卷积运算在图像处理中的应用

要在形状27x35使用时渲染图像,请执行以下操作:

random_image = []
for x in range(1 , 946):
        random_image.append(random.randint(0 , 255))

random_image_arr = np.array(random_image)
matplotlib.pyplot.imshow(random_image_arr.reshape(27 , 35))

这将产生:

然后我尝试使用 torch.nn.Conv2d 以下内容:

conv2 = torch.nn.Conv2d(3, 18, kernel_size=3, stride=1, padding=1)

image_d = np.asarray(random_image_arr.reshape(27 , 35))

conv2(torch.from_numpy(image_d))

但这会显示错误:

~/.local/lib/python3.6/site-packages/torch/nn/modules/conv.py in forward(self, input)
    299     def forward(self, input):
    300         return F.conv2d(input, self.weight, self.bias, self.stride,
--> 301                         self.padding, self.dilation, self.groups)
    302 
    303 

RuntimeError: input has less dimensions than expected

输入的形状 image_d 是 (27, 35)

我是否应该更改 Conv2d 为了将卷积应用于图像?

更新。从@mclawrence的回答中我得到了:

随机图像=[]
对于范围(1946)内的x:
random_image.append(random.randint(0,255))

随机图像arr=np.数组(随机图像)
matplotlib.pyplot.imshow(随机图像重组(27,35))

这将渲染图像:

应用卷积运算:

conv2 = torch.nn.Conv2d(1, 18, kernel_size=3, stride=1, padding=1)

image_d = torch.FloatTensor(np.asarray(random_image_arr.reshape(1, 1, 27 , 35))).numpy()

fc = conv2(torch.from_numpy(image_d))

matplotlib.pyplot.imshow(fc[0][0].data.numpy())

渲染图像: