# TORCH.NN.FUNCTIONAL.CONV2D
# torch.nn.functional.conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1) → Tensor
# 名词解释：
# input: input tensor of shape (minibatch,in_channels,iH,iW) minibatch也就是最小的批量大小，
# in_channels为卷积的图片来源个数
# out_channels 为卷积核的个数
# iH 和 iW 是图片高度和宽度
# weight filters of shape (out_channels,in_channels/groups,kH,kW) 卷积大小，第二个参数的groups一般为1
# stride 步幅默认为1
# padding 在每一边都填充 默认为0
import torch
import torch.nn.functional as F
input = torch.tensor([[1,2,0,3,1],
[0,1,2,3,1],
[1,2,1,0,0],
[5,2,3,1,1],
[2,1,0,1,1]])
# 卷积核
kernel = torch.tensor([[1,2,1],
[0,1,0],
[2,1,0]])
input = torch.reshape(input,[1,1,5,5])
kernel = torch.reshape(kernel,[1,1,3,3])
#为什么要转变shape，因为functional的tensor格式为（x,x,x,x）
print(input.shape)
print(kernel.shape)
# 结果：
# torch.Size([5, 5])
# torch.Size([3, 3])
# 经过torch.reshape之后结果为：
# torch.Size([1, 1, 5, 5])
# torch.Size([1, 1, 3, 3])
output = F.conv2d(input,kernel,stride=1)
print(output)
# tensor([[[[10, 12, 12],
# [18, 16, 16],
# [13, 9, 3]]]])
output2 = F.conv2d(input,kernel,stride=2)
print(output2)
# tensor([[[[10, 12],
# [13, 3]]]])
output3 = F.conv2d(input,kernel,stride=1,padding=1)
print(output3)
# tensor([[[[ 1, 3, 4, 10, 8],
# [ 5, 10, 12, 12, 6],
# [ 7, 18, 16, 16, 8],
# [11, 13, 9, 3, 4],
# [14, 13, 9, 7, 4]]]])
