Integrate the TensorFlow Lite model into the app

[sayannath]

Link of the Colab Notebook here.

Metatdata of the TF-Lite model

TFLITE_MODEL_FILE = 'zero-dce.tflite'

interpreter = tf.lite.Interpreter(model_path = TFLITE_MODEL_FILE)
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

print("Input Shape:", input_details[0]['shape'])
print("Input Type:", input_details[0]['dtype'])
print("Output Shape:", output_details[0]['shape'])
print("Output Type:", output_details[0]['dtype'])

Output

Input Shape: [  1 400 600   3]
Input Type: <class 'numpy.float32'>
Output Shape: [  1 400 600   3]
Output Type: <class 'numpy.float32'>

The TensorFlow Lite model expects an image of dimension 400x600 where 600 is the image height and 400 is the image width. An image array will be given as an output, which is also of the same dimension.

Branch to be worked on feature/tflite-integrate