In　the　production　process　of　bamboo　laminated　lumber,　in　order　to　reduce　the　waste　generated　in　the　process　of　bamboo　subdivision　and　rough　section,　it　is　necessary　to　determine　the　inner　contour　perimeter　and　thickness　of　the　bamboo　end　surface.　The　long　bamboo　strip　with　bamboo　branch　also　cannot　carry　out　the　rough　section　because　of　the　feature　on　its　fiber　structure.　In　order　to　improve　the　production　efficiency　of　the　bamboo　industry　and　reduce　the　waste　of　bamboo　materials,　this　study　proposed　a　lightweight　end-to-end　network　model,　which　could　not　only　obtain　the　precise　position　of　bamboo　branches,　but　also　segment　the　inner　and　outer　contours　of　bamboo　end　faces,　providing　conditions　for　subsequent　calculation　of　the　bamboo　inner　contour　and　thickness.　The　network　can　be　divided　into　two　stages,　i.e.,　down-sampling　and　up-sampling.　In　the　down-sampling　stage,　a　backbone　feature　extraction　network　was　built　by　stacking　3×3　convolutional　layers　to　achieve　16　times　down-sampling.　Each　convolutional　layer　would　be　fol-　lowed　by　a　BN　layer　and　a　PReLU　activation　function.　In　order　to　alleviate　the　problem　of　gradient　disappearance,　this　study　also　built　a　residual　structure　in　the　backbone.　In　the　up-sampling　stage,　two　times　of　four　times　up-sampling　were　used　to　achieve　end-to-end　output.　Before　the　first　up-sampling,　the　feature　map　was　sent　to　the　serial-parallel　ASPP.　Serial-parallel　ASPP　was　improved　on　the　basis　of　ASPP.　It　changed　the　convolution　kernel　of　the　first　branch　to　3×3　to　further　expand　the　receptive　field.　In　order　to　alleviate　the　“grid　effect”　caused　by　the　dilated　convolution,　the　parallel　dilated　convolution　branch　was　reduced　to　two,　each　with　serial　two　dilated　convolutions.　Experiments　proved　that　the　improved　ASPP　can　further　improved　the　network　accuracy.　Before　the　second　up-sampling,　it　was　fused　with　the　CBAM　mechanism,　which　consisted　of　two　parts,　i.e.,　the　spatial　attention　module　and　the　channel　at-　tention　module.　This　research　used　different　loss　functions　for　different　output　tasks　in　the　training　stage.　The　end　face　segmentation　adopted　the　loss　function　combining　BCE　and　Dice,　and　the　bamboo　branch　position　detection　adopted　the　MSE　loss　function.　Experiment　results　showed　that　the　proposed　method　achieved　96.11%　intersection-over-union　in　the　task　of　segmenting　bamboo　end　faces,　3.09%　distance　error　in　the　bamboo　branch　position　detection　task,　and　114.21　frames　per　second.　Compared　with　the　LEDNet,　BiSeNet-V2,　and　RegSeg　lightweight　segmentation　networks,　the　method　proposed　in　this　study　can　better　balance　the　detection　accuracy　and　detection　speed,　providing　technical　support　for　realizing　the　automation　of　bamboo　laminated　lumber　productions.　©　2023　Nanjing　Forestry　University.　All　rights　reserved.