未验证 提交 ba7657f4 编写于 作者: J Jason 提交者: GitHub

Update tf.nn.conv2d_transpose.md

上级 aceba8e1
...@@ -41,7 +41,7 @@ TensorFlow: 默认输入数据格式为`NHWC`,表示`(batch,height, width, i ...@@ -41,7 +41,7 @@ TensorFlow: 默认输入数据格式为`NHWC`,表示`(batch,height, width, i
| 输入 | 卷积核 | 输出 | | 输入 | 卷积核 | 输出 |
|--------------------|-------------------|------------------| |--------------------|-------------------|------------------|
|NHWC | (kernel_h, kernel_w, filters_num, in_channels)| (batch, out_h, out_w, filters_num)| |NHWC | (kernel_h, kernel_w, filters_num, in_channels)| (batch, out_h, out_w, filters_num)|
|NDHW | (kernel_h, kernel_w, filters_num, in_channels) | (batch, filters_num, out_h, out_w)| |NCHW | (kernel_h, kernel_w, filters_num, in_channels) | (batch, filters_num, out_h, out_w)|
PaddlePaddle:只支持输入数据格式为`NCHW`,且**卷积核格式**与TensorFlow不同,其中输入、输出、卷积核对应关系如下表所示, PaddlePaddle:只支持输入数据格式为`NCHW`,且**卷积核格式**与TensorFlow不同,其中输入、输出、卷积核对应关系如下表所示,
......
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