[train hyper-parameters: Namespace(batch_size=16, epochs=100)]
[epoch: 1]
train loss:0.1188 test accuracy:0.4343
[epoch: 2]
train loss:0.1103 test accuracy:0.4343
[epoch: 3]
train loss:0.0990 test accuracy:0.4963
[epoch: 4]
train loss:0.0994 test accuracy:0.3796
[epoch: 5]
train loss:0.0931 test accuracy:0.5643
[epoch: 6]
train loss:0.0847 test accuracy:0.5687
[epoch: 7]
train loss:0.0815 test accuracy:0.5377
[epoch: 8]
train loss:0.0781 test accuracy:0.5835
[epoch: 9]
train loss:0.0738 test accuracy:0.5643
[epoch: 10]
train loss:0.0730 test accuracy:0.5938
[epoch: 11]
train loss:0.0666 test accuracy:0.5347
[epoch: 12]
train loss:0.0648 test accuracy:0.6263
[epoch: 13]
train loss:0.0600 test accuracy:0.5775
[epoch: 14]
train loss:0.0572 test accuracy:0.5938
[epoch: 15]
train loss:0.0511 test accuracy:0.6219
[epoch: 16]
train loss:0.0503 test accuracy:0.6470
[epoch: 17]
train loss:0.0474 test accuracy:0.6366
[epoch: 18]
train loss:0.0435 test accuracy:0.5879
[epoch: 19]
train loss:0.0409 test accuracy:0.6322
[epoch: 20]
train loss:0.0373 test accuracy:0.6174
[epoch: 21]
train loss:0.0377 test accuracy:0.6189
[epoch: 22]
train loss:0.0346 test accuracy:0.5716
[epoch: 23]
train loss:0.0301 test accuracy:0.6219
[epoch: 24]
train loss:0.0254 test accuracy:0.5761
[epoch: 25]
train loss:0.0244 test accuracy:0.6514
[epoch: 26]
train loss:0.0246 test accuracy:0.6041
[epoch: 27]
train loss:0.0224 test accuracy:0.6115
[epoch: 28]
train loss:0.0208 test accuracy:0.6455
[epoch: 29]
train loss:0.0184 test accuracy:0.6145
[epoch: 30]
train loss:0.0158 test accuracy:0.6322
[epoch: 31]
train loss:0.0159 test accuracy:0.6130
[epoch: 32]
train loss:0.0162 test accuracy:0.5746
[epoch: 33]
train loss:0.0162 test accuracy:0.6041
[epoch: 34]
train loss:0.0130 test accuracy:0.6470
[epoch: 35]
train loss:0.0157 test accuracy:0.6219
[epoch: 36]
train loss:0.0104 test accuracy:0.6337
[epoch: 37]
train loss:0.0149 test accuracy:0.6086
[epoch: 38]
train loss:0.0107 test accuracy:0.6337
[epoch: 39]
train loss:0.0114 test accuracy:0.6027
[epoch: 40]
train loss:0.0109 test accuracy:0.5953
[epoch: 41]
train loss:0.0096 test accuracy:0.6352
[epoch: 42]
train loss:0.0118 test accuracy:0.5894
[epoch: 43]
train loss:0.0114 test accuracy:0.6278
[epoch: 44]
train loss:0.0114 test accuracy:0.6145
[epoch: 45]
train loss:0.0082 test accuracy:0.6204
[epoch: 46]
train loss:0.0083 test accuracy:0.5849
[epoch: 47]
train loss:0.0098 test accuracy:0.5894
[epoch: 48]
train loss:0.0116 test accuracy:0.6086
[epoch: 49]
train loss:0.0082 test accuracy:0.6012
[epoch: 50]
train loss:0.0096 test accuracy:0.6233
[epoch: 51]
train loss:0.0087 test accuracy:0.6292
[epoch: 52]
train loss:0.0078 test accuracy:0.6056
[epoch: 53]
train loss:0.0081 test accuracy:0.5894
[epoch: 54]
train loss:0.0089 test accuracy:0.6056
[epoch: 55]
train loss:0.0065 test accuracy:0.5864
[epoch: 56]
train loss:0.0089 test accuracy:0.6278
[epoch: 57]
train loss:0.0084 test accuracy:0.6352
[epoch: 58]
train loss:0.0084 test accuracy:0.6100
[epoch: 59]
train loss:0.0068 test accuracy:0.6189
[epoch: 60]
train loss:0.0080 test accuracy:0.6012
[epoch: 61]
train loss:0.0086 test accuracy:0.6440
[epoch: 62]
train loss:0.0082 test accuracy:0.5864
[epoch: 63]
train loss:0.0053 test accuracy:0.6160
[epoch: 64]
train loss:0.0054 test accuracy:0.6233
[epoch: 65]
train loss:0.0083 test accuracy:0.6322
[epoch: 66]
train loss:0.0068 test accuracy:0.5820
[epoch: 67]
train loss:0.0039 test accuracy:0.6027
[epoch: 68]
train loss:0.0080 test accuracy:0.5672
[epoch: 69]
train loss:0.0073 test accuracy:0.6086
[epoch: 70]
train loss:0.0066 test accuracy:0.5938
[epoch: 71]
train loss:0.0071 test accuracy:0.5938
[epoch: 72]
train loss:0.0051 test accuracy:0.6130
[epoch: 73]
train loss:0.0075 test accuracy:0.6086
[epoch: 74]
train loss:0.0078 test accuracy:0.6012
[epoch: 75]
train loss:0.0048 test accuracy:0.6278
[epoch: 76]
train loss:0.0046 test accuracy:0.6100
[epoch: 77]
train loss:0.0035 test accuracy:0.6041
[epoch: 78]
train loss:0.0050 test accuracy:0.6233
[epoch: 79]
train loss:0.0065 test accuracy:0.6233
[epoch: 80]
train loss:0.0084 test accuracy:0.5879
[epoch: 81]
train loss:0.0066 test accuracy:0.5820
[epoch: 82]
train loss:0.0053 test accuracy:0.6278
[epoch: 83]
train loss:0.0064 test accuracy:0.6056
[epoch: 84]
train loss:0.0055 test accuracy:0.6145
[epoch: 85]
train loss:0.0064 test accuracy:0.5894
[epoch: 86]
train loss:0.0042 test accuracy:0.6455
[epoch: 87]
train loss:0.0050 test accuracy:0.6130
[epoch: 88]
train loss:0.0072 test accuracy:0.6071
[epoch: 89]
train loss:0.0056 test accuracy:0.5968
[epoch: 90]
train loss:0.0046 test accuracy:0.6071
[epoch: 91]
train loss:0.0045 test accuracy:0.5598
[epoch: 92]
train loss:0.0054 test accuracy:0.6484
[epoch: 93]
train loss:0.0065 test accuracy:0.6086
[epoch: 94]
train loss:0.0068 test accuracy:0.6145
[epoch: 95]
train loss:0.0038 test accuracy:0.6292
[epoch: 96]
train loss:0.0042 test accuracy:0.6278
[epoch: 97]
train loss:0.0052 test accuracy:0.6086
[epoch: 98]
train loss:0.0044 test accuracy:0.6100
[epoch: 99]
train loss:0.0063 test accuracy:0.6086
[epoch: 100]
train loss:0.0062 test accuracy:0.6160
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 shuffleNett v1的图像分类,可直接运行。 数据集采用厨房常见的8类厨余垃圾(剩菜剩饭、大骨头、水果果皮、水果果肉、茶叶渣、菜根菜叶、蛋壳、鱼骨),包括2031张训练图片和677张预测图片。 网络训练了100个epoch。模型在测试集最好的表现达到65%精度 shuffleNet v1 参数有1815296个,百万的数量级
资源推荐
资源详情
资源评论
收起资源包目录
经典CNN轻量级网络之shuffleNet v1 对厨余垃圾8分类数据集的分类任务 (2000个子文件)
img_5356.jpg 249KB
img_5361.jpg 243KB
img_6017.jpg 242KB
img_3337.jpg 241KB
img_3932.jpg 223KB
img_5574.jpg 220KB
img_4106.jpg 218KB
img_4105.jpg 215KB
img_2602_result.jpg 213KB
img_5606.jpg 213KB
img_5230.jpg 208KB
img_5281.jpg 201KB
img_3996.jpg 201KB
img_5580.jpg 200KB
img_4491.jpg 199KB
img_5359.jpg 199KB
img_3565.jpg 189KB
img_5707.jpg 187KB
img_5579.jpg 186KB
img_5601.jpg 186KB
img_2990.jpg 185KB
img_3971.jpg 185KB
img_5590.jpg 184KB
img_3755.jpg 183KB
img_4042.jpg 182KB
img_5571.jpg 181KB
img_3893_result.jpg 181KB
img_5992.jpg 179KB
img_5513.jpg 178KB
img_5568.jpg 177KB
img_4857.jpg 177KB
img_3844.jpg 176KB
img_4346_result.jpg 176KB
img_5596.jpg 175KB
img_2640.jpg 175KB
img_4869.jpg 175KB
img_5244.jpg 174KB
img_6468.jpg 173KB
img_5877.jpg 173KB
img_4062.jpg 173KB
img_3376.jpg 172KB
img_4081.jpg 169KB
img_3791.jpg 168KB
img_4055.jpg 167KB
img_5413.jpg 167KB
img_4940.jpg 167KB
img_5274.jpg 167KB
img_2668.jpg 166KB
img_6329.jpg 165KB
img_6232.jpg 165KB
img_3824.jpg 165KB
img_2590.jpg 164KB
img_2477.jpg 163KB
img_5319.jpg 161KB
img_3401.jpg 160KB
img_2383.jpg 160KB
img_2380.jpg 160KB
img_5551.jpg 160KB
img_4182.jpg 160KB
img_5569.jpg 160KB
img_2460.jpg 159KB
img_3137.jpg 159KB
img_5553.jpg 158KB
img_2369.jpg 158KB
img_3381.jpg 158KB
img_4974.jpg 157KB
img_2653.jpg 155KB
img_4852_result.jpg 155KB
img_6298.jpg 155KB
img_6524.jpg 155KB
img_4989.jpg 155KB
img_4973.jpg 154KB
img_5015.jpg 153KB
img_5583.jpg 153KB
img_4276.jpg 152KB
img_3123.jpg 152KB
img_2778.jpg 151KB
img_5969.jpg 149KB
img_4156.jpg 148KB
img_2208.jpg 148KB
img_6568.jpg 148KB
img_5937.jpg 148KB
img_4770.jpg 147KB
img_5186.jpg 146KB
img_3809.jpg 144KB
img_5007.jpg 144KB
img_5034.jpg 144KB
img_5738.jpg 143KB
img_5202.jpg 143KB
img_5562.jpg 141KB
img_6600.jpg 141KB
img_2306.jpg 140KB
img_2494.jpg 139KB
img_3776.jpg 138KB
img_4675.jpg 138KB
img_4936.jpg 138KB
img_3551.jpg 138KB
img_2777.jpg 138KB
img_2526.jpg 138KB
img_2969.jpg 137KB
共 2000 条
- 1
- 2
- 3
- 4
- 5
- 6
- 20
资源评论
听风吹等浪起
- 粉丝: 1w+
- 资源: 1359
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
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