比较与torch.nn.Conv2d的功能差异
torch.nn.Conv2d
torch.nn.Conv2d(
in_channels=120,
out_channels=240,
kernel_size=4,
stride=1,
padding=0,
padding_mode='zeros',
dilation=1,
groups=1,
bias=True
)
更多内容详见torch.nn.Conv2d。
mindspore.nn.Conv2d
class mindspore.nn.Conv2d(
in_channels=120,
out_channels=240,
kernel_size=4,
stride=1,
pad_mode='same',
padding=0,
dilation=1,
group=1,
has_bias=False,
weight_init='normal',
bias_init='zeros',
data_format='NCHW'
)(input_x)
更多内容详见mindspore.nn.Conv2d。
使用方式
PyTorch:默认不对输入进行填充,bias为True。
MindSpore:默认对输入进行填充,使输出与输入维度一致,如果不需要padding,可以将参数设为’valid’。默认has_bias为False。
代码示例
import mindspore as ms
import mindspore.nn as nn
import torch
import numpy as np
# In MindSpore
net = nn.Conv2d(120, 240, 4, stride=2, has_bias=True, weight_init='normal')
x = ms.Tensor(np.ones([1, 120, 1024, 640]), ms.float32)
output = net(x).shape
print(output)
# Out:
# (1, 240, 512, 320)
# In MindSpore
net = nn.Conv2d(120, 240, 4, stride=2, pad_mode='valid', has_bias=True, weight_init='normal')
x = ms.Tensor(np.ones([1, 120, 1024, 640]), ms.float32)
output = net(x).shape
print(output)
# Out:
# (1, 240, 511, 319)
# In PyTorch
m = torch.nn.Conv2d(120, 240, 4, stride=2)
input = torch.rand(1, 120, 1024, 640)
output = m(input)
print(output.shape)
# Out:
# torch.Size([1, 240, 511, 319])