Purpose To develop a deep learning method for rapidly reconstructing T1 and T2 maps from undersampled electrocardiogram (ECG) triggered cardiac magnetic resonance fingerprinting (cMRF) images. Methods A neural network was developed that outputs T1 and T2 values when given a measured cMRF signal time course and cardiac RR interval times recorded by an ECG. Over 8 million cMRF signals, corresponding to 4000 random cardiac rhythms, were simulated for training. The training signals were corrupted by simulated k‐space undersampling artifacts and random phase shifts to promote robust learning. The deep learning reconstruction was evaluated in Monte Carlo simulations for a variety of cardiac rhythms and compared with dictionary‐based pattern matching in 58 healthy subjects at 1.5T. Results In simulations, the normalized root‐mean‐square error (nRMSE) for T1 was below 1% in myocardium, blood, and liver for all tested heart rates. For T2, the nRMSE was below 4% for myocardium and liver and below 6% for blood for all heart rates. The difference in the mean myocardial T1 or T2 observed in vivo between dictionary matching and deep learning was 3.6 ms for T1 and −0.2 ms for T2. Whereas dictionary generation and pattern matching required more than 4 min per slice, the deep learning reconstruction only required 336 ms. Conclusion A neural network is introduced for reconstructing cMRF T1 and T2 maps directly from undersampled spiral images in under 400 ms and is robust to arbitrary cardiac rhythms, which paves the way for rapid online display of cMRF maps.