mindspore.ops.Conv2D

class mindspore.ops.Conv2D(out_channel, kernel_size, mode=1, pad_mode='valid', pad=0, stride=1, dilation=1, group=1, data_format='NCHW')[source]

2D convolution layer.

Refer to mindspore.ops.conv2d() for more detail.

Supported Platforms:

Ascend GPU CPU

Examples

>>> x = Tensor(np.ones([10, 32, 32, 32]), mindspore.float32)
>>> weight = Tensor(np.ones([32, 32, 3, 3]), mindspore.float32)
>>> conv2d = ops.Conv2D(out_channel=32, kernel_size=3)
>>> output = conv2d(x, weight)
>>> print(output.shape)
(10, 32, 30, 30)