AI Tech 6기 Team Cㅏ이Vㅓ즈 🤖

Members

• 김찬우
• 설훈
• 이도형
• 이현지
• 조민지
• 조성혁

Project Schedule

• 

Results

• Public

• Private

Wrap-up Reports

• Notion
• pdf download

Ground Rules

Conventional Commits 1.0.0

<타입>[적용 범위(선택 사항)]: <설명>

[본문(선택 사항)]

[꼬리말(선택 사항)]

Types

• fix | feat | BREAKING CHANGE | build | chore | ci | docs | style | refactor | test | release
  • fix : 기능에 대한 버그 수정
  • feat : 새로운 기능 추가, 기존의 기능을 요구 사항에 맞추어 수정
  • build : 빌드 관련 수정
  • chore : 패키지 매니저 수정, 그 외 기타 수정 ex) .gitignore
  • ci : CI 관련 설정 수정
  • docs : 문서(주석) 수정
  • style : 코드 스타일, 포맷팅에 대한 수정
  • refactor : 기능의 변화가 아닌 코드 리팩터링 ex) 변수 이름 변경
  • test : 테스트 코드 추가/수정
  • release : 버전 릴리즈

Github Flow

It will be updated.

Requirements

• Python >= 3.5 (3.6 recommended)
• PyTorch >= 0.4 (1.2 recommended)
• tqdm (Optional for test.py)
• tensorboard >= 1.14 (see 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

pytorch-template/
│
├── 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
│
├── data/ - default directory for storing input data
│
├── model/ - models, losses, and metrics
│   ├── model.py
│   ├── metric.py
│   └── loss.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

Try python train.py -c config.json to run code.

Config file format

Config files are in .json format. 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.

# 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 sequence of keys, which are used to access that option in the config dict. In this example, target for the learning rate option is ('optimizer', 'args', 'lr') because config['optimizer']['args']['lr'] points to the learning rate. python train.py -c config.json --bs 256 runs training with options given in config.json except for the batch size which is increased to 256 by command line options.

Data Loader

• Writing your own data loader

1. Inherit BaseDataLoader

   BaseDataLoader is a subclass of torch.utils.data.DataLoader, you can use either of them.

   BaseDataLoader handles:

   • Generating next batch
   • Data shuffling
   • Generating validation data loader by calling BaseDataLoader.split_validation()

• DataLoader Usage

  BaseDataLoader is an iterator, to iterate through batches:

  for batch_idx, (x_batch, y_batch) in data_loader:
      pass

• Example

  Please refer to data_loader/data_loaders.py for an MNIST data loading example.

Trainer

• Writing your own trainer

1. Inherit BaseTrainer

   BaseTrainer handles:

   • Training process logging
   • Checkpoint saving
   • Checkpoint resuming
   • Reconfigurable performance monitoring for saving current best model, and early stop training.
     • If config monitor is set to max val_accuracy, which means then the trainer will save a checkpoint model_best.pth when validation accuracy of epoch replaces current maximum.
     • If config early_stop is set, training will be automatically terminated when model performance does not improve for given number of epochs. This feature can be turned off by passing 0 to the early_stop option, or just deleting the line of config.

2. Implementing abstract methods

   You need to implement _train_epoch() for your training process, if you need validation then you can implement _valid_epoch() as in trainer/trainer.py

• Example

  Please refer to trainer/trainer.py for MNIST training.

• Iteration-based training

  Trainer.__init__ takes an optional argument, len_epoch which controls number of batches(steps) in each epoch.

Model

• Writing your own model

1. Inherit BaseModel

   BaseModel handles:

   • Inherited from torch.nn.Module
   • __str__: Modify native print function to prints the number of trainable parameters.

2. Implementing abstract methods

   Implement the foward pass method forward()

• Example

  Please refer to model/model.py for a LeNet example.

Loss

Custom loss functions can be implemented in 'model/loss.py'. Use them by changing the name given in "loss" in config file, to corresponding name.

Metrics

Metric functions are located in 'model/metric.py'.

You can monitor multiple metrics by providing a list in the configuration file, e.g.:

"metrics": ["accuracy", "top_k_acc"],

Additional logging

If you have additional information to be logged, in _train_epoch() of your trainer class, merge them with log as shown below before returning:

additional_log = {"gradient_norm": g, "sensitivity": s}
log.update(additional_log)
return log

Testing

You can test trained model by running test.py passing path to the trained checkpoint by --resume argument.

Validation data

To split validation data from a data loader, call BaseDataLoader.split_validation(), then it will return a data loader for validation of size specified in your config file. The validation_split can be a ratio of validation set per total data(0.0 <= float < 1.0), or the number of samples (0 <= int < n_total_samples).

Note: the split_validation() method will modify the original data loader Note: split_validation() will return None if "validation_split" is set to 0

Checkpoints

You can specify the name of the training session in config files:

"name": "MNIST_LeNet",

The checkpoints will be saved in save_dir/name/timestamp/checkpoint_epoch_n, with timestamp in mmdd_HHMMSS format.

A copy of config file will be saved in the same folder.

Note: checkpoints contain:

{
  'arch': arch,
  'epoch': epoch,
  'state_dict': self.model.state_dict(),
  'optimizer': self.optimizer.state_dict(),
  'monitor_best': self.mnt_best,
  'config': self.config
}

Wandb Visualization

This template supports Wandb visualization by using Wandb library.

Quickstart

Get started with W&B in four steps:

1. First, sign up for a free W&B account.

2. Second, install the W&B SDK with pip. Navigate to your terminal and type the following command:

pip install wandb

3. Third, log into W&B:

wandb.login()

4. Use the example code snippet below as a template to integrate W&B to your Python script:

import wandb

# Start a W&B Run with wandb.init
run = wandb.init(project="my_first_project")

# Save model inputs and hyperparameters in a wandb.config object
config = run.config
config.learning_rate = 0.01

# Model training code here ...

# Log metrics over time to visualize performance with wandb.log
for i in range(10):
    run.log({"loss": loss})

That's it! Navigate to the W&B App to view a dashboard of your first W&B Experiment. Use the W&B App to compare multiple experiments in a unified place, dive into the results of a single run, and much more!

Example W&B Dashboard that shows Runs from an Experiment.

 

Contribution

TODOs

• [ ]

License

This project is licensed under the MIT License. See LICENSE for more details

Acknowledgements

This project is inspired by the project Tensorflow-Project-Template by Mahmoud Gemy