【DL】小而美的開源庫
Tencent/FeatherCNN : 嵌入式平臺上的 CNN 庫
FeatherCNN, developed by Tencent TEG AI Platform, is a high-performance lightweight CNN inference library. FeatherCNN is currently targeting at ARM CPUs, and is capable to extend to other devices in the future.
Comparing with other libraries, FeatherCNN is
Highly Performant FeatherCNN delivers state-of-the-art inference computing performance on a wide range of devices, including mobile phones (iOS/Android), embedded devices (Linux) as well as ARM-based servers (Linux).
Easily Deployable FeatherCNN packs everything in a single code base to get rid of third-party dependencies. Hence, it facilitates deployment on mobile platforms. FeatherCNN’s own model format is fully compatible with Caffe models. We are working to provide compatibility with other pre-trained models.
Featherweight The compiled FeatherCNN library is in small size of several hundred KBs.