PyTorch framework A simple and complete framework for PyTorch, providing a variety of data loading and simple task solutions that are easy to extend and migrate

Last update: Dec 19, 2021

Related tags

Pytorch Utilities PyTorch-framework

Overview

PyTorch framework

一个简单且完整的PyTorch的框架，提供了各种数据的加载以及简单任务的解决方案，易于扩展和迁移。

1.该框架提供了各种数据类型的加载(.wav .mat .jpg .csv .npy)方案。

2.该框架提供了简单分类任务和回归任务的解决方案，以及几个基础模型：CNN、RNN、Attention （ResNet、LSTM、Transformer-encoder)

3.该框架是一个简单且完整的框架，只保留了必要的部分并有详细的注释，方便阅读和理解。

并且解耦了各个模块，易于扩展和迁移。迁移到其他任务上只需要更改dataloader和model部分 (还有损失函数)。

用法：

训练和验证

python main.py --dataset_path ./data/audio/wav2vec/ --model_path  wav2vec --feature wav2vec --feature_dim 768 --task regression --model lstm

python main.py --dataset_path ./data/vision/AU/ --model_path  AU --feature AU --feature_dim 34 --task regression --model lstm

python main.py --dataset_path ./data/vision/vggface/ --model_path  vggface --feature vggface --feature_dim 128 --task regression --model lstm

python main.py --dataset_path ./data/vision/image/ --model_path  image --feature image  --task classification --model resnet

测试

python test.py --dataset_path ./data/audio/wav2vec/ --model_path  ./model/wav2vec_regression_1.pth --feature wav2vec --feature_dim 768 --task regression --model lstm

多卡训练

CUDA_VISIBLE_DEVICES=0,1 python main.py --dataset_path ./data/vision/image/ --model_path  image --feature image  --task classification --model resnet --parallel

CUDA_VISIBLE_DEVICE 和 parallel 搭配使用，单用 parallel 会默认使用所有卡。

如果有任何问题，欢迎联系我（[email protected])

PyTorch framework A simple and complete framework for PyTorch, providing a variety of data loading and simple task solutions that are easy to extend and migrate

Related tags

Overview

PyTorch framework

Owner

Cong Cai

Pretrained ConvNets for pytorch: NASNet, ResNeXt, ResNet, InceptionV4, InceptionResnetV2, Xception, DPN, etc.

Model summary in PyTorch similar to `model.summary()` in Keras

This is an differentiable pytorch implementation of SIFT patch descriptor.

GPU-accelerated PyTorch implementation of Zero-shot User Intent Detection via Capsule Neural Networks

S3-plugin is a high performance PyTorch dataset library to efficiently access datasets stored in S3 buckets.

OptNet: Differentiable Optimization as a Layer in Neural Networks

Fast and Easy-to-use Distributed Graph Learning for PyTorch Geometric

Fast, general, and tested differentiable structured prediction in PyTorch

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

PyTorch to TensorFlow Lite converter

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision

Tutorial for surrogate gradient learning in spiking neural networks

Learning Sparse Neural Networks through L0 regularization

Fast Discounted Cumulative Sums in PyTorch

Pytorch bindings for Fortran

PyNIF3D is an open-source PyTorch-based library for research on neural implicit functions (NIF)-based 3D geometry representation.

Differentiable SDE solvers with GPU support and efficient sensitivity analysis.

Training PyTorch models with differential privacy

Tacotron 2 - PyTorch implementation with faster-than-realtime inference