Feature Map Explorer enables visualization of 4-dimensional image-based feature map data in a fluid, interactive fashion, using a range of views spanning from low-level channel visualizations to detailed numerical information about each channel slice. Think of this as a way to peer into the DNN processing “black box” to find intimate information about what the model is learning, where the model is failing to use resources efficiently, and what is changing as a model is learning during training to better process data handed to it.


Download

NVIDIA® Feature Map Explorer is freely offered through the NVIDIA Registered Developer Program.

Dive Into Each Channel


Feature Map Explorer enables deep learning developers to visualize and examine each channel from a feature map to see what has been learned or what is missing in a feature.


Compare Feature Maps


Feature Map Explorer allows deep learning developers to compare two tensors in various ways. The two tensors could represent feature maps from two different epochs that show the learning progression from one epoch to another, it could also be feature maps from two different batch items.


System Requirements


Supported operating systems:

  • Ubuntu 18.04
  • Windows 10

Required hardware:

  • GPU: Pascal or newer
  • CPU: x86-64