Advanced micro devices, inc. (20240112297). CNN SEAMLESS TILE PROCESSING FOR LOW-POWER INFERENCE ACCELERATOR simplified abstract
Contents
- 1 CNN SEAMLESS TILE PROCESSING FOR LOW-POWER INFERENCE ACCELERATOR
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 CNN SEAMLESS TILE PROCESSING FOR LOW-POWER INFERENCE ACCELERATOR - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
CNN SEAMLESS TILE PROCESSING FOR LOW-POWER INFERENCE ACCELERATOR
Organization Name
Inventor(s)
Tung Chuen Kwong of Markham (CA)
Akila Subramaniam of Austin TX (US)
CNN SEAMLESS TILE PROCESSING FOR LOW-POWER INFERENCE ACCELERATOR - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240112297 titled 'CNN SEAMLESS TILE PROCESSING FOR LOW-POWER INFERENCE ACCELERATOR
Simplified Explanation
The patent application describes methods and devices for processing image data using layers of a convolutional neural network on a sub-frame portion basis. The processing device includes memory and a processor that determines the size of input tiles based on receptive fields and allocated memory, as well as whether the allocated memory is sufficient to store data for the input tile and padded data for the receptive field.
- The processor determines the size of input tiles based on receptive fields and allocated memory.
- The processor checks if the allocated memory is enough to store data for the input tile and padded data for the receptive field.
Potential Applications
This technology can be applied in image recognition systems, medical imaging analysis, autonomous vehicles, and video processing applications.
Problems Solved
This technology addresses the challenge of efficiently processing image data using convolutional neural networks on a sub-frame portion basis while managing memory allocation effectively.
Benefits
The benefits of this technology include improved efficiency in processing image data, optimized memory usage, and enhanced performance of convolutional neural networks.
Potential Commercial Applications
Potential commercial applications of this technology include image processing software, medical imaging devices, surveillance systems, and autonomous vehicle technology.
Possible Prior Art
One possible prior art could be the use of convolutional neural networks for image processing tasks, but the specific method described in this patent application for processing image data on a sub-frame portion basis using memory allocation may be novel.
What is the impact of this technology on memory usage in image processing tasks?
This technology aims to optimize memory usage by efficiently allocating memory for storing data related to input tiles and receptive fields, which can lead to more efficient processing of image data and improved performance of convolutional neural networks.
How does this technology compare to existing methods for processing image data using convolutional neural networks?
This technology introduces a novel approach to processing image data on a sub-frame portion basis, which may offer advantages in terms of memory management and efficiency compared to traditional methods of processing image data using convolutional neural networks.
Original Abstract Submitted
methods and devices are provided for processing image data on a sub-frame portion basis using layers of a convolutional neural network. the processing device comprises memory and a processor. the processor is configured to determine, for an input tile of an image, a receptive field via backward propagation and determine a size of the input tile based on the receptive field and an amount of local memory allocated to store data for the input tile. the processor determines whether the amount of local memory allocated to store the data of the input tile and padded data for the receptive field.
