- Install Miniconda. Either 2.7 or 3.6 because this project creates its own environment so anything is fine.
- Create a conda environment, using the appropriate command. On Windows, open the installed "Conda prompt" to run this command. On MacOS and Linux, you can just use a terminal window to run the command. Modify the command based on your OS ('linux', 'mac', or 'win'):
conda env create -f environment_<OS>.yml
- This should create an environment named
local_features
. Activate it using the following Windows command:activate local_features
or the following MacOS / Linux command:source activate local_features
. - Run the notebook using:
jupyter notebook ./code/proj2.ipynb
adityanair111 / feature-matching Goto Github PK
View Code? Open in Web Editor NEWThe intention is to capture the notion of interest points and use these to create feature vectors (SIFT) and employ them in matching objects.