[train hyper-parameters: Namespace(batch_size=16, epochs=50)]
[epoch: 1]
train loss:0.3083 test accuracy:0.0198
[epoch: 2]
train loss:0.2946 test accuracy:0.0313
[epoch: 3]
train loss:0.2830 test accuracy:0.0494
[epoch: 4]
train loss:0.2731 test accuracy:0.0659
[epoch: 5]
train loss:0.2648 test accuracy:0.0956
[epoch: 6]
train loss:0.2556 test accuracy:0.1120
[epoch: 7]
train loss:0.2463 test accuracy:0.1079
[epoch: 8]
train loss:0.2366 test accuracy:0.1450
[epoch: 9]
train loss:0.2299 test accuracy:0.1582
[epoch: 10]
train loss:0.2200 test accuracy:0.1730
[epoch: 11]
train loss:0.2141 test accuracy:0.1928
[epoch: 12]
train loss:0.2057 test accuracy:0.2076
[epoch: 13]
train loss:0.1966 test accuracy:0.2339
[epoch: 14]
train loss:0.1889 test accuracy:0.2718
[epoch: 15]
train loss:0.1824 test accuracy:0.2586
[epoch: 16]
train loss:0.1732 test accuracy:0.3097
[epoch: 17]
train loss:0.1647 test accuracy:0.3171
[epoch: 18]
train loss:0.1591 test accuracy:0.3056
[epoch: 19]
train loss:0.1491 test accuracy:0.3386
[epoch: 20]
train loss:0.1424 test accuracy:0.3311
[epoch: 21]
train loss:0.1363 test accuracy:0.3575
[epoch: 22]
train loss:0.1279 test accuracy:0.3501
[epoch: 23]
train loss:0.1191 test accuracy:0.3509
[epoch: 24]
train loss:0.1126 test accuracy:0.3567
[epoch: 25]
train loss:0.1065 test accuracy:0.3764
[epoch: 26]
train loss:0.0989 test accuracy:0.3979
[epoch: 27]
train loss:0.0916 test accuracy:0.3888
[epoch: 28]
train loss:0.0840 test accuracy:0.3929
[epoch: 29]
train loss:0.0788 test accuracy:0.3855
[epoch: 30]
train loss:0.0726 test accuracy:0.3970
[epoch: 31]
train loss:0.0645 test accuracy:0.4053
[epoch: 32]
train loss:0.0596 test accuracy:0.4152
[epoch: 33]
train loss:0.0546 test accuracy:0.3937
[epoch: 34]
train loss:0.0513 test accuracy:0.4135
[epoch: 35]
train loss:0.0444 test accuracy:0.3781
[epoch: 36]
train loss:0.0404 test accuracy:0.4028
[epoch: 37]
train loss:0.0407 test accuracy:0.4119
[epoch: 38]
train loss:0.0333 test accuracy:0.4234
[epoch: 39]
train loss:0.0332 test accuracy:0.4226
[epoch: 40]
train loss:0.0302 test accuracy:0.4152
[epoch: 41]
train loss:0.0279 test accuracy:0.4473
[epoch: 42]
train loss:0.0282 test accuracy:0.4357
[epoch: 43]
train loss:0.0244 test accuracy:0.4077
[epoch: 44]
train loss:0.0252 test accuracy:0.4316
[epoch: 45]
train loss:0.0233 test accuracy:0.4432
[epoch: 46]
train loss:0.0195 test accuracy:0.4160
[epoch: 47]
train loss:0.0233 test accuracy:0.4152
[epoch: 48]
train loss:0.0190 test accuracy:0.4423
[epoch: 49]
train loss:0.0173 test accuracy:0.4407
[epoch: 50]
train loss:0.0167 test accuracy:0.4201
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
【基于efficientnet对151类大型动物图像识别数据集】 【包含代码、数据集和训练好的权重文件,可直接运行】 项目总大小:77MB 本数据集分为以下151类:豹子、蟒蛇、长毛象、猫狗等等151个类别 下载解压后的图像目录:训练集(5056张图片)、和测试集(1214张图片) data-train 训练集-每个子文件夹放同类别的图像,文件夹名为分类类别 data-test 测试集-每个子文件夹放同类别的图像,文件夹名为分类类别 【项目介绍,efficientnet的参数量为403,9573】 网络训练的时候采用cos 学习率自动衰减,训练了50个epoch。模型在测试集最好的表现达到45%精度,加大epoch可以增加精度。在run_results 目录下存有最好的权重文件,以及训练日志和loss、精度曲线等等 预测的时候,只需要运行predict即可,代码会自动将inference下所有图片推理,并取前三个概率最大类别的绘制在左上角 【训练自己的数据参考readme文件,不需要更改,代码会自动生成,例如分类类别个数等等】
资源推荐
资源详情
资源评论
收起资源包目录
经典轻量级CNN网络之EfficientNet 图像分类网络实战项目:151类大型动物图像识别数据集 (2000个子文件)
acinonyx-jubatus_16_fabcb506_result.jpg 29KB
lampropeltis-triangulum_40_0d5c2938.jpg 22KB
pavo-cristatus_58_9b67f8f6.jpg 21KB
heloderma-suspectum_97_1cd550c1.jpg 20KB
codium-fragile_23_59dd8a3c.jpg 20KB
eunectes-murinus_97_fb89577a.jpg 20KB
chelonia-mydas_48_a0c6655f.jpg 20KB
heloderma-suspectum_85_2d4c4d2d.jpg 20KB
pavo-cristatus_34_6870d199.jpg 20KB
eunectes-murinus_70_a66d32be.jpg 20KB
codium-fragile_75_d46863a9.jpg 19KB
centruroides-vittatus_21_d68bf8e9.jpg 19KB
ailurus-fulgens_32_7d4e07de.jpg 19KB
eidolon-helvum_3_f100efb6.jpg 19KB
heloderma-suspectum_44_8f869d55.jpg 19KB
alces-alces_38_0dada1cd.jpg 19KB
aethia-cristatella_5_abc6c27d_result.jpg 19KB
lampropeltis-triangulum_28_880a642e.jpg 19KB
equus-quagga_43_f5806387.jpg 19KB
lepus-americanus_94_0f8a1ba6.jpg 19KB
codium-fragile_88_3cebf427.jpg 18KB
codium-fragile_66_ca04c016.jpg 18KB
pantherophis-alleghaniensis_36_b7cee827.jpg 18KB
lampropeltis-triangulum_90_4c1696e0.jpg 18KB
ovis-aries_4_76f40054.jpg 18KB
pantherophis-alleghaniensis_26_c6bf9f00.jpg 18KB
pavo-cristatus_7_86f12e67.jpg 18KB
pantherophis-alleghaniensis_77_31a471b6.jpg 18KB
lepus-americanus_33_856409f0.jpg 18KB
codium-fragile_85_56bfbda7.jpg 18KB
hapalochlaena-maculosa_63_937ebcbe.jpg 18KB
lampropeltis-triangulum_8_deb233c1.jpg 18KB
centrochelys-sulcata_38_12963b80.jpg 18KB
malayopython-reticulatus_55_75ef7491.jpg 18KB
codium-fragile_44_1b60be0a.jpg 18KB
centrochelys-sulcata_98_f8394f9d.jpg 18KB
pavo-cristatus_54_62ed414e.jpg 18KB
ailuropoda-melanoleuca_8_464a554f.jpg 18KB
ovis-aries_21_133dde4b.jpg 18KB
telmatobufo-bullocki_17_0a5b0ce5.jpg 18KB
panthera-leo_85_93fea230.jpg 18KB
pantherophis-alleghaniensis_60_52e7ab5e.jpg 18KB
heloderma-suspectum_46_b8762654.jpg 18KB
pavo-cristatus_17_9cdc94ec.jpg 18KB
malayopython-reticulatus_84_7546c52e.jpg 18KB
malayopython-reticulatus_83_b6f56a11.jpg 18KB
pavo-cristatus_90_0e327b99.jpg 18KB
centrochelys-sulcata_69_9054ce5a.jpg 17KB
acinonyx-jubatus_94_1a947b54.jpg 17KB
chelonia-mydas_68_60d15998.jpg 17KB
pavo-cristatus_16_12b76ac1.jpg 17KB
acinonyx-jubatus_96_d0bb6474.jpg 17KB
sciurus-carolinensis_27_f22205a9.jpg 17KB
pavo-cristatus_69_87f69d04.jpg 17KB
pantherophis-alleghaniensis_61_0bb0fc54.jpg 17KB
equus-quagga_33_2a546cdb.jpg 17KB
sciurus-carolinensis_28_08e91d73.jpg 17KB
ailuropoda-melanoleuca_8_845f0202.jpg 17KB
pavo-cristatus_58_c535838d.jpg 17KB
telmatobufo-bullocki_94_65b87234.jpg 17KB
rusa-unicolor_56_966d5cb7.jpg 17KB
malayopython-reticulatus_82_bdffb06b.jpg 17KB
pavo-cristatus_95_2d6c2d80.jpg 17KB
pavo-cristatus_44_e093a057.jpg 17KB
heloderma-suspectum_100_a5fbe855.jpg 17KB
eidolon-helvum_36_d8b3c87d.jpg 17KB
lampropeltis-triangulum_37_04cac3de.jpg 17KB
pantherophis-alleghaniensis_86_ed0ab3bf.jpg 17KB
telmatobufo-bullocki_74_4fb0d462.jpg 17KB
heloderma-suspectum_69_a5db20ab.jpg 17KB
lepus-americanus_92_2713c3be.jpg 17KB
hapalochlaena-maculosa_56_f8e6cabb.jpg 17KB
pantherophis-alleghaniensis_98_9b2d087f.jpg 17KB
hapalochlaena-maculosa_73_166060d2.jpg 17KB
hapalochlaena-maculosa_75_4a87b448.jpg 17KB
pantherophis-alleghaniensis_29_61b40235.jpg 17KB
gallus-gallus-domesticus_48_05303deb.jpg 17KB
icterus-gularis_29_52f99beb.jpg 17KB
centruroides-vittatus_12_7625ede0.jpg 17KB
centruroides-vittatus_80_b9668028.jpg 17KB
heloderma-suspectum_61_ffa04f4f.jpg 17KB
pavo-cristatus_56_7b907e28.jpg 17KB
eunectes-murinus_19_774821a5.jpg 17KB
eunectes-murinus_59_7f9500b0.jpg 16KB
pavo-cristatus_19_91031dc3.jpg 16KB
acinonyx-jubatus_13_e2559ec4.jpg 16KB
heloderma-suspectum_14_07b48e87.jpg 16KB
rusa-unicolor_80_1d1c83da.jpg 16KB
giraffa-camelopardalis_42_e79471b6.jpg 16KB
heloderma-suspectum_33_bbc6f81a.jpg 16KB
centruroides-vittatus_87_e6cac359.jpg 16KB
crotalus-atrox_79_af201921.jpg 16KB
pantherophis-alleghaniensis_98_4be8a6f4.jpg 16KB
ophiophagus-hannah_44_3cc7e25e.jpg 16KB
heloderma-suspectum_61_93274343.jpg 16KB
heloderma-suspectum_11_951b3caa.jpg 16KB
pantherophis-alleghaniensis_79_9502f794.jpg 16KB
pavo-cristatus_44_a4d248ea.jpg 16KB
pavo-cristatus_54_c00cf927.jpg 16KB
centruroides-vittatus_44_e0266b0a.jpg 16KB
共 2000 条
- 1
- 2
- 3
- 4
- 5
- 6
- 20
资源评论
Ai医学图像分割
- 粉丝: 2w+
- 资源: 2122
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功