Skip to content

Monocular depth estimation utilizes Unet architecture, a neural network model. Unet encodes image features and decodes them to predict depth from single images. It's crucial for applications like autonomous driving and augmented reality

Notifications You must be signed in to change notification settings

Gangadhar24377/MonocularDepthEstimation

 
 

Repository files navigation

Depth Estimation

Instructions

To successfully run the detection.ipynb notebook, follow these steps:

1. Dataset Folder

Ensure the ryu_data folder (dataset folder) is located in the same directory as the detection.ipynb file. This folder should contain all the necessary data for the depth estimation process.

2. Update File Paths

Open the detection.ipynb file in your Jupyter Notebook or Jupyter Lab. Inside the notebook, locate the sections where file paths are specified.

Replace the existing paths with their corresponding paths on your local machine. Update the paths for the following files and directories:

  • Replace path/to/ryu_data with the actual path to the ryu_data folder.
  • Update any other file paths or directory paths as required based on the structure of your local dataset folder.

3. Save and Run

After making the necessary changes to the file paths, save the detection.ipynb file.

About

Monocular depth estimation utilizes Unet architecture, a neural network model. Unet encodes image features and decodes them to predict depth from single images. It's crucial for applications like autonomous driving and augmented reality

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%