larq
finn-examples
| larq | finn-examples | |
|---|---|---|
| 2 | 1 | |
| 692 | 161 | |
| 0.3% | 4.3% | |
| 7.5 | 0.0 | |
| 17 days ago | 8 days ago | |
| Python | Jupyter Notebook | |
| Apache License 2.0 | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
larq
-
Running CNN on ATmega328P
You quantize the model parameters i.e., don't just send the model in which uses floating point math instead change it to fixed point. This has 2 advantages 1) a pure size reduction and 2) most low power MCU's don't have float point multipliers but do have single cycle fixed point multipliers. This is a classic DSP trick used for a long time. The real research aspects come-in as you start dropping below 8-bit; even coming down to single-bit in some cases(see Larq)
-
Simplifying AI to FPGA deployment, looking for opportunities
It is a difficult question. I work almost exclusively with open source, so I'm not much use to give you advice. Maybe you can see how Plumerai handles things -- they have some stuff proprietary, but they've also open-sourced their BNN Larq stuff: https://github.com/larq/larq
finn-examples
-
Simplifying AI to FPGA deployment, looking for opportunities
FINN can implement arbitrary and mixed precision DNNs, not just BNNs. There is an examples git repo: https://github.com/Xilinx/finn-examples
What are some alternatives?
model-optimization - A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Vitis-Tutorials - Vitis In-Depth Tutorials
data-science-ipython-notebooks - Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
nngen - NNgen: A Fully-Customizable Hardware Synthesis Compiler for Deep Neural Network
f4pga-arch-defs - FOSS architecture definitions of FPGA hardware useful for doing PnR device generation.
rfsoc_studio - The Strathclyde RFSoC Studio Installer for PYNQ.
Alveo-PYNQ - Introductory examples for using PYNQ with Alveo
PYNQ - Python Productivity for ZYNQ
Vitis_Accel_Examples - Vitis_Accel_Examples