At　present,　millimeter　wave　radar　imaging　technology　has　become　a　recognized　human　security　solution　in　the　field.　The　millimeter　wave　radar　imaging　system　can　be　used　to　detect　a　concealed　object;　multiple-input　multiple-output　radar　antennas　and　synthetic　aperture　radar　techniques　are　used　to　obtain　the　raw　data.　The　analytical　Fourier　transform　algorithm　is　used　for　image　reconstruction.　When　imaging　a　target　at　90　mm　from　radar,　which　belongs　to　the　near　field　imaging　scene,　the　image　resolution　can　reach　1.90　mm　in　X-direction　and　1.73　mm　in　Y-direction.　Since　the　error　caused　by　the　distance　between　radar　and　target　will　lead　to　noise,　the　original　reconstruction　image　is　processed　by　gamma　transform,　which　eliminates　image　noise,　then　the　image　is　enhanced　by　linearly　stretched　transform　to　improve　visual　recognition,　which　lays　a　good　foundation　for　supervised　learning.　In　order　to　flexibly　deploy　the　machine　learning　algorithm　in　various　application　scenarios,　ShuffleNetV2,　MobileNetV3　and　GhostNet　representative　of　lightweight　convolutional　neural　networks　with　redefined　convolution,　branch　structure　and　optimized　network　layer　structure　are　used　to　distinguish　multi-category　SAR　images.　Through　the　fusion　of　squeeze-and-excitation　and　the　selective　kernel　attention　mechanism,　more　precise　features　are　extracted　for　classification,　the　proposed　GhostNet_SEResNet56　can　realize　the　best　classification　accuracy　of　SAR　images　within　limited　resources,　which　prediction　accuracy　is　98.18%　and　the　number　of　parameters　is　0.45　M.