版权声明:本文为博主原创文章,未经博主允许不得转载。 https://blog.csdn.net/Arctic_Beacon/article/details/86626259
官网
tensorflow:
https://tensorflow.google.cn/api_docs/python/tf/nn/conv2d
pytorch
https://pytorch.org/docs/master/nn.html?highlight=conv2d#torch.nn.Conv2d
区别如下:
tf.nn.conv2d(
input,
filter,
strides,
padding,
use_cudnn_on_gpu=True,
data_format='NHWC',
dilations=[1, 1, 1, 1],
name=None
)
NHWC 为:[batch, height, width, channels]
torch.nn.
Conv2d
(in_channels, out_channels, kernel_size, stride=1, padding=0, dilation=1, groups=1, bias=True)
In the simplest case, the output value of the layer with input size (N,C,H,W)and output (N,Cout,Hout,Wout)