The existing RF signal based indoor localization techniques such as BLE or Wi-Fi fingerprinting are hard to apply to large scale indoor environment such as airport and department stores since the localization error grows as the physical dimension of the indoor space increases. This can be attributed to unstable received signal strengths (RSS) of the underlying RF signal, which is enlarged with the increased physical scale and the complexity of the indoor space. In this paper, instead of RF signal we use the geomagnetic sensor signal for indoor localization, whose signal strength is more stable than RF RSS. Our approach using the geomagnetic field is as follows. Although similar geomagnetic field values exist in indoor space, an object movement would experience a unique sequence of the geomagnetic field signals as the movement continues. We can locate the position of the object by tracking the geomagnetic field signal sequence sensed with the object movement by using a deep neural network model called recurrent neural network (RNN), which is good at recognizing time varying sequence of sensor data. We use two different versions of RNN model: basic RNN and Long Short-Term Memory (LSTM). We have trained RNNs to learn the magnetic field maps of both medium scale (about 94m × 26m) and large scale (about 608m × 50m area) indoor testbeds and analyze both training and test set results by tuning several training hyperparameters. For comparison, we have also implemented both Bluetooth Low Energy (BLE) and Wi-Fi based fingerprinting localization techniques and measured their localization accuracies for the testbeds. By using Google TensorFlow 1.6 and Nvdia CUDA Toolkit v9.0 with cuDNN v7.1 library as a deep learning framework, we could achieve the average localization accuracy of 0.51 and 1.04 meters for the medium and the large-scale testbeds respectively with LSTM model, substantially improving the localization performance compared to the existing RF based fingerprinting techniques.