DeepFish - GitLite

KO | EN

gitlite — search

#javascript #python #react #llm #go #macos #windows #awesome #vue #awesome-list #pytorch #security #ios #mcp

DeepFish

(★ 136)

JCU DeepFish dataset

파일 탐색기

최종 버전 다운로드 (.zip)

- - __init__.py
  - fish_clf.py
  - fish_loc.py
  - fish_reg.py
  - fish_seg.py
  - image_folder.py
- - __init__.py
  - csrnet.py
  - fcn8.py
  - fcn8_vgg16.py
  - glance.py
  - inception.py
  - lcfcn.py
  - resfcn.py
  - resnet.py
  - unet.py
- - blobs_functions.py
- - __init__.py
  - clf_wrapper.py
  - loc_wrapper.py
  - reg_wrapper.py
  - seg_wrapper.py
- __init__.py
- metrics.py
- utils.py
- count.gif
- Figure_4.png
- index.html
- project.mobirise
- seg.gif
- single_image_loc.png
- single_image_seg.png
- predict.py
- predict_simple.py
- train_single_image.py
.gitignore
exp_configs.py
LICENSE
README.md
requirements.txt
results.ipynb
setup.py
trainval.py

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/alzayats/DeepFish

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd DeepFish

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

jupyter notebook

브라우저에서 노트북(.ipynb) 파일들을 열람하고 실행할 수 있는 Jupyter 화면을 켭니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

## DeepFish (A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis)

### Accepted at Nature Scientific Reports [[Paper]](https://www.nature.com/articles/s41598-020-71639-x) [[Dataset]](http://data.qld.edu.au/public/Q5842/2020-AlzayatSaleh-00e364223a600e83bd9c3f5bcd91045-DeepFish/)  [[Project]](https://alzayats.github.io/DeepFish/)

![CNN](https://raw.githubusercontent.com/alzayats/DeepFish/master/docs/Figure_4.png)
![counting](https://raw.githubusercontent.com/alzayats/DeepFish/master/docs/count.gif) 
![Segmentation](https://raw.githubusercontent.com/alzayats/DeepFish/master/docs/seg.gif)

The dataset consists of approximately 40 thousand images collected underwater from 20 habitats in the marine-environments of tropical Australia.
The dataset originally contained only classification labels. Thus, we collected point-level and segmentation labels to have a more comprehensive fish analysis benchmark.
Videos for DeepFish were collected for 20 habitats from remote coastal marine environments of tropical Australia. These videos were acquired using cameras mounted on metal frames, deployed over the side of a vessel to acquire video footage underwater. The cameras were lowered to the seabed and left to record the natural fish community, while the vessel maintained a distance of 100 m. The depth and the map coordinates of the cameras were collected using an acoustic depth sounder and a GPS, respectively. Video recording was carried out during daylight hours and in relatively low turbidity periods. The video clips were captured in full HD resolution (1920 × 1080 pixels) from a digital camera. In total, the number of video frames taken is 39,766. 
[[more]](https://research.jcu.edu.au/data/published/48fcdde6576ee929325b01fca4207914/)

## To install DeepFish as a Python package for access outside the repo:
`python setup.py install` OR `pip install -e .`

## Install requirements
`pip install -r requirements.txt`

`pip install git+https://github.com/ElementAI/LCFCN`

## Download

*  Download the DeepFish dataset from [here](http://data.qld.edu.au/public/Q5842/2020-AlzayatSaleh-00e364223a600e83bd9c3f5bcd91045-DeepFish/)

## 1. Train and test on single image

### Localization
```
python scripts/train_single_image.py -e loc -d ${PATH_TO_DATASET}
```

This outputs the following image

![CNN](https://raw.githubusercontent.com/alzayats/DeepFish/master/docs/single_image_loc.png)

### Segmentation

```
python scripts/train_single_image.py -e seg -d ${PATH_TO_DATASET}
```

This outputs the following image

![CNN](https://raw.githubusercontent.com/alzayats/DeepFish/master/docs/single_image_seg.png)

## 2. Train and test on the dataset

Run the following command to reproduce the experiments in the paper:

`python trainval.py -e ${TASK} -sb ${SAVEDIR_BASE} -d ${DATADIR} -r 1`

The variables (`${...}`) can be substituted with the following values:

* `TASK` : loc, seg, clf, reg
* `SAVEDIR_BASE`: Absolute path to where results will be saved
* `DATADIR`: Absolute path containing the downloaded datasets

Experiment hyperparameters are defined in `exp_configs.py`

## 3. Predict on your own images or video

To run a trained model on **your own data** (arbitrary images or a video you
recorded) without the DeepFish dataset structure (no CSV files or masks needed),
use `scripts/predict_simple.py`. It runs on GPU or CPU automatically.

### On a folder of images
```
python scripts/predict_simple.py -i ${PATH_TO_IMAGES} -m ${PATH_TO_MODEL}.pth -t loc -o output/
```

### On a video
Frames are extracted automatically. Use `--frame_stride` to sample every Nth
frame (e.g. one frame every half second for a 30 fps clip with `--frame_stride 15`):
```
python scripts/predict_simple.py --video ${PATH_TO_VIDEO}.mp4 -m ${PATH_TO_MODEL}.pth -t loc -o output/ --frame_stride 15
```

`-t/--task` can be `loc` (localization/counting via points), `seg` (segmentation),
`clf` (fish / no-fish classification), or `reg` (count regression) — it must match
the task the model was trained for.

Results are written to the output directory:
```
output/
    predictions.json     # Per-image predictions (counts, points, etc.)
    frames/              # Extracted video frames (only when --video is used)
    visualizations/      # Visualization images (for loc and seg tasks)
```

> `scripts/predict.py` is a separate tool that visualizes predictions against the
> **DeepFish dataset** validation split (it requires the dataset structure and its
> ground-truth labels). For new/unlabelled data, use `predict_simple.py` above.

## Citations

If you use the DeepFish dataset in your work, please cite it as:

```
@article{saleh2020realistic,
  title={A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis},
  author={Saleh, Alzayat and Laradji, Issam H and Konovalov, Dmitry A and Bradley, Michael and Vazquez, David and Sheaves, Marcus},
  journal={Scientific Reports},
  volume={10},
  number={1},
  pages={14671},
  year={2020},
  publisher={Nature Publishing Group UK London},
  doi={https://doi.org/10.1038/s41598-020-71639-x}
}
```