GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → blue-oil → Blueoil

blue-oil / Blueoil

Licence: apache-2.0
Bring Deep Learning to small devices

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningmachine-learningfpgaquantization

Projects that are alternatives of or similar to Blueoil

Brevitas
Brevitas: quantization-aware training in PyTorch
Stars: ✭ 343 (+40.57%)
Mutual labels:  fpga, quantization
Finn
Dataflow compiler for QNN inference on FPGAs
Stars: ✭ 284 (+16.39%)
Mutual labels:  fpga, quantization
Qkeras
QKeras: a quantization deep learning library for Tensorflow Keras
Stars: ✭ 254 (+4.1%)
Mutual labels:  fpga, quantization
Tf2
An Open Source Deep Learning Inference Engine Based on FPGA
Stars: ✭ 113 (-53.69%)
Mutual labels:  fpga, quantization
Nncf
PyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference
Stars: ✭ 218 (-10.66%)
Mutual labels:  quantization
Openwifi Hw
FPGA/hardware design of openwifi
Stars: ✭ 181 (-25.82%)
Mutual labels:  fpga
Pytorch Playground
Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
Stars: ✭ 2,201 (+802.05%)
Mutual labels:  quantization
Fpga Chip8
CHIP-8 console on FPGA
Stars: ✭ 169 (-30.74%)
Mutual labels:  fpga
Xrt
Xilinx Run Time for FPGA
Stars: ✭ 236 (-3.28%)
Mutual labels:  fpga
Axi
AXI SystemVerilog synthesizable IP modules and verification infrastructure for high-performance on-chip communication
Stars: ✭ 227 (-6.97%)
Mutual labels:  fpga
Red Pitaya Notes
Notes on the Red Pitaya Open Source Instrument
Stars: ✭ 205 (-15.98%)
Mutual labels:  fpga
Spoonn
FPGA-based neural network inference project with an end-to-end approach (from training to implementation to deployment)
Stars: ✭ 186 (-23.77%)
Mutual labels:  fpga
80x86
80186 compatible SystemVerilog CPU core and FPGA reference design
Stars: ✭ 220 (-9.84%)
Mutual labels:  fpga
Wb2axip
Bus bridges and other odds and ends
Stars: ✭ 177 (-27.46%)
Mutual labels:  fpga
Icicle
32-bit RISC-V system on chip for iCE40 and ECP5 FPGAs
Stars: ✭ 234 (-4.1%)
Mutual labels:  fpga
Kd lib
A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Stars: ✭ 173 (-29.1%)
Mutual labels:  quantization
Echomods
Open source ultrasound processing modules and building blocks
Stars: ✭ 200 (-18.03%)
Mutual labels:  fpga
Hastlayer Sdk
Turning .NET assemblies into FPGA hardware for faster execution and lower power usage. See the Readme and https://hastlayer.com.
Stars: ✭ 226 (-7.38%)
Mutual labels:  fpga
Lq Nets
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Stars: ✭ 195 (-20.08%)
Mutual labels:  quantization
Verilog Generator Of Neural Net Digit Detector For Fpga
Verilog Generator of Neural Net Digit Detector for FPGA
Stars: ✭ 187 (-23.36%)
Mutual labels:  fpga
View All Similar Projects ➔

Blueoil provides two features.

  • Training a neural network model
  • Converting a trained model to an executable binary (or library), which utilize FPGAs for acceleration.
Type Status
blueoil Build status
lmnet Build status
dlk Build status
docs CircleCI

See also CI settings.

Documentation

You can see online documentation with enter.

Check out the Installation and Usage Guide page for getting started.

Note: Currently, Installation page is just in to be written, Please see Setup section to build docker on your development environment.

Prerequisites

  • GNU/Linux x86_64 with kernel version > 3.10
  • NVIDIA GPU with Architecture >= 3.0 (Kepler)
  • NVIDIA drivers >= 410.48
  • Docker >=1.12 (or >=17.03.0)
  • nvidia-docker >= 2.0

The blueoil is run on docker container with original docker image based on NVIDIA's CUDA images (cuda:10.0-cudnn7-devel).

The machine running the CUDA container only requires the NVIDIA driver, the CUDA toolkit doesn't have to be installed.

Please see the detail in the nvidia-docker's prerequisites.

Set up

There are some submodules in this repositry, so you should run git submodule update --init --recursive after cloning or git clone --recursive [this repository].

make build

Note: The private repository submodules are set to connect by ssh, if you want to use HTTPS, you should edit URLs in .gitmodules and run git submodule sync before git submodule update --init --recursive command. (see how to edit)

How to make document

cd docs
make html

You can see generated documents in HTML format under docs/_build/html/ directory on your enviroment.

Also, you can see the deploy-preview online documentation from a Pull Request page that are integrated by netilify.

How to test

We can test each opereations of drore_run.sh by using shell script.

Prerequisites

  • expect >= version 5.45
$ make test

You can test specific task.

$ CUDA_VISIBLE_DEVICES={YOUR_GPU_ID} make test-classification
$ CUDA_VISIBLE_DEVICES={YOUR_GPU_ID} make test-object-detection
$ CUDA_VISIBLE_DEVICES={YOUR_GPU_ID} make test-semantic-segmentation

You can also test the modules used in Blueoil.

$ make test-lmnet
$ make test-dlk
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].