This　paper　proposes　a　fast　VVC　coding　unit　partition　algorithm　based　on　ensemble　convolutional　neural　network　(CNN)　by　investigating　and　bagging　spatial-temporal　adjacent　coding　features.　First,　we　propose　an　ensemble　CNN　framework　to　aggregate　the　reference　features　to　predict　the　depths　of　uncoded　CUs.　The　proposed　model　consists　of　three　light-weight　CNNs,　which　can　compromise　prediction　accuracy　with　overhead.　Then　a　majority　voting　mechanism　is　used　to　unify　the　predicted　depth.　By　extracting　the　majority　prediction　of　base　learners,　the　outputs　of　three　CNNs　are　integrated　to　obtain　the　final　prediction.　To　avoid　Rate　Distortion　(RD)　loss　caused　by　a　small　probability　of　prediction　failure,　we　introduce　the　optimal　depth　strategy.　During　the　encoding　process,　the　optimal　depth　is　used　for　the　decision-making　of　coding　unit　partition,　thus　avoiding　redundant　rate　distortion　optimization　process.　Compared　with　the　original　encoder,　the　proposed　algorithm　saves　21.56%　encoding　time　on　average,　with　a　BDBR　loss　of　0.39%.　The　performance　is　even　superior　in　High-Definition　(HD)　and　Ultra　HD　(UHD)　sequences,　up　to　59.52%.　This　approach　has　a　great　efficiency　of　time　reduction　compared　with　state-of-the-arts　with　negligible　RD　performance　loss.