https://github.com/bnbsking/deep-learning-playground
A space for experimenting with deep learning.
https://github.com/bnbsking/deep-learning-playground
Last synced: about 2 months ago
JSON representation
A space for experimenting with deep learning.
- Host: GitHub
- URL: https://github.com/bnbsking/deep-learning-playground
- Owner: bnbsking
- Created: 2025-01-03T07:15:00.000Z (5 months ago)
- Default Branch: main
- Last Pushed: 2025-01-03T11:45:13.000Z (5 months ago)
- Last Synced: 2025-03-27T12:01:26.655Z (2 months ago)
- Language: Python
- Size: 193 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep-Learning-Playground
A space for experimenting with deep learning.
# Quick start
+ Tabular single regression
+ Dataset: [Boston Housing](https://www.kaggle.com/code/prasadperera/the-boston-housing-dataset/data)
+ Descriptions:
+ Dense Neural Network
+ (Batch, 12) -> (Batch, 1)
+ Commands:
```bash
python _examples/boston_housing/preprocess.py
python main.py --mode train --cfg _examples/boston_housing/cfg.yaml
python main.py --mode valid --cfg _examples/boston_housing/cfg.yaml
python main.py --mode infer --cfg _examples/boston_housing/cfg.yaml
```
+ Tabular time series multiple regression
+ Dataset: [Stock Pricing Dataset](https://www.kaggle.com/datasets/hershyandrew/amzn-dpz-btc-ntfx-adjusted-may-2013may2019)
+ Descriptions:
+ Long-Short-Term-Memory or TransformerEncoder
+ default window size = 64
+ autoregression generated dataset
+ (Batch, 64, 4) -> (Batch, 4)
+ Commands
```bash
python _examples/stock_pricing/preprocess.py
python main.py --mode train --cfg _examples/stock_pricing/cfg.yaml
python main.py --mode valid --cfg _examples/stock_pricing/cfg.yaml
python main.py --mode infer --cfg _examples/stock_pricing/cfg.yaml
```
+ Image classification
+ Dataset: [Mnist](https://www.kaggle.com/c/dogs-vs-cats/data?select=train.zip)
+ Description
+ Convolutiontal Nweural Network or ResNet18 or Vit_b_16
+ (Batch, 1, 28, 28) -> (Batch, 10)
+ Commands
```bash
python _examples/mnist/preprocess.py
python main.py --mode train --cfg _examples/mnist/cfg.yaml
python main.py --mode valid --cfg _examples/mnist/cfg.yaml
python main.py --mode infer --cfg _examples/mnist/cfg.yaml
```
# Design
+ modularization, reusability, extensibility, flexibility, Readability
+ see [main.py](./main.py) and [configs](./_examples/boston_housing/cfg.yaml) to view the workflow of this framework