124 Open source projects that are alternatives of or similar to Pretrained

BERT for Multitask Learning

An extension of Open3D to address 3D Machine Learning tasks

Tensorflow implementation of the SRGAN algorithm for single image super-resolution

Silero Models: pre-trained STT models and benchmarks made embarrassingly simple

Detect various irregularities of a product as it moves along a conveyor belt.

Supplementary information and code for the paper: An efficient deep learning model for musical onset detection

Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models

🏡 Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

An unofficial Gluon FR Toolkit for face recognition. https://gluon-face.readthedocs.io

This repo contains implementation of different architectures for emotion recognition in conversations.

A deep neural network that learns to drive in video games

Finetuning any DNN for better embedding on neural search tasks

The PyTorch-based audio source separation toolkit for researchers

A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

Pretrained EfficientNet, EfficientNet-Lite, MixNet, MobileNetV3 / V2, MNASNet A1 and B1, FBNet, Single-Path NAS

[CVPR2020] f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation https://arxiv.org/abs/2001.10331

Pytorch-Named-Entity-Recognition-with-BERT

[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

74.3% MobileNetV3-Large and 67.2% MobileNetV3-Small model on ImageNet

A PyTorch implementation of EfficientNet and EfficientNetV2 (coming soon!)

Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more

Neural syntax annotator, supporting sequence labeling, lemmatization, and dependency parsing.

A repository that shares tuning results of trained models generated by TensorFlow / Keras. Post-training quantization (Weight Quantization, Integer Quantization, Full Integer Quantization, Float16 Quantization), Quantization-aware training. TensorFlow Lite. OpenVINO. CoreML. TensorFlow.js. TF-TRT. MediaPipe. ONNX. [.tflite,.h5,.pb,saved_model,tfjs,tftrt,mlmodel,.xml/.bin, .onnx]

PyTorch and Tensorflow functional model definitions

A collection of pre-trained RL agents using Stable Baselines3

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Real-time pose estimation accelerated with NVIDIA TensorRT

Pre-trained NFNets with 99% of the accuracy of the official paper "High-Performance Large-Scale Image Recognition Without Normalization".

高质量中文预训练模型集合：最先进大模型、最快小模型、相似度专门模型

Classification models trained on ImageNet. Keras.

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

DimeNet and DimeNet++ models, as proposed in "Directional Message Passing for Molecular Graphs" (ICLR 2020) and "Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Molecules" (NeurIPS-W 2020)

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

Repository containing an independent implementation of the paper: "A Fully Progressive Approach to Single-Image Super-Resolution"

ImageNet pre-trained models with batch normalization for the Caffe framework

This repository contains PyTorch implementation for the baseline models from the paper Utterance-level Dialogue Understanding: An Empirical Study

End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service

Keras implementation of BERT with pre-trained weights

Segmentation models with pretrained backbones. PyTorch.

Motion Fused Frames implementation in PyTorch, codes and pretrained models.

Spleeter is Deezer source separation library with pretrained models written in Python and uses Tensorflow. It makes it easy to train source separation model (assuming you have a dataset of isolated sources), and provides already trained state of the art model for performing various flavour of separation :

a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results

InceptionV3, InceptionV4, Inception-Resnet pretrained models for Torch7 and PyTorch

Create a smart video application using the Intel Distribution of OpenVINO toolkit. The toolkit uses models and inference to run single-class object detection.

SQuAD Question Answering Using BERT, PyTorch

Fine-tune pretrained Convolutional Neural Networks with PyTorch

PyTorch-style and human-readable RegNet with a spectrum of pre-trained models

Pretrained BERT model for analysing COVID-19 Twitter data

HugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision

Natural Language Processing Best Practices & Examples

PyTorch implementation of "Pyramid Scene Parsing Network".

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

Data repository for pretrained NLP models and NLP corpora.

A TensorFlow implementation of the Mnemonic Descent Method.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

[ICCV 2019] Harmonious Bottleneck on Two Orthogonal Dimensions

A collection of computer vision pre-trained models.

Deep Neural Networks Improve Radiologists' Performance in Breast Cancer Screening