---
library_name: tf-keras
pipeline_tag: object-detection
tags:
- ObjectDetection
- RetinaNet
- ResNet50
- ObjectClassification
- Feature Pyramid Network
---

## Model description

Implementing RetinaNet: Focal Loss for Dense Object Detection.

This repo contains the model for the notebook [**Object Detection with RetinaNet**](https://keras.io/examples/vision/retinanet/)

Here the model is tasked with localizing the objects present in an image, and at the same time, classifying them into different categories. In this, RetinaNet has been implemented, a popular `single-stage detector`, which is accurate and runs fast. RetinaNet uses a `feature pyramid network` to efficiently detect objects at multiple scales and introduces a new loss, the `Focal loss function`, to alleviate the problem of the extreme foreground-background class imbalance.

Full credits go to [**Srihari Humbarwadi**](https://twitter.com/srihari_rh)

## References
* [RetinaNet Paper](https://arxiv.org/abs/1708.02002)
* [Feature Pyramid Network Paper](https://arxiv.org/abs/1612.03144)


## Training and evaluation data

The dataset used here is a [COCO2017 dataset](https://github.com/srihari-humbarwadi/datasets/releases/download/v0.1.0/data.zip) 

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:

| name | learning_rate | decay | momentum | nesterov | training_precision |
|----|-------------|-----|--------|--------|------------------|
|SGD|{'class_name': 'PiecewiseConstantDecay', 'config': {'boundaries': [125, 250, 500, 240000, 360000], 'values': [2.5e-06, 0.000625, 0.00125, 0.0025, 0.00025, 2.5e-05], 'name': None}}|0.0|0.8999999761581421|False|float32|

 ## Model Plot

<details>
<summary>View Model Plot</summary>

![Model Image](./model.png)

</details>

<center>
Model Reproduced By <u><a href="https://github.com/robotjellyzone"><b>Kavya Bisht</b></a></u>
</center>