-party runtime dependencies and no BLAS / NNPACK requirement.
Pure C++ implementation with C API and Python binding.

機械学習C++GitHub

4182

PatrickStar

Tencent

772スター

PatrickStar enables Larger, Faster, Greener Pretrained Models for NLP and democratizes AI for everyone.

機械学習PythonBSD-3-ClauseGitHub

4183

PocketFlow

Tencent

2,913スター

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

機械学習PythonGitHub

4184

tencent-ml-images

Tencent

3,065スター

Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet

機械学習PythonGitHub

4185

TencentPretrain

Tencent

1,096スター

Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

Reproducibility TencentPretrain has been tested on many datasets and should match the performances of the original pre-training model implementations such as BERT, GPT-2, ELMo, T5, CLIP.
Model modularity TencentPretrain is divided into the following parts: embedding, encoder, target embedding (optional), decoder (optional), and target. Ample modules are implemented in each part. Clear and robust interface allows users to combine modules to construct pre-training models with as few restrictions as possible.

機械学習PythonGitHub

4186

TNN

Tencent

4,664スター

TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capability, high performance, model compression and code pruning. Based on ncnn and Rapidnet, TNN further strengthens the support and performance optimization for mobile devices, and also draws on the advantages of good extensibility and high performance from existed open source efforts. TNN has been deployed in multiple Apps from Tencent, such as Mobile QQ, Weishi, Pitu, etc. Contributions are welcome to work in collaborative with us and make TNN a better framework.

機械学習C++GitHub

4187

HFGI

Tengfei-Wang

474スター

CVPR 2022 HFGI: High-Fidelity GAN Inversion for Image Attribute Editing

機械学習Jupyter NotebookGitHub

4188

TensorAeroSpace

65スター

PyTorch + Gymnasium framework for aerospace control. Deep RL (SAC, PPO, DDPG, DQN, IHDP, ET-DHP) and adaptive controllers (AIDI, MPC, iADP) on nonlinear F-16/B747/UAV/satellite sims. Includes in-flight damage modeling, real-time 3D flight viewer, TensorBoard/WandB, Optuna. EN/RU docs.

機械学習Jupyter NotebookMITGitHub

4189