doonny/PipeCNN
An OpenCL-based FPGA Accelerator for Convolutional Neural Networks
This project helps researchers and engineers accelerate the computation of large-scale convolutional neural networks (CNNs) on Field-Programmable Gate Arrays (FPGAs). It takes pre-trained CNN models (like VGG-16 or ResNet-50) and image datasets, then outputs classification results and performance metrics, allowing for efficient deep learning inference. It's designed for hardware engineers, embedded systems developers, and deep learning researchers who work with FPGA acceleration.
1,367 stars. No commits in the last 6 months.
Use this if you need to accelerate convolutional neural network inference on FPGA hardware and are familiar with OpenCL or High-Level Synthesis (HLS) design flows.
Not ideal if you are looking for state-of-the-art performance for deep learning acceleration, as newer techniques have surpassed its original benchmarks.
Stars
1,367
Forks
375
Language
C
License
Apache-2.0
Category
Last pushed
Feb 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/doonny/PipeCNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
fastmachinelearning/hls4ml
Machine learning on FPGAs using HLS
alibaba/TinyNeuralNetwork
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
KULeuven-MICAS/zigzag
HW Architecture-Mapping Design Space Exploration Framework for Deep Learning Accelerators
fastmachinelearning/hls4ml-tutorial
Tutorial notebooks for hls4ml
es-ude/elastic-ai.creator
Design, train and generate neural networks optimized specifically for FPGAs.