Neural network architecture search method and device, electronic equipment and readable storage medium

The invention relates to the technical field of data processing, and provides a neural network architecture search method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining scene definition information; analyzing the scene definition information to obtain scene type information; selecting a corresponding target sub-network from a preset neural network module pool according to the scene type information; and deploying the target sub-network in the target scene. According to the technical scheme, quick search and selection of the neural network can be realized, so that subsequent quick scene response is facilitated. 本申请涉及数据处理技术领域，提供了一种神经网络架构搜索方法、装置、电子设备及计算机可读存储介质，方法包括：获取场景定义信息；对场景定义信息进行分析得到场景类型信息；根据场景类型信息从预设的神经网络模块池中选出对应的目标子网络；将目标子网络部署于目标场景中。通过上述技术方案能够实现神经网络的快速搜索选取，从而有利于后续进行快速的场景响应。