基于深度可分离卷积网络的皮肤镜图像病灶分割方法
|
|
崔文成, 张鹏霞, 邵虹
|
Dermoscopic image lesion segmentation method based on deep separable convolutional network
|
|
Wencheng CUI, Pengxia ZHANG, Hong SHAO
|
|
表1 参数调优
|
| |
|
| 对比项 | | Epoch | | | 10 | 20 | 40 | | Batchsize=4 | train_ac = 86.71% | train_ac = 90.52% | train_ac = 92.54% | | Lr=0.01 | test_ac = 85.04% | test_ac = 88.03% | test_ac = 90.45% | | Batchsize=4 | train_ac = 89.45% | train_ac = 92.14% | train_ac = 94.65% | | Lr=0.05 | test_ac = 87.60% | test_ac = 91.03% | test_ac = 92.96% | | Batchsize=8 | train_ac =83.04 % | train_ac = 85.94% | train_ac = 90.81% | | Lr=0.01 | test_ac = 80.60% | test_ac = 84.36% | test_ac = 89.23% | | Batchsize=8 | train_ac = 84.57% | train_ac = 92.24% | train_ac = 95.24% | | Lr=0.05 | test_ac = 83.04% | test_ac = 90.82% | test_ac = 93.82% |
|
|
|