# ResNet-101 Trained onYFCC100m Geotagged Data

Determine the geolocation of a photograph

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 |

## Performance

• This model correctly localized 82.2% of the IM2GPS test set within 2,500 kilometers.

## Examples

### Resource retrieval

Get the pre-trained net:

 In[1]:=
 Out[1]=

### Basic Usage

Obtain an estimate of the latitude and longitude of where a photo was taken:

 In[2]:=
 Out[2]=

Show a map of the area corresponding to the position:

 In[3]:=
 Out[3]=

Mark the position on a world map:

 In[4]:=
 Out[4]=

### 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:

 In[5]:=
 Out[5]=

### Fine Scale Predictions

In places with high population density, very fine-grained predictions are possible. Consider the following four landmarks in Paris:

 In[6]:=
 Out[6]=

Predict the locations of the four landmarks and mark the locations on the map:

 In[7]:=
 Out[7]=

Compare with the actual locations:

 In[8]:=
 Out[8]=

### Region Density

Inspect the distribution of the available positions. Display a heat map of the location density on the map:

 In[9]:=
 Out[9]=

### Net information

Inspect the number of parameters of all arrays in the net:

 In[10]:=
 Out[10]=

Obtain the total number of parameters:

 In[11]:=
 Out[11]=

Obtain the layer type counts:

 In[12]:=
 Out[12]=

Display the summary graphic:

 In[13]:=
 Out[13]=

### Export to MXNet

Export the net into a format that can be opened in MXNet:

 In[14]:=
 Out[14]=

Export also creates a net.params file containing parameters:

 In[15]:=
 Out[15]=

Get the size of the parameter file:

 In[16]:=
 Out[16]=

The size is similar to the byte count of the resource object:

 In[17]:=
 Out[17]=

## Requirements

Wolfram Language 11.2 (September 2017) or above