A guide to convolution arithmetic for deep learning.
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.
Publisher URL: http://arxiv.org/abs/1603.07285
Choose from over 15,000 academics journals covering ten research areas then let Researcher deliver you papers tailored to your interests each day.