python - PyTorch 中的高斯滤波器

Question

我正在寻找一种仅使用 PyTorch 函数将高斯滤波器应用于图像(张量)的方法。使用numpy，等价的代码是

import numpy as np
from scipy import signal
import matplotlib.pyplot as plt

# Define 2D Gaussian kernel
def gkern(kernlen=256, std=128):
    """Returns a 2D Gaussian kernel array."""
    gkern1d = signal.gaussian(kernlen, std=std).reshape(kernlen, 1)
    gkern2d = np.outer(gkern1d, gkern1d)
    return gkern2d

# Generate random matrix and multiply the kernel by it
A = np.random.rand(256*256).reshape([256,256])

# Test plot
plt.figure()
plt.imshow(A*gkern(256, std=32))
plt.show()

我发现的最接近的建议是基于 this post :

import torch.nn as nn

conv = nn.Conv2d(in_channels = 1, out_channels = 1, kernel_size=264, bias=False)
with torch.no_grad():
    conv.weight = gaussian_weights

但它给了我错误 NameError: name 'gaussian_weights' is not defined .我怎样才能让它工作？

Answer 1

Yupp I also had the same idea. So now the question becomes: is there a way to define a Gaussian kernel (or a 2D Gaussian) without using Numpy and/or explicitly specifying the weights?

是的，这很容易。看看 signal.gaussian的函数文档就知道了.有一个链接到 source code .所以该方法正在做的是以下内容:

def gaussian(M, std, sym=True):
    if M < 1:
        return np.array([])
    if M == 1:
        return np.ones(1, 'd')
    odd = M % 2
    if not sym and not odd:
        M = M + 1
    n = np.arange(0, M) - (M - 1.0) / 2.0
    sig2 = 2 * std * std
    w = np.exp(-n ** 2 / sig2)
    if not sym and not odd:
        w = w[:-1]
    return w

你很幸运，因为在 Pytorch 中转换很简单，(几乎)只是替换 np来自 torch你就完成了!
另外，请注意 np.outer火炬中的等效项是 ger .