This project implements a deep learning neural network model to generate the depth image of a given image. Model is a U-net model with MobileNetV2 as the encoder, and model has utilized skip connection from encoder to decoder. Model generates a depth image of resolution 480x640 for input image of same size.

This project was implemented taking reference from the following paper:

High Quality Monocular Depth Estimation via Transfer Learning (arXiv 2018) [Ibraheem Alhashim] and Peter Wonka

• Download the dataset and give the location of dataset.
• Change the following according to the needs: batch_size, epochs, lr (learning rate). Load the pretrained model if needed.

• Give the location for the dictionary of images to be converted and load the pretrained model

• Give the location for the dictionary of images to be converted and load the pretrained model.

• NYU Depth V2 (50K) (4.1 GB): File is extraced while running the "train_mobilenetv2.ipynb".

• Mobilenet (55 MB). Pretrained model is trained on 2 NVIDIA GeForce GTX 1080 for 6 hours(6 epoches).

Written by Alinstein Jose, University of Victoria.