Let's talk about the project on LinkedIn !

Photo sharing and photo storage services like to have location data for each photo that is uploaded. With the location data, these services can build advanced features, such as automatic suggestion of relevant tags or automatic photo organization, which help provide a compelling user experience. Although a photo's location can often be obtained by looking at the photo's metadata, many photos uploaded to these services will not have location metadata available. This can happen when, for example, the camera capturing the picture does not have GPS or if a photo's metadata is scrubbed due to privacy concerns.

The images below display some sample outputs of my finished project (on the left is top three probabilities):

The landmark images are a subset of the Google Landmarks Dataset v2. It can be downloaded using this link You can find license information for the full dataset on Kaggel

Notice: please be careful with the versions; if you use newer versions of PyTorch and torchvision, there will probably be some errors. So it's recommended to install packages through the steps below:

1. Clone the repo

   git clone https://github.com/salehsargolzaee/Landmark-Recognition   

2. Change directory to repo folder

   cd path/to/repo/folder

3. Download the landmark dataset. Unzip the folder and place it in this project's home directory, at the location data/landmark_images.

4. Create an environment with required packages

   conda env create -f environment.yaml
   conda activate landmark-tagging

• or you can use pip:

  pip install -r requirements.txt

5. Run jupyter notebook

   jupyter notebook

6. Open landmark.ipynb

Saleh Sargolzaee - LinkedIn - salehsargolzaee@gmail.com

Project Link: https://github.com/salehsargolzaee/Landmark-Recognition

(back to top)

Give a ⭐️ if you liked the project!