未验证 提交 19f43aa2 编写于 作者: C cuicheng01 提交者: GitHub

Merge pull request #1685 from littletomatodonkey/dev/improve_class_num_dist

improve distillation config
......@@ -18,7 +18,7 @@ Global:
# model architecture
Arch:
name: "DistillationModel"
class_num: 1000
class_num: &class_num 1000
# if not null, its lengths should be same as models
pretrained_list:
# if not null, its lengths should be same as models
......@@ -28,11 +28,13 @@ Arch:
models:
- Teacher:
name: MobileNetV3_large_x1_0
class_num: *class_num
pretrained: True
use_ssld: True
dropout_prob: null
- Student:
name: MobileNetV3_small_x1_0
class_num: *class_num
pretrained: False
dropout_prob: null
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册