如何在mmcls的基础上构造一维卷积神经网络? #1088
-
我已试图查询该问题
描述该问题我再、准备修改mmcls中的EfficientNet的时候,发现构造的卷积使用的是from mmcv.cnn.bricks import ConvModule,但是ConvModule无法控制是1维卷积还是2维卷积,请问应该如何处理呢? |
Beta Was this translation helpful? Give feedback.
Replies: 5 comments
-
We recommend using English or English & Chinese for issues so that we could have broader discussion. |
Beta Was this translation helpful? Give feedback.
-
是只输入的图片不是rgb 3通道图片,只有一个通道,类似灰度图这种吗? |
Beta Was this translation helpful? Give feedback.
-
不是的,我是想把efficient网络改成可以输入一个序列的,就是一个一维向量,然后网络里面应该用的是conv1d,但是我没找到mmcls里面构造网络时用的conv2d在哪里?mmcls里面构造时用的是from mmcv.cnn.bricks import ConvModule,但是一个卷积模型无法设置为1d卷积 |
Beta Was this translation helpful? Give feedback.
-
try:
|
Beta Was this translation helpful? Give feedback.
-
好的,非常感谢帮忙 |
Beta Was this translation helpful? Give feedback.
try: