[train hyper-parameters: Namespace(batch_size=16, lr=0.001, lrf=0.01)]
[epoch: 1]
train loss:0.0707 test accuracy:0.8121
[epoch: 2]
train loss:0.0287 test accuracy:0.8879
[epoch: 3]
train loss:0.0141 test accuracy:0.9000
[epoch: 4]
train loss:0.0097 test accuracy:0.9242
[epoch: 5]
train loss:0.0061 test accuracy:0.9303
[epoch: 6]
train loss:0.0065 test accuracy:0.9424
[epoch: 7]
train loss:0.0054 test accuracy:0.9485
[epoch: 8]
train loss:0.0029 test accuracy:0.9182
[epoch: 9]
train loss:0.0019 test accuracy:0.9182
[epoch: 10]
train loss:0.0032 test accuracy:0.9394
[epoch: 11]
train loss:0.0044 test accuracy:0.9515
[epoch: 12]
train loss:0.0020 test accuracy:0.9303
[epoch: 13]
train loss:0.0010 test accuracy:0.9545
[epoch: 14]
train loss:0.0007 test accuracy:0.9636
[epoch: 15]
train loss:0.0004 test accuracy:0.9667
[epoch: 16]
train loss:0.0002 test accuracy:0.9667
[epoch: 17]
train loss:0.0001 test accuracy:0.9667
[epoch: 18]
train loss:0.0006 test accuracy:0.9515
[epoch: 19]
train loss:0.0008 test accuracy:0.9606
[epoch: 20]
train loss:0.0004 test accuracy:0.9606
[epoch: 21]
train loss:0.0003 test accuracy:0.9636
[epoch: 22]
train loss:0.0002 test accuracy:0.9606
[epoch: 23]
train loss:0.0001 test accuracy:0.9667
[epoch: 24]
train loss:0.0001 test accuracy:0.9667
[epoch: 25]
train loss:0.0001 test accuracy:0.9667
[epoch: 26]
train loss:0.0001 test accuracy:0.9667
[epoch: 27]
train loss:0.0000 test accuracy:0.9636
[epoch: 28]
train loss:0.0000 test accuracy:0.9636
[epoch: 29]
train loss:0.0000 test accuracy:0.9636
[epoch: 30]
train loss:0.0000 test accuracy:0.9636
[epoch: 31]
train loss:0.0000 test accuracy:0.9636
[epoch: 32]
train loss:0.0000 test accuracy:0.9606
[epoch: 33]
train loss:0.0000 test accuracy:0.9636
[epoch: 34]
train loss:0.0000 test accuracy:0.9667
[epoch: 35]
train loss:0.0000 test accuracy:0.9667
[epoch: 36]
train loss:0.0000 test accuracy:0.9667
[epoch: 37]
train loss:0.0000 test accuracy:0.9636
[epoch: 38]
train loss:0.0000 test accuracy:0.9636
[epoch: 39]
train loss:0.0000 test accuracy:0.9636
[epoch: 40]
train loss:0.0000 test accuracy:0.9636
[epoch: 41]
train loss:0.0000 test accuracy:0.9636
[epoch: 42]
train loss:0.0000 test accuracy:0.9636
[epoch: 43]
train loss:0.0000 test accuracy:0.9636
[epoch: 44]
train loss:0.0000 test accuracy:0.9636
[epoch: 45]
train loss:0.0000 test accuracy:0.9636
[epoch: 46]
train loss:0.0000 test accuracy:0.9636
[epoch: 47]
train loss:0.0000 test accuracy:0.9636
[epoch: 48]
train loss:0.0000 test accuracy:0.9636
[epoch: 49]
train loss:0.0000 test accuracy:0.9636
[epoch: 50]
train loss:0.0000 test accuracy:0.9636
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
本项目基于VGG16迁移学习的图像分类,可直接运行。 数据集采用其他垃圾六分类数据集(一次性快餐盒、污损塑料、烟蒂、牙签、破碎花盆和碗碟、竹筷),包括990张训练图片和330张预测图片。 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96.5%精度。 如果想要训练自己的数据集,请查看README文件
资源推荐
资源详情
资源评论
收起资源包目录
其他垃圾数据集的六分类图像识别项目:基于VGG16网络的迁移学习 (1342个子文件)
img_1074.jpg 279KB
img_921.jpg 257KB
img_2056.jpg 203KB
img_48.jpg 168KB
img_787.jpg 164KB
img_2053.jpg 162KB
img_2058.jpg 160KB
img_2038.jpg 159KB
img_2083.jpg 154KB
img_1901.jpg 153KB
img_2097.jpg 153KB
img_245.jpg 146KB
img_97.jpg 145KB
img_451.jpg 142KB
img_2050.jpg 141KB
img_681.jpg 136KB
img_238.jpg 134KB
img_967.jpg 133KB
img_871.jpg 132KB
img_1898.jpg 129KB
img_1903.jpg 128KB
img_4.jpg 127KB
img_559.jpg 126KB
img_606.jpg 126KB
img_378.jpg 125KB
img_419.jpg 125KB
img_428.jpg 125KB
img_545.jpg 124KB
img_937.jpg 122KB
img_2064.jpg 119KB
img_872.jpg 118KB
img_1183.jpg 117KB
img_1621.jpg 114KB
img_1050.jpg 112KB
img_385.jpg 112KB
img_556.jpg 109KB
img_2131.jpg 109KB
img_713.jpg 108KB
img_755.jpg 108KB
img_2125.jpg 108KB
img_986.jpg 108KB
img_720.jpg 106KB
img_485.jpg 106KB
img_358.jpg 106KB
img_779.jpg 105KB
img_1812.jpg 104KB
img_31.jpg 104KB
img_1936.jpg 103KB
img_807.jpg 103KB
img_376.jpg 102KB
img_1014.jpg 101KB
img_1203.jpg 100KB
img_1230.jpg 100KB
img_2094.jpg 99KB
img_1527.jpg 98KB
img_152.jpg 97KB
img_356.jpg 95KB
img_1902.jpg 94KB
img_2119.jpg 94KB
img_2198.jpg 94KB
img_704.jpg 93KB
img_434.jpg 93KB
img_618.jpg 91KB
img_1055.jpg 91KB
img_1905.jpg 90KB
img_514.jpg 90KB
img_741.jpg 90KB
img_814.jpg 90KB
img_620.jpg 89KB
img_677.jpg 89KB
img_475.jpg 89KB
img_583.jpg 89KB
img_525.jpg 89KB
img_224.jpg 88KB
img_251.jpg 88KB
img_976.jpg 88KB
img_479.jpg 87KB
img_2177.jpg 87KB
img_237.jpg 86KB
img_706.jpg 86KB
img_295.jpg 86KB
img_121.jpg 85KB
img_698.jpg 85KB
img_2076.jpg 85KB
img_28.jpg 85KB
img_617.jpg 84KB
img_138.jpg 84KB
img_235.jpg 83KB
img_2061.jpg 83KB
img_745.jpg 83KB
img_531.jpg 82KB
img_740.jpg 82KB
img_692.jpg 82KB
img_747.jpg 82KB
img_764.jpg 82KB
img_688.jpg 81KB
img_354_result.jpg 80KB
img_2115.jpg 80KB
img_804.jpg 80KB
img_503.jpg 80KB
共 1342 条
- 1
- 2
- 3
- 4
- 5
- 6
- 14
资源评论
Ai医学图像分割
- 粉丝: 2w+
- 资源: 2128
下载权益
C知道特权
VIP文章
课程特权
开通VIP
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
- GitBook 教授 Javascript 编程基础知识.zip
- Generation.org 开发的 JAVA 模块练习.zip
- FastDFS Java 客户端 SDK.zip
- etcd java 客户端.zip
- Esercizi di informatica!执行计划,metti alla prova!.zip
- Eloquent JavaScript 翻译 - 2ª edição .zip
- Eclipse Paho Java MQTT 客户端库 Paho 是一个 Eclipse IoT 项目 .zip
- disconf 的 Java 应用程序.zip
- cloud.google.com 上使用的 Java 和 Kotlin 代码示例.zip
- 未命名3(3).cpp
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