VLIW Code Generation for a Convolutional Network Accelerator

The article realization of NAND FLASH control glueless interface circuit based on FPGA,comparing the advantages and disadvantages of the NAND Flash and analysising the function of control interface circuit. The control interface circuit can correct carry out the SRAM timing-input block erase, page reads, page programming, state read instructions into the required operation sequence of NAND Flash, greatly simplifies the NAND FLASH read and write timing control. According to the ECC algorithm,the realization method of ECC check code generation,error search,error correction is described.The function of operate instructions of the NAND Flash control interface circuit designed in this paper is verified on Xillinx Spartan-3 board, and the frequency can reach 100MHz.

Download Full-text

An experiment in table driven code generation

ACM SIGPLAN Notices ◽

10.1145/872726.806978 ◽

1982 ◽

Vol 17 (6) ◽

pp. 32-43 ◽

Cited By ~ 3

Author(s):

Susan L. Graham ◽

Robert R. Henry ◽

Robert A. Schulman

Keyword(s):

Code Generation

Download Full-text

Knowledge and Geo-Object Based Graph Convolutional Network for Remote Sensing Semantic Segmentation

Sensors ◽

10.3390/s21113848 ◽

2021 ◽

Vol 21 (11) ◽

pp. 3848

Author(s):

Wei Cui ◽

Meng Yao ◽

Yuanjie Hao ◽

Ziwei Wang ◽

Xin He ◽

...

Keyword(s):

Remote Sensing ◽

Prior Knowledge ◽

Contextual Information ◽

Information Aggregation ◽

Semantic Segmentation ◽

Spatial Correlations ◽

Convolutional Network ◽

Object Based ◽

Graph Neural Networks ◽

Salt And Pepper

Pixel-based semantic segmentation models fail to effectively express geographic objects and their topological relationships. Therefore, in semantic segmentation of remote sensing images, these models fail to avoid salt-and-pepper effects and cannot achieve high accuracy either. To solve these problems, object-based models such as graph neural networks (GNNs) are considered. However, traditional GNNs directly use similarity or spatial correlations between nodes to aggregate nodes’ information, which rely too much on the contextual information of the sample. The contextual information of the sample is often distorted, which results in a reduction in the node classification accuracy. To solve this problem, a knowledge and geo-object-based graph convolutional network (KGGCN) is proposed. The KGGCN uses superpixel blocks as nodes of the graph network and combines prior knowledge with spatial correlations during information aggregation. By incorporating the prior knowledge obtained from all samples of the study area, the receptive field of the node is extended from its sample context to the study area. Thus, the distortion of the sample context is overcome effectively. Experiments demonstrate that our model is improved by 3.7% compared with the baseline model named Cluster GCN and 4.1% compared with U-Net.

Download Full-text

SACN: A Novel Rotating Face Detector Based on Architecture Search

Electronics ◽

10.3390/electronics10050558 ◽

2021 ◽

Vol 10 (5) ◽

pp. 558

Author(s):

Anping Song ◽

Xiaokang Xu ◽

Xinyi Zhai

Keyword(s):

Face Detection ◽

Human Face ◽

Angle Error ◽

Rotation Invariant ◽

Convolutional Network ◽

Data Set ◽

Practical Applications ◽

Model Size ◽

Average Angle ◽

Face Detector

Rotation-Invariant Face Detection (RIPD) has been widely used in practical applications; however, the problem of the adjusting of the rotation-in-plane (RIP) angle of the human face still remains. Recently, several methods based on neural networks have been proposed to solve the RIP angle problem. However, these methods have various limitations, including low detecting speed, model size, and detecting accuracy. To solve the aforementioned problems, we propose a new network, called the Searching Architecture Calibration Network (SACN), which utilizes architecture search, fully convolutional network (FCN) and bounding box center cluster (CC). SACN was tested on the challenging Multi-Oriented Face Detection Data Set and Benchmark (MOFDDB) and achieved a higher detecting accuracy and almost the same speed as existing detectors. Moreover, the average angle error is optimized from the current 12.6° to 10.5°.

Download Full-text