Shypd.aiThe largest open index of AI toolsnncase is an open deep learning compiler stack that optimizes and compiles neural networks for Kendryte AI accelerators. It supports multiple inputs, outputs, and multi-branch structures for efficient deployment.
Trending
About
nncase is an open deep learning compiler stack specifically designed for Kendryte AI accelerators. It enables the optimization and compilation of neural networks, supporting various models like TFLite, Caffe, and ONNX. Key features include support for multiple inputs and outputs, multi-branch structures, static memory allocation, operator fusion, and both float and quantized uint8 inference. The compiler also facilitates post-quantization from float models using calibration datasets and offers flat model loading with zero copy. It's an essential tool for developers working on embedded AI systems with Kendryte hardware, providing robust performance benchmarks for image classification, object detection, image segmentation, and pose estimation.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
