UnPool layer

Contains all the work done on the Spatial Dropout layer. This layer does an approximate inverse of the Max Pool operation.

Link to PR

#2493

Link to Blogs

• Blog post 1

• Blog post 2

  

  MaxPooling Operation and Corresponding UnPool operation.

What’s in this folder

1. UnPool.ipynb - Understanding the working of the PyTorch layer.
2. test.cpp - Armadillo implementation of the layer’s functionality.
3. maxpool.txt - The output obtained from running the cpp file.

How to run

To run the .cpp file, you need to have armadillo installed in your system.

g++ test.cpp -o test -larmadillo && ./test > maxpool.txt

To run UnPool.ipynb, you would need the pytorch python library.

Google Colab link for notebook

UnPool layer