Spectrum sensing is a key technol-ogy for cognitive radios.We present spectrum sensing as a classification problem and pro-pose a sensing method based on deep le-ing classification.We normalize the received signal power to overcome the effects of noise power uncertainty.We train the model with as many types of signals as possible as well as noise data to enable the trained network mod-el to adapt to untrained new signals.We also use transfer leing strategies to improve the performance for real-world signals.Extensive experiments are conducted to evaluate the per-formance of this method.The simulation re-sults show that the proposed method performs better than two traditional spectrum sensing methods,i.e.,maximum-minimum eigenvalue ratio-based method and frequency domain entropy-based method.In addition,the ex-perimental results of the new untrained signal types show that our method can adapt to the detection of these new signals.Furthermore,the real-world signal detection experiment results show that the detection performance can be further improved by transfer leing.Finally,experiments under colored noise show that our proposed method has superior detec-tion performance under colored noise,while the traditional methods have a significant per-formance degradation,which further validate the superiority of our method.