VeriSilicon / acuitylite
Acuitylite is an end-to-end neural network deployment tool
☆16Updated last month
Alternatives and similar repositories for acuitylite:
Users that are interested in acuitylite are comparing it to the libraries listed below
- Open deep learning compiler stack for cpu, gpu and specialized accelerators☆10Updated 3 years ago
- Tensorflow Lite external delegate based on TIM-VX☆46Updated last month
- ☆34Updated 8 months ago
- Zhouyi model zoo☆94Updated 4 months ago
- Acuity Model Zoo☆136Updated 2 years ago
- DDK for Rockchip NPU☆61Updated 4 years ago
- VeriSilicon Tensor Interface Module☆229Updated last month
- Simple test code to benchmark the VFP floating point or NEON units of ARM processors☆26Updated 11 years ago
- Fork of https://source.codeaurora.org/quic/hexagon_nn/nnlib☆57Updated last year
- HiFi 5 NN Library☆34Updated this week
- A light-weight neural network optimizer for different software/hardware backends.☆19Updated 4 years ago
- symmetric int8 gemm☆66Updated 4 years ago
- ONNX converter and optimizer scirpts for Kneron hardware.☆38Updated last year
- Tengine Convert Tool supports converting multi framworks' models into tmfile that suitable for Tengine-Lite AI framework.☆92Updated 3 years ago
- ☆24Updated 2 years ago
- Optimizing Mobile Deep Learning on ARM GPU with TVM☆180Updated 6 years ago
- quantize aware training package for NCNN on pytorch☆70Updated 3 years ago
- PyTorch -> ONNX -> TVM for autotuning☆23Updated 4 years ago
- Cortex M KWS example with Tengine Lite.☆73Updated 4 years ago
- Implement vgg16 model by ARM Compute Library☆31Updated 5 years ago
- ☆31Updated last month
- Image processing library for learning purpose☆54Updated 2 months ago
- 将MNN拆解的简易前向推理框架(for study!)☆20Updated 3 years ago
- An optimized neural network operator library for chips base on Xuantie CPU.☆87Updated 7 months ago
- ☆22Updated 5 years ago
- Tencent NCNN with added CUDA support☆68Updated 4 years ago
- Snapdragon Neural Processing Engine (SNPE) SDKThe Snapdragon Neural Processing Engine (SNPE) is a Qualcomm Snapdragon software accelerate…☆33Updated 2 years ago
- autoTVM神经网络推理代码优化搜索演示,基于tvm编译开源模型centerface,并使用autoTVM搜索最优推理代码, 最终部署编译为c++代码,演示平台是cuda,可以是其他平台,例如树莓派,安卓手机,苹果手机.Thi is a demonstration of …☆27Updated 3 years ago
- RidgeRun Inference Framework☆27Updated 2 years ago
- One stage object detection model based on YOLOv3, written in PyTorch.☆9Updated 2 years ago