Larq 是一个开源深度学习库，专注于使用极低精度权重和激活（如 Binarized Neural Networks）训练神经网络。它基于 tf.keras 接口，提供易于使用的量化层和量化器，以构建 BNNs 和其他类型的 Quantized Neural Networks。Larq 家族还包括预训练模型库 Larq Zoo 和适用于移动设备部署的 Larq Compute Engine。
Larq is an open-source deep learning library for training neural networks with extremely low precision weights and activations, such as Binarized Neural Networks (BNNs).
Existing deep neural networks use 32 bits, 16 bits or 8 bits to encode each weight and activation, making them large, slow and power-hungry. This prohibits many applications in resource-constrained environments. Larq is the first step towards solving this. It is designed to provide an easy to use, composable way to train BNNs (1 bit) and other types of Quantized Neural Networks (QNNs) and is based on the tf.keras interface.
Larq is part of a family of libraries for BNN development; you can also check out Larq Zo
最低0.47元/天 解锁文章
544
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
