G2比赛代码.zip

# PyTorch Template Project PyTorch deep learning project made easy. <!-- @import "[TOC]" {cmd="toc" depthFrom=1 depthTo=6 orderedList=false} --> <!-- code_chunk_output --> * [PyTorch Template Project](#pytorch-template-project) * [Requirements](#requirements) * [Features](#features) * [Folder Structure](#folder-structure) * [Usage](#usage) * [Config file format](#config-file-format) * [Using config files](#using-config-files) * [Resuming from checkpoints](#resuming-from-checkpoints) * [Using Multiple GPU](#using-multiple-gpu) * [Customization](#customization) * [Custom CLI options](#custom-cli-options) * [Data Loader](#data-loader) * [Trainer](#trainer) * [Model](#model) * [Loss](#loss) * [metrics](#metrics) * [Additional logging](#additional-logging) * [Validation data](#validation-data) * [Checkpoints](#checkpoints) * [Tensorboard Visualization](#tensorboard-visualization) * [Contribution](#contribution) * [TODOs](#todos) * [License](#license) * [Acknowledgements](#acknowledgements) <!-- /code_chunk_output --> ## modification notes * put the data in the same dir to source code. ``` images_test_A images_train_5s pytorch-template ``` * modify config.json to change parameters. Some parameters are not used * steps: * train with validation set: in config.json, stage is "train", command: python train.py -c config.json * train with all train data: keep the parameters the same, change "stage" in config.json to "all", run the same command: * test: command python test.py -c config.json -r /path/to/you best model parameters * prediction result can be find in saved/model/G2/[timestamps]/prediction.json ## Requirements * Python >= 3.5 (3.6 recommended) * PyTorch >= 0.4 (1.2 recommended) * tqdm (Optional for `test.py`) * tensorboard >= 1.14 (see [Tensorboard Visualization](#tensorboard-visualization)) ## Features * Clear folder structure which is suitable for many deep learning projects. * `.json` config file support for convenient parameter tuning. * Customizable command line options for more convenient parameter tuning. * Checkpoint saving and resuming. * Abstract base classes for faster development: * `BaseTrainer` handles checkpoint saving/resuming, training process logging, and more. * `BaseDataLoader` handles batch generation, data shuffling, and validation data splitting. * `BaseModel` provides basic model summary. ## Folder Structure ``` folder structure/ │ ├── train.py - main script to start training ├── test.py - evaluation of trained model │ ├── config.json - holds configuration for training ├── parse_config.py - class to handle config file and cli options │ ├── new_project.py - initialize new project with template files │ ├── base/ - abstract base classes │ ├── base_data_loader.py │ ├── base_model.py │ └── base_trainer.py │ ├── data_loader/ - anything about data loading goes here │ ├── data_loaders.py │ └── g2dataset.py/ - customized class for G2 dataset and transforms │ ├── model/ - models, losses, and metrics │ ├── loss.py │ ├── metric.py - accuracy and score │ ├── model.py │ ├── resnet.py - models used for G2 │ ├── scheduler.py - learning rate scheduler │ └── utils.py │ ├── saved/ │ ├── models/ - trained models are saved here │ └── log/ - default logdir for tensorboard and logging output │ ├── trainer/ - trainers │ └── trainer.py │ ├── logger/ - module for tensorboard visualization and logging │ ├── visualization.py │ ├── logger.py │ └── logger_config.json │ └── utils/ - small utility functions ├── util.py └── ... ``` ## Usage The code in this repo is an MNIST example of the template. Try `python train.py -c config.json` to run code. ### Config file format Config files are in `.json` format: ```javascript { "name": "Mnist_LeNet", // training session name "n_gpu": 1, // number of GPUs to use for training. "arch": { "type": "MnistModel", // name of model architecture to train "args": { } }, "data_loader": { "type": "MnistDataLoader", // selecting data loader "args":{ "data_dir": "data/", // dataset path "batch_size": 64, // batch size "shuffle": true, // shuffle training data before splitting "validation_split": 0.1 // size of validation dataset. float(portion) or int(number of samples) "num_workers": 2, // number of cpu processes to be used for data loading } }, "optimizer": { "type": "Adam", "args":{ "lr": 0.001, // learning rate "weight_decay": 0, // (optional) weight decay "amsgrad": true } }, "loss": "nll_loss", // loss "metrics": [ "accuracy", "top_k_acc" // list of metrics to evaluate ], "lr_scheduler": { "type": "StepLR", // learning rate scheduler "args":{ "step_size": 50, "gamma": 0.1 } }, "trainer": { "epochs": 100, // number of training epochs "save_dir": "saved/", // checkpoints are saved in save_dir/models/name "save_freq": 1, // save checkpoints every save_freq epochs "verbosity": 2, // 0: quiet, 1: per epoch, 2: full "monitor": "min val_loss" // mode and metric for model performance monitoring. set 'off' to disable. "early_stop": 10 // number of epochs to wait before early stop. set 0 to disable. "tensorboard": true, // enable tensorboard visualization } } ``` Add addional configurations if you need. ### Using config files Modify the configurations in `.json` config files, then run: ``` python train.py --config config.json ``` ### Resuming from checkpoints You can resume from a previously saved checkpoint by: ``` python train.py --resume path/to/checkpoint ``` ### Using Multiple GPU You can enable multi-GPU training by setting `n_gpu` argument of the config file to larger number. If configured to use smaller number of gpu than available, first n devices will be used by default. Specify indices of available GPUs by cuda environmental variable. ``` python train.py --device 2,3 -c config.json ``` This is equivalent to ``` CUDA_VISIBLE_DEVICES=2,3 python train.py -c config.py ``` ## Customization ### Project initialization Use the `new_project.py` script to make your new project directory with template files. `python new_project.py ../NewProject` then a new project folder named 'NewProject' will be made. This script will filter out unneccessary files like cache, git files or readme file. ### Custom CLI options Changing values of config file is a clean, safe and easy way of tuning hyperparameters. However, sometimes it is better to have command line options if some values need to be changed too often or quickly. This template uses the configurations stored in the json file by default, but by registering custom options as follows you can change some of them using CLI flags. ```python # simple class-like object having 3 attributes, `flags`, `type`, `target`. CustomArgs = collections.namedtuple('CustomArgs', 'flags type target') options = [ CustomArgs(['--lr', '--learning_rate'], type=float, target=('optimizer', 'args', 'lr')), CustomArgs(['--bs', '--batch_size'], type=int, target=('data_loader', 'args', 'batch_size')) # options added here can be modified by command line flags. ] ``` `target` argument should be s