Er1cZ / Deploying_CNN_on_FPGA_using_OpenCL
Squeezenet V1.1 on Cyclone V SoC-FPGA at 450ms/image, 20x faster than ARM A9 processor alone. A project for 2017 Innovate FPGA design contest.
☆102Updated 6 years ago
Alternatives and similar repositories for Deploying_CNN_on_FPGA_using_OpenCL:
Users that are interested in Deploying_CNN_on_FPGA_using_OpenCL are comparing it to the libraries listed below
- OpenCL HLS based CNN Accelerator on Intel DE10 Nano FPGA.☆76Updated last year
- Convolutional Neural Network Using High Level Synthesis☆84Updated 4 years ago
- FPGA-based ZynqNet CNN accelerator developed by Vivado_HLS☆107Updated 7 years ago
- A FPGA Based CNN accelerator, following Google's TPU V1.☆132Updated 5 years ago
- DPU on PYNQ☆209Updated last year
- Deep Learning Accelerator (Convolution Neural Networks)☆170Updated 7 years ago
- Vitis HLS Library for FINN☆189Updated 2 weeks ago
- Convolutional accelerator kernel, target ASIC & FPGA☆178Updated last year
- FPGA/AES/LeNet/VGG16