Stars
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
A pytorch quantization backend for optimum
This is a fully parameterized verilog implementation of computation kernels for accleration of the Inference of Convolutional Neural Networks on FPGAs
This project accelerates CNN computation with the help of FPGA, for more than 50x speed-up compared with CPU.
An OpenCL-based FPGA Accelerator for Convolutional Neural Networks
A FPGA Based CNN accelerator, following Google's TPU V1.
A Verilog design of LeNet-5, a Convolutional Neural Network architecture
Find contours and their hierarchy relationship in a binary image.
Edge tracing with ambiguity modeling for binary edge images.
Set of video-based and multimodal traffic surveillance datasets. Special interest on intersection surveillance. No onboard data
The Highway Traffic Anomaly data set and related code
Performance and resource models for fpgaConvNet: a Streaming-Architecture-based CNN Accelerator.
lus-oa / YOLOv5-FPGA
Forked from ptoupas/amd-open-hardware-23This repository provides an FPGA-based solution for executing object detection, focusing specifically on the popular YOLOv5 model architecture.
OpenPose uses Pytorch for static quantization, saving, and loading of models
网络训练、图像预处理以及部分hend功能是基于pc端实现的，只有主干网络部署在fpga上，片上资源无法支持整个网络所需资源，建议添加外部存储及DDR
This project is to design yolo AI accelerator in verilog HDL.
Generator of verilog description for FPGA MobileNet implementation
FPGA/AES/LeNet/VGG16
The simplest implementation of LeNet5 with mnist in PyTorch. Accuracy: ~99%
A Fix-pointed Rudimentary CNN Convolution Accelerator