There are 39 repositories under pretrained-models topic.
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Deezer source separation library including pretrained models.
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
A PyTorch implementation of EfficientNet and EfficientNetV2 (coming soon!)
Natural Language Processing Best Practices & Examples
Segmentation models with pretrained backbones. PyTorch.
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
Easy-to-use and powerful NLP library with Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including Neural Search, Question Answering, Information Extraction and Sentiment Analysis end-to-end system.
A treasure chest for visual recognition powered by PaddlePaddle
Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Sandbox for training deep learning networks
Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.
A curated list of pretrained sentence and word embedding models
Implementation of EfficientNet model. Keras and TensorFlow Keras.
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.
Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS
GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型
The PyTorch-based audio source separation toolkit for researchers
An open source implementation of CLIP.
A collection of computer vision pre-trained models.
Classification models trained on ImageNet. Keras.
This repo contains implementation of different architectures for emotion recognition in conversations.
Awesome Pretrained Chinese NLP Models，高质量中文预训练模型集合
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".
An extension of Open3D to address 3D Machine Learning tasks
Keras implementation of BERT with pre-trained weights
Tensorflow implementation of the SRGAN algorithm for single image super-resolution
a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results
Data repository for pretrained NLP models and NLP corpora.
Real-time pose estimation accelerated with NVIDIA TensorRT