一. 前言本篇博客是《基于YOLO26害虫实时检测系统》系列文章之《纸板缺陷检测数据集说明(含下载链接)》网上有很多害虫检测数据集的数据百度一下一搜一大堆但质量参差不齐很多不能用即使一个一个的看也会浪费很多时间才有可能辨别出有用的数据集。为了方便你我他本博客将分享一个由我自己整理的害虫检测数据可直接应用到目标检测算法比如yolo系列中当然也可以应用到分类模型中数据集总共有18976张图片并包含它的高质量标注文件。数据质量非常高甚至可应用到工业落地的项目中。二. 害虫检测类别说明在害虫检测识别算法开发中我们需要定义害虫的行为类别项目将害虫状态分为102种names {0: rice_leaf_roller, 1: rice_leaf_caterpillar, 2: paddy_stem_maggot, 3: asiatic_rice_borer,4: yellow_rice_borer, 5: rice_gall_midge, 6: Rice_Stemfly, 7: brown_plant_hopper,8: white_backed_plant_hopper, 9: small_brown_plant_hopper, 10: rice_water_weevil, 11: rice_leafhopper,12: grain_spreader_thrips, 13: rice_shell_pest, 14: grub, 15: mole_cricket,16: wireworm, 17: white_margined_moth, 18: black_cutworm, 19: large_cutworm,20: yellow_cutworm, 21: red_spider, 22: corn_borer, 23: army_worm,24: aphids, 25: Potosiabre_vitarsis, 26: peach_borer, 27: english_grain_aphid,28: green_bug, 29: bird_cherry-oataphid, 30: wheat_blossom_midge, 31: penthaleus_major,32: longlegged_spider_mite, 33: wheat_phloeothrips, 34: wheat_sawfly, 35: cerodonta_denticornis,36: beet_fly, 37: flea_beetle, 38: cabbage_army_worm, 39: beet_army_worm,40: Beet_spot_flies, 41: meadow_moth, 42: beet_weevil, 43: sericaorient_alismots_chulsky,44: alfalfa_weevil, 45: flax_budworm, 46: alfalfa_plant_bug, 47: tarnished_plant_bug,48: Locustoidea, 49: lytta_polita, 50: legume_blister_beetle, 51: blister_beetle,52: therioaphis_maculata_Buckton, 53: odontothrips_loti, 54: Thrips, 55: alfalfa_seed_chalcid,56: Pieris_canidia, 57: Apolygus_lucorum, 58: Limacodidae, 59: Viteus_vitifoliae,60: Colomerus_vitis, 61: Brevipoalpus_lewisi_McGregor, 62: oides_decempunctata, 63: Polyphagotars_onemus_latus,64: Pseudococcus_comstocki_Kuwana, 65: parathrene_regalis, 66: Ampelophaga, 67: Lycorma_delicatula,68: Xylotrechus, 69: Cicadella_viridis, 70: Miridae, 71: Trialeurodes_vaporariorum,72: Erythroneura_apicalis, 73: Papilio_xuthus, 74: Panonchus_citri_McGregor, 75: Phyllocoptes_oleiverus_ashmead,76: Icerya_purchasi_Maskell, 77: Unaspis_yanonensis, 78: Ceroplastes_rubens, 79: Chrysomphalus_aonidum,80: Parlatoria_zizyphus_Lucus, 81: Nipaecoccus_vastalor, 82: Aleurocanthus_spiniferus, 83: Tetradacus_c_Bactrocera_minax,84: Dacus_dorsalis(Hendel), 85: Bactrocera_tsuneonis, 86: Prodenia_litura, 87: Adristyrannus,88: Phyllocnistis_citrella_Stainton, 89: Toxoptera_citricidus, 90: Toxoptera_aurantii, 91: Aphis_citricola_Vander_Goot,92: Scirtothrips_dorsalis_Hood, 93: Dasineura_sp, 94: Lawana_imitata_Melichar, 95: Salurnis_marginella_Guerr,96: Deporaus_marginatus_Pascoe, 97: Chlumetia_transversa, 98: Mango_flat_beak_leafhopper, 99: Rhytidodera_bowrinii_white,100: Sternochetus_frigidus, 101: Cicadellidae}为了便于大家理解下面给出实际应用中的效果图三. 害虫测数据集下载数据包含内容害虫检测数据集数据集总共有18976张图片其中验证集2784张训练集16192张都有相应的标注文件四. 深度学习YOLO26神经网络实现害虫检测和识别参考文章害虫检测和识别2基于深度学习YOLO26神经网络实现害虫检测和识别(含训练代码和数据集)害虫检测和识别2基于深度学习YOLO26神经网络实现害虫检测和识别(含训练代码和数据集)-CSDN博客五. 基于GUI交互界面实现害虫检测和识别参考文章害虫检测和识别3基于深度学习YOLO26神经网络实现害虫检测和识别(含训练代码、数据集和GUI交互界面)害虫检测和识别3基于深度学习YOLO26神经网络实现害虫检测和识别(含训练代码、数据集和GUI交互界面-CSDN博客项目完整文件下载请见演示与介绍视频的简介处给出➷➷➷https://www.bilibili.com/video/BV1Lm8s6GEn6/