Pytorch可视化指定层(Udacity)

import cv2
import matplotlib.pyplot as plt
%matplotlib inline

# TODO: Feel free to try out your own images here by changing img_path
# to a file path to another image on your computer!
img_path = 'images/udacity_sdc.png'

# load color image
bgr_img = cv2.imread(img_path)
# convert to grayscale
gray_img = cv2.cvtColor(bgr_img, cv2.COLOR_BGR2GRAY)

# normalize, rescale entries to lie in [0,1]
gray_img = gray_img.astype("float32")/255

# plot image
plt.imshow(gray_img, cmap='gray')
plt.show()

显示图像

定义滤波器，并将其可视化

import numpy as np

## TODO: Feel free to modify the numbers here, to try out another filter!
filter_vals = np.array([[-1, -1, 1, 1], [-1, -1, 1, 1], [-1, -1, 1, 1], [-1, -1, 1, 1]])

print('Filter shape: ', filter_vals.shape)

Filter shape:  (4, 4)

# Defining four different filters,
# all of which are linear combinations of the `filter_vals` defined above

# define four filters
filter_1 = filter_vals
filter_2 = -filter_1
filter_3 = filter_1.T
filter_4 = -filter_3
filters = np.array([filter_1, filter_2, filter_3, filter_4])

# For an example, print out the values of filter 1
print('Filter 1: \n', filter_1)

Filter 1: [[-1 -1 1 1] [-1 -1 1 1] [-1 -1 1 1] [-1 -1 1 1]]

定义卷积层和池化层¶

将卷积层初始化，使其包含你所创建的所有滤波器。然后添加一个最大池化层（相关文档请通过点击这里查阅），内核大小为（4x4），这样你就可以看到，在这一步之后，图像分辨率已经降低了！

import torch
import torch.nn as nn
import torch.nn.functional as F

# define a neural network with a convolutional layer with four filters
# AND a pooling layer of size (4, 4)
class Net(nn.Module):

    def __init__(self, weight):
        super(Net, self).__init__()
        # initializes the weights of the convolutional layer to be the weights of the 4 defined filters
        k_height, k_width = weight.shape[2:]
        # assumes there are 4 grayscale filters
        self.conv = nn.Conv2d(1, 4, kernel_size=(k_height, k_width), bias=False)
        self.conv.weight = torch.nn.Parameter(weight)
        # define a pooling layer
        self.pool = nn.MaxPool2d(4, 4)

    def forward(self, x):
        # calculates the output of a convolutional layer
        # pre- and post-activation
        conv_x = self.conv(x)
        activated_x = F.relu(conv_x)

        # applies pooling layer
        pooled_x = self.pool(activated_x)

        # returns all layers
        return conv_x, activated_x, pooled_x

# instantiate the model and set the weights
weight = torch.from_numpy(filters).unsqueeze(1).type(torch.FloatTensor)
model = Net(weight)

# print out the layer in the network
print(model)

Net(
  (conv): Conv2d(1, 4, kernel_size=(4, 4), stride=(1, 1), bias=False)
  (pool): MaxPool2d(kernel_size=4, stride=4, padding=0, dilation=1, ceil_mode=False)
)

将每个滤波器的输出可视化

首先，我们将定义一个辅助函数viz_layer，它会接收一个特定的层和多个滤波器（可选参数）作为输入，并在图像通过后显示该层的输出。

# helper function for visualizing the output of a given layer
# default number of filters is 4
def viz_layer(layer, n_filters= 4):
    fig = plt.figure(figsize=(20, 20))

    for i in range(n_filters):
        ax = fig.add_subplot(1, n_filters, i+1, xticks=[], yticks=[])
        # grab layer outputs
        ax.imshow(np.squeeze(layer[0,i].data.numpy()), cmap='gray')
        ax.set_title('Output %s' % str(i+1))

让我们看一下应用ReLu激活函数后，该卷积层的输出是什么。

# plot original image
plt.imshow(gray_img, cmap='gray')

# visualize all filters
fig = plt.figure(figsize=(12, 6))
fig.subplots_adjust(left=0, right=1.5, bottom=0.8, top=1, hspace=0.05, wspace=0.05)
for i in range(4):
    ax = fig.add_subplot(1, 4, i+1, xticks=[], yticks=[])
    ax.imshow(filters[i], cmap='gray')
    ax.set_title('Filter %s' % str(i+1))

# convert the image into an input Tensor
gray_img_tensor = torch.from_numpy(gray_img).unsqueeze(0).unsqueeze(1)

# get all the layers
conv_layer, activated_layer, pooled_layer = model(gray_img_tensor)

# visualize the output of the activated conv layer
viz_layer(activated_layer)

将池化层的输出可视化

然后，看一下池化层的输出。池化层将上面描绘的特征映射图作为输入，并通过一些池化因子，通过在一个给定内核区域中构造一个仅拥有最大（即最亮）值的新的较小图像来减少那些映射图的维度。

# visualize the output of the pooling layer
viz_layer(pooled_layer)