convolution arithmetic

We have hosted the application convolution arithmetic in order to run this application in our online workstations with Wine or directly.

Quick description about convolution arithmetic:

A technical report on convolution arithmetic in the context of deep learning. The code and the images of this tutorial are free to use as regulated by the licence and subject to proper attribution. The animations will be output to the gif directory. Individual animation steps will be output in PDF format to the pdf directory and in PNG format to the png directory. We introduce a guide to help deep learning practitioners understand and manipulate convolutional neural network architectures. The guide clarifies the relationship between various properties (input shape, kernel shape, zero padding, strides and output shape) of convolutional, pooling and transposed convolutional layers, as well as the relationship between convolutional and transposed convolutional layers. Relationships are derived for various cases, and are illustrated in order to make them intuitive.

Features:

• Convolution animations
• Transposed convolution animations
• Dilated convolution animations
• You can generate the Makefile
• You can generate the animations
• You can compile the document

Programming Language: Python.
Categories: