Online activation compression with k-means
AssigneeIntel Corporation
InventorsGal Leibovich, Gal Novik, Yonatan Glesner
Life of this patent
Estimating the term…
Abstract
Methods and apparatus relating to online activation compression with K-means are described. In one embodiment, logic (e.g., in a processor) compresses one or more activation functions for a convolutional network based on non-uniform quantization. The non-uniform quantization for each layer of the convolutional network is performed offline, and an activation function for a specific layer of the convolutional network is quantized during runtime. Other embodiments are also disclosed and claimed.
Claims25
An apparatus comprising:
- logic, at least a portion of which is in hardware, to compress one or more activation functions for a convolutional network based on non-uniform quantization,
- wherein the non-uniform quantization for each layer of the convolutional network is to be performed offline, wherein an activation function for a specific layer of the convolutional network is to be quantized during runtime.
A method comprising:
- compressing one or more activation functions for a convolutional network based on non-uniform quantization,
- wherein the non-uniform quantization for each layer of the convolutional network is performed offline, wherein an activation function for a specific layer of the convolutional network is quantized during runtime.
One or more computer-readable medium comprising one or more instructions that when executed on at least one processor configure the at least one processor to perform one or more operations to:
- compress one or more activation functions for a convolutional network based on non-uniform quantization,
- wherein the non-uniform quantization for each layer of the convolutional network is performed offline, wherein an activation function for a specific layer of the convolutional network is quantized during runtime.
Dependencies are inferred from the claim text.