Metadata-Version: 2.1
Name: imBroker
Version: 0.0.1
Summary: A Tensorflow Lite Image Classification Model Integration Library
Author: dakshoza (Daksh Oza)
Author-email: <ozadaksh31@gmail.com>
Project-URL: Bug Tracker, https://github.com/yourusername/disPred/issues
Project-URL: Source Code, https://github.com/yourusername/disPred
Keywords: broker,tensorflow lite,image classification,flexible,real time
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: opencv-python (==4.8.0.74)
Requires-Dist: numpy (==1.23.5)
Requires-Dist: tensorflow (==2.14.0)

# TFLite Image Classification Broker

This library provides a simple interface for image classification using TensorFlow Lite models. It's designed to work with pre-trained models and can process both single images and directories of images.

## Installation

```bash
pip install imBroker
```

## Features

- Single image classification
- Batch classification for directories
- Support for custom TFLite models
- Handles any type of image shapes

## Usage

### Initializing the Broker

```python
from imBroker import tflBroker

# Define your TFlite model's path
model_path = "path/to/your/model.tflite"

# Define your output labels
output_labels = {
    0: 'Label 1',
    1: 'Label 2',
    ... 
}

# Initialize the broker
broker = tflBroker(model_path, output_labels)
```

### Classifying a Single Image

```python
result = broker.predict_single_image("path/to/image.jpg")
print(result)
```

### Classifying a Directory of Images

```python
results = broker.predict_image_directory("path/to/image/directory")
print(results)
```
