In this paper, we study fingerprinting-based indoor localization in commodity 5-GHz WiFi networks. We first theoretically and experimentally validate three hypotheses on the channel state information (CSI) data of 5-GHz OFDM channels. We then propose a system termed BiLoc, which uses bi-modality deep learning for localization in the indoor environment using off-the-shelf WiFi devices. We develop a deep learning-based algorithm to exploit bi-modal data, i.e., estimated angle of arrivings and average amplitudes (which are calibrated CSI data using several proposed techniques), for both the off-line and online stages of indoor fingerprinting. The proposed BiLoc system is implemented using commodity WiFi devices. Its superior performance is validated with extensive experiments under three typical indoor environments and through comparison with three benchmark schemes.