Lack of full use of phase information is a common problem in synthetic aperture radar (SAR) automatic target recognition (ATR). In this paper, we propose a complex manifold multi-scale feature fusion network (CMMFF-Net) for SAR image target recognition. Unlike traditional complex-valued networks, we extend SAR complex images to complex manifold space and construct a complex-valued manifold feature extraction module, which can extract manifold features from SAR amplitude and phase images. Moreover, the multiscale feature extraction and fusion module helps to further extract richer and discriminative target features by fusing multiscale information. Experimental results on SAR complex image dataset demonstrate the effectiveness of proposed method.