https://github.com/frgfm/kaggle-whale-id
Short team project about the Kaggle Whale identification challenge
https://github.com/frgfm/kaggle-whale-id
image-classification kaggle-competition python pytorch
Last synced: 2 months ago
JSON representation
Short team project about the Kaggle Whale identification challenge
- Host: GitHub
- URL: https://github.com/frgfm/kaggle-whale-id
- Owner: frgfm
- License: mit
- Created: 2018-12-22T11:19:17.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-01-12T17:01:14.000Z (over 6 years ago)
- Last Synced: 2024-12-29T17:41:25.502Z (4 months ago)
- Topics: image-classification, kaggle-competition, python, pytorch
- Language: Jupyter Notebook
- Size: 2.04 MB
- Stars: 0
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Kaggle whale identification challenge
This repository is a short team project about the Kaggle Whale identification [challenge](https://www.kaggle.com/c/humpback-whale-identification).
## Requirements
The torch, torchvision, numpy, pandas and matplotlib packages are required to properly use the repo.
Tested on the following version:
```python
import sys
import torch, torchvision, numpy, pandas, matplotlib
print(f"Python {'.'.join(map(str, sys.version_info[:3]))}")
print(f"PyTorch {torch.__version__}, Torchvision {torchvision.__version__}, Numpy {numpy.__version__}, Pandas {pandas.__version__}, Matplotlib {matplotlib.__version__}")
```
```console
Python 3.6.5
PyTorch 1.0.0, Torchvision 0.2.1, Numpy 1.15.4, Pandas 0.23.4, Matplotlib 2.2.3
```
##
## How to use it
Download the dataset, and run the training script
### Downloading the dataset
- Create a data folder within the root
- Join the Kaggle competition (accept the terms)
- Download the dataset directly with browser download or set your [Kaggle API](https://github.com/Kaggle/kaggle-api) and run the following commands
```bash
cd data
kaggle competitions download -c humpback-whale-identification
```
- Unzip the train and test folders
## TODO
- [ ] Explanatory Data Analysis
- [ ] State-of-the-art review
- [ ] Submission implementation
- [ ] Optimization & improvements