@@ -1115,7 +1115,7 @@ def conv3d(x,
1115
1115
Args:
1116
1116
x (Tensor): The input is 5-D Tensor with shape [N, C, D, H, W], the data
1117
1117
type of input is float16 or float32 or float64.
1118
- weight (Variable ): The convolution kernel, a Tensor with shape [M, C/g, kD, kH, kW],
1118
+ weight (Tensor ): The convolution kernel, a Tensor with shape [M, C/g, kD, kH, kW],
1119
1119
where M is the number of filters(output channels), g is the number of groups,
1120
1120
kD, kH, kW are the filter's depth, height and width respectively.
1121
1121
bias (Tensor, optional): The bias, a Tensor of shape [M, ].
@@ -1151,22 +1151,10 @@ def conv3d(x,
1151
1151
1152
1152
Returns:
1153
1153
A Tensor representing the conv3d, whose data type is
1154
- the same with input. If act is None, the tensor variable storing the
1155
- convolution result, and if act is not None, the tensor variable storing
1154
+ the same with input. If act is None, the tensor storing the
1155
+ convolution result, and if act is not None, the tensor storing
1156
1156
convolution and non-linearity activation result.
1157
1157
1158
- Raises:
1159
- ValueError: If `data_format` is not "NCDHW" or "NDHWC".
1160
- ValueError: If the channel dimension of the input is less than or equal to zero.
1161
- ValueError: If `padding` is a string, but not "SAME" or "VALID".
1162
- ValueError: If `padding` is a tuple, but the element corresponding to the input's batch size is not 0
1163
- or the element corresponding to the input's channel is not 0.
1164
- ShapeError: If the input is not 5-D Tensor.
1165
- ShapeError: If the input's dimension size and filter's dimension size not equal.
1166
- ShapeError: If the dimension size of input minus the size of `stride` is not 2.
1167
- ShapeError: If the number of input channels is not equal to filter's channels * groups.
1168
- ShapeError: If the number of output channels is not be divided by groups.
1169
-
1170
1158
Examples:
1171
1159
.. code-block:: python
1172
1160
0 commit comments