Released in 2017, this geolocation model classifies the location in which a photo was taken among more than 15,000 predefined locations around the world. The classes correspond to cells extracted from Google's S2 Geometry library.
Number of layers: 344 |
Parameter count: 74,405,235 |
Trained size: 299 MB |
Examples
Resource retrieval
Get the pre-trained net:
Basic Usage
Obtain an estimate of the latitude and longitude of where a photo was taken:
Show a map of the area corresponding to the position:
Mark the position on a world map:
Multiple Predictions
The net returns a probability distribution over all available locations. Obtain the 50 most probable locations for a given image and plot these locations on the world map, with the size of the location marker proportional to the probability:
Fine Scale Predictions
In places with high population density, very fine-grained predictions are possible. Consider the following four landmarks in Paris:
Predict the locations of the four landmarks and mark the locations on the map:
Compare with the actual locations:
Region Density
Inspect the distribution of the available positions. Display a heat map of the location density on the map:
Net information
Inspect the number of parameters of all arrays in the net:
Obtain the total number of parameters:
Obtain the layer type counts:
Display the summary graphic:
Export to MXNet
Export the net into a format that can be opened in MXNet:
Export also creates a net.params file containing parameters:
Get the size of the parameter file:
The size is similar to the byte count of the resource object:
Requirements
Wolfram Language 11.2
(September 2017) or above
External Links
Resource History
Reference