amrmorsey / Latte
Latte is a convolutional neural network (CNN) inference engine written in C++ and uses AVX to vectorize operations. The engine runs on Windows 10, Linux and macOS Sierra.
☆12Updated 6 years ago
Related projects ⓘ
Alternatives and complementary repositories for Latte
- ONNX Parser is a tool that automatically generates openvx inference code (CNN) from onnx binary model files.☆17Updated 5 years ago
- Training neural networks with 8-bit computations☆29Updated 8 years ago
- Benchmarking Analysis of Vision Kernels on Embedded CPU, GPU and FPGA☆14Updated 5 years ago
- Binary Neural Network on IceStick FPGA.☆50Updated 6 years ago
- DynamicVINO is an open-source C++ library for establishing easy-to-use, extensible and scalable deep learning inference system for Intel…☆14Updated 6 years ago
- Pretrained VGG16 neural net in C language☆49Updated 2 years ago
- An implementation of a BinaryConnect network for cifar10☆11Updated 5 years ago
- Lightweight C implementation of CNNs for Embedded Systems☆54Updated last year
- training ternary neural networks☆12Updated 7 years ago
- ☆39Updated 7 years ago
- RidgeRun Inference Framework☆27Updated 2 years ago
- Provides users a possibility to train their own GOTURN tracker CNN model on custom data☆11Updated 7 years ago
- End-to-end deep learning based autonomous RC car using Raspberry Pi 3.☆36Updated 6 years ago
- YOLO reimplement in caffe, written with python layer.☆13Updated 7 years ago
- ☆13Updated 4 years ago
- Heterogeneous Run Time version of TensorFlow. Added heterogeneous capabilities to the TensorFlow, uses heterogeneous computing infrastruc…☆36Updated 6 years ago
- CS-E4850 Computer Vision Course - Python assignments☆9Updated 5 years ago
- PyTorch -> ONNX -> TVM for autotuning☆23Updated 4 years ago
- Learn NVDLA by SOMNIA☆26Updated 4 years ago
- Library for fast image convolution in neural networks on Intel Architecture☆29Updated 7 years ago
- Deep Learning Compression and Acceleration SDK -- deep model compression for Edge and IoT embedded systems, and deep model acceleration f…☆20Updated 6 years ago
- ☆13Updated 7 years ago
- Accelerating CNN's convolution operation on GPUs by using memory-efficient data access patterns.☆14Updated 6 years ago
- MultiviewFaceDetection☆8Updated 9 months ago
- FastHOG library that has been fixed to work with CUDA 5.x on Ubuntu 12.04☆19Updated 10 years ago
- Input-aware cuBLAS/clBLAS implementation for better performance☆17Updated 2 years ago
- Deep neural network framework (C/C++/CUDA).☆31Updated 9 years ago
- Bridging caffe2 with yolo, esp on mobile devices☆16Updated 7 years ago