https://github.com/sayannath/blood-cell-detection-tfod-2.0

Using TensorFlow Object Detection API to detect blood cells
https://github.com/sayannath/blood-cell-detection-tfod-2.0

blood-cells detection efficient-det keras medical-diagnosis medical-image-processing object-detection tensorflow tfod tfod-api

Last synced: 14 days ago
JSON representation

Using TensorFlow Object Detection API to detect blood cells

• Host: GitHub
• URL: https://github.com/sayannath/blood-cell-detection-tfod-2.0
• Owner: sayannath
• License: mit
• Created: 2021-05-07T16:06:07.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2021-08-27T14:10:10.000Z (about 3 years ago)
• Last Synced: 2023-03-11T09:02:28.988Z (over 1 year ago)
• Topics: blood-cells, detection, efficient-det, keras, medical-diagnosis, medical-image-processing, object-detection, tensorflow, tfod, tfod-api
• Language: Jupyter Notebook
• Homepage: https://drive.google.com/drive/folders/1ZVVpgf6smfpgZsIy2PCr9mzuyxCpoL63?usp=sharing
• Size: 21.8 MB
• Stars: 4
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Blood-Cell-Detection-TFOD-2.0

This project demonstrates the use of TensorFlow Object Detection API to automatically detect Red Blood Cells (RBCs), White Blood Cells (WBCs), and Platelets in each image taken via microscopic image readings.

The dataset used in this project was collected from [here](https://github.com/Shenggan/BCCD_Dataset).

The project directory structure looks like:

```

.

├── BCCD-Dataset

│   ├── test

│   └── train

├── LICENSE

├── README.md

├── annotations

│   └── label_map.pbtxt

├── assets

│   └── example.jpeg

├── export_tflite_graph_tf2.py

├── exporter_main_v2.py

├── generate_tfrecord.py

├── model_main_tf2.py

├── models

│   └── pipeline.config

├── output_images

│   ├── four.png

│   ├── one.png

│   ├── three.png

│   └── two.png

└── results_graph

    ├── classification_loss.png

    └── total_loss.png

```

I followed the official [TensorFlow Object Detection API documentation](https://github.com/tensorflow/models/tree/master/research/object_detection) to kickstart the training process on Google Colab Pro using Cloud GPU to export the inference graph.

I used a EfficientDet D0 based architecture,since it yields a pretty good `[email protected]` of around **90.14%**. 
 

The `results_graph` folder contains the graph _classification_loss_ during training.



Source: https://arxiv.org/abs/1911.09070

## Sample Image



## Inference

Here are some results after running the trained model on some test images:



    

     


    

    



## Results

 


**[email protected]**

 


**Classification Loss**

## Further undertakings

* Optimise the model using the [OpenVINO toolkit](https://software.intel.com/en-us/openvino-toolkit) 

* Convert the _saved_model_ to .tflite

* To be paired with microscopes used by pathologists

## Acknowledgements

I am thankful to [Sayak Paul](https://sayak.dev) for guiding me in this project.

## Developed & Maintained by

👨 [Sayan Nath](https://sayannath.biz)