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

ONNX Runtime for PyTorch accelerates PyTorch model training using ONNX Runtime.

An implementation of Performer, a linear attention-based transformer, in Pytorch

Riemannian Adaptive Optimization Methods with pytorch optim

A tutorial on "Bayesian Compression for Deep Learning" published at NIPS (2017).

Training PyTorch models with differential privacy

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

PyGCL: Graph Contrastive Learning Library for PyTorch

A very simple and small path tracer written in pytorch meant to be run on the GPU

lookahead optimizer (Lookahead Optimizer: k steps forward, 1 step back) for pytorch

Pytorch implementation of Distributed Proximal Policy Optimization

This is an differentiable pytorch implementation of SIFT patch descriptor.

PyTorch Lightning Optical Flow models, scripts, and pretrained weights.

A Closer Look at Structured Pruning for Neural Network Compression

A tiny package to compare two neural networks in PyTorch

ocaml-torch provides some ocaml bindings for the PyTorch tensor library.

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

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

Implements pytorch code for the Accelerated SGD algorithm.

3D-RETR: End-to-End Single and Multi-View3D Reconstruction with Transformers

Distiller is an open-source Python package for neural network compression research.