modules.conv.decnet*¶
Function ยท nn.Module
net = decnet*(
out_size, order=2, kernel_size=3, in_length=2, out_planes=1
)
Instant presents of mdnc.module.conv.DecoderNet*d
.
Arguments¶
Requries
Argument | Type | Description |
---|---|---|
out_size | int or(int,) | The size of the output data. This argument needs to be specified by users, because the network needs to configure its layers according to the output size. |
order | int | The order of the convolutional layers, could be 1 , 2 , or 3 . |
kernel_size | int or(int,) | The kernel size of each convolutional layer. |
in_length | int | The length of the input vector, if not set, the input needs to be feature maps. See the property input_size to check the input data size in this case. |
out_planes | int | The channel number of the output data. |
APIs¶
API | Net depth | Channel | Layer configs | Source |
---|---|---|---|---|
decnet13 | 5 | 64 | [2, 2, 2, 2, 2] | |
decnet16 | 5 | 64 | [3, 3, 2, 2, 2] | |
decnet18 | 5 | 64 | [3, 3, 3, 3, 3] | |
decnet23 | 5 | 64 | [4, 4, 4, 4, 4] |
Last update: March 14, 2021