cppxaxa/mirnet-tflite

TensorFlow Lite models for MIRNet for low-light image enhancement.

MIRNet-TFLite

This repository shows the TensorFlow Lite model conversion and inference processes for the MIRNet model as proposed by Learning Enriched Features for Real Image Restoration and Enhancement. This model is capable of enhancing low-light images upto a great extent.

Source

Model training code and pre-trained weights are provided by Soumik through this repository.

Comparison between the TensorFlow Lite and original models

TensorFlow Lite model (dynamic-range quantized)

Original model

About the notebooks

• MIRNet_TFLite.ipynb: Shows the model conversion and inference processes. Models converted in this notebook support dynamic shaped inputs.
• MIRNet_TFLite_Fixed_Shape.ipynb: Shows the model conversion and inference processes. Models converted in this notebook only support fixed shaped inputs.
• Add_Metadata.ipynb: Adds metadata to TensorFlow Lite models. Metadata makes it easier for mobile developers to integrate the TensorFlow Lite models in their applications.

TensorFlow Lite models

• Dynamic shape (contains dynamic-range and fp16 quantized models)
• Fixed shape (contains dynamic-range, integer, and fp16 quantized models)
• Fixed shape metadata-populated models

Benchmarking

Pixel 4 was used in order to run the benchmarking tests. Also, fixed-shape TensorFlow Lite models (accepting 400x400x3 images) were only benchmarked.