Depression　as　a　common　mental　illness,　has　become　the　second　largest　killer　of　human　beings.　However　a　significant　number　of　patients　are　not　even　aware　they　have　depression.　Therefore,　combined　with　deep　learning　method,　a　novel　diagnosis　method　of　depression　based　on　Electroencephalography　(EEG)　signals　is　proposed　in　this　paper,　which　adopts　two-dimensional　Convolutional　Neural　Network　(2D-CNN)　to　build　a　binary　classification　model.　Firstly,　the　EEG　signals　are　converted　into　RGB　three-channel　color　brain　maps　as　the　input　of　2D-CNN.　Secondly,　2D-CNN　is　applied　to　automatically　extract　EEG　features　and　classify　them.　Moreover,　the　effectiveness　and　reliability　of　the　proposed　algorithm　are　assessed　on　the　depression　dataset.　In　addition,　the　proposed　method　is　compared　with　Support　Vector　Machine　(SVM)　classifier　and　Long　and　Short　Term　Memory　(LSTM)　network.　The　experimental　results　show　that　the　proposed　2D-CNN　algorithm　has　the　best　performance,　and　the　accuracy　can　reach　up　to　92%.　This　method　provide　a　novel　approach　for　the　diagnosis　of　depression.　©　2022,　The　Author(s),　under　exclusive　license　to　Springer　Nature　Singapore　Pte　Ltd.