提交 513c45d3 编写于 作者: W wukesong

change lenet&alexnet dir

上级 be2cfa9e
......@@ -148,7 +148,7 @@ In order to facilitate developers to enjoy the benefits of MindSpore framework a
| Loss | 0.108 |
| Params (M) | 61.10 |
| Checkpoint for Fine tuning | 445MB(.ckpt file) |
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/alexnet|
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/alexnet|
#### [LeNet](#table-of-contents)
......@@ -168,7 +168,7 @@ In order to facilitate developers to enjoy the benefits of MindSpore framework a
| Loss | 0.004 |
| Params (M) | 0.06 |
| Checkpoint for Fine tuning | 483KB(.ckpt file) |
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/lenet|
| Scripts | https://gitee.com/mindspore/mindspore/tree/master/model_zoo/official/cv/lenet|
### Object Detection and Segmentation
......
......@@ -29,7 +29,7 @@ def fc_with_initialize(input_channels, out_channels):
return nn.Dense(input_channels, out_channels, weight, bias)
def weight_variable():
return TruncatedNormal(0.02) # 0.02
return TruncatedNormal(0.02)
class AlexNet(nn.Cell):
......
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