https://github.com/12austincc/Cleavage-StageEmbryoSegmentation

https://github.com/12austincc/Cleavage-StageEmbryoSegmentation

Last synced: about 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/12austincc/Cleavage-StageEmbryoSegmentation
• Owner: 12austincc
• License: mit
• Created: 2024-06-26T12:23:45.000Z (7 months ago)
• Default Branch: main
• Last Pushed: 2024-09-18T02:13:20.000Z (4 months ago)
• Last Synced: 2024-09-18T10:39:44.256Z (4 months ago)
• Language: Python
• Size: 37.4 MB
• Stars: 2
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• Awesome-Segment-Anything - [code

README

        
# Cleavage-Stage Embryo Segmentation Using SAM-Based Dual Branch Pipeline: Development and Evaluation with the CleavageEmbryo Dataset

This is the official pytorch implementation of SAM-Based Dual Branch Pipeline, please refer the [paper](url) for more details.

## Dataset

CleavageEmbryo Dataset.

[]()

## Install

The code requires `python>=3.8`, as well as `pytorch>=1.7` and `torchvision>=0.8`.

Install Segment Anything:

```

pip install git+https://github.com/facebookresearch/segment-anything.git

```

Install requirements:

```

pip install -r requirements.txt

```

## QuickStart

[sam_dual](https://whueducn-my.sharepoint.com/:u:/g/personal/2020302111430_whu_edu_cn/EVPYa9MhqG5FjPuOsNRNvY4Bepec4ZXdjKpZtum0Gq0uaQ?e=Rk1JNl)

[yolo](https://whueducn-my.sharepoint.com/:u:/g/personal/2020302111430_whu_edu_cn/EUaMh7yAWKpHubH-QNWtJfwBnaHTimkIHyaRYS5-Z2sYuA?e=ngwvjX)

### Inference test images

```

python inference.py

```

### Evaluation with Pre-trained Models 

```

python evaluate.py

```

### Training on your own dataset

download [sam](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth)

modify config.py and then

```

python train_es.py

```

## Citation

```

```

## Acknowledgment

The code is built on [segment-anything-model](https://github.com/facebookresearch/segment-anything) and [lightning-sam](https://github.com/luca-medeiros/lightning-sam), many thanks for the Third Party Libs.