池化:对不同位置的特征进行聚合统计称为池化.目的就是减少特征,降低了信息输出的维度.
import skimage.data
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
import numpycnn
# 读取图像
img = skimage.data.chelsea()
# 转成灰度图像
img = skimage.color.rgb2gray(img)
# 初始化卷积核
l1_filter = np.zeros((2, 3, 3))
# 检测垂直边缘
l1_filter[0, :, :] = np.array([[[-1, 0, 1], [-1, 0, 1], [-1, 0, 1]]])
# 检测水平边缘
l1_filter[1, :, :] = np.array([[[1, 1, 1], [0, 0, 0], [-1, -1, -1]]])
"""
第一个卷积层
"""
# 卷积操作
l1_feature_map = numpycnn.conv(img, l1_filter)
# ReLU
l1_feature_map_relu = numpycnn.relu(l1_feature_map)
# Pooling
l1_feature_map_relu_pool = numpycnn.pooling(l1_feature_map_relu, 2, 2)
"""
第二个卷积层
"""
# 初始化卷积核
l2_filter = np.random.rand(3, 5, 5, l1_feature_map_relu_pool.shape[-1])
# 卷积操作
l2_feature_map = numpycnn.conv(l1_feature_map_relu_pool, l2_filter)
# ReLU
l2_feature_map_relu = numpycnn.relu(l2_feature_map)
# Pooling
l2_feature_map_relu_pool = numpycnn.pooling(l2_feature_map_relu, 2, 2)
"""
第三个卷积层
"""
# 初始化卷积核
l3_filter = np.random.rand(1, 7, 7, l2_feature_map_relu_pool.shape[-1])
# 卷积操作
l3_feature_map = numpycnn.conv(l2_feature_map_relu_pool, l3_filter)
# ReLU
l3_feature_map_relu = numpycnn.relu(l3_feature_map)
# Pooling
l3_feature_map_relu_pool = numpycnn.pooling(l3_feature_map_relu, 2, 2)
"""
结果可视化
"""
fig0, ax0 = plt.subplots(nrows=1, ncols=1)
ax0.imshow(img).set_cmap("gray")
ax0.set_title("Input Image")
ax0.get_xaxis().set_ticks([])
ax0.get_yaxis().set_ticks([])
plt.show()
plt.savefig("in_img1.png", bbox_inches="tight")
plt.close(fig0)
# 第一层
fig1, ax1 = plt.subplots(nrows=3, ncols=2)
ax1[0, 0].imshow(l1_feature_map[:, :, 0]).set_cmap("gray")
ax1[0, 0].get_xaxis().set_ticks([])
ax1[0, 0].get_yaxis().set_ticks([])
ax1[0, 0].set_title("L1-Map1")
ax1[0, 1].imshow(l1_feature_map[:, :, 1]).set_cmap("gray")
ax1[0, 1].get_xaxis().set_ticks([])
ax1[0, 1].get_yaxis().set_ticks([])
ax1[0, 1].set_title("L1-Map2")
ax1[1, 0].imshow(l1_feature_map_relu[:, :, 0]).set_cmap("gray")
ax1[1, 0].get_xaxis().set_ticks([])
ax1[1, 0].get_yaxis().set_ticks([])
ax1[1, 0].set_title("L1-Map1ReLU")
ax1[1, 1].imshow(l1_feature_map_relu[:, :, 1]).set_cmap("gray")
ax1[1, 1].get_xaxis().set_ticks([])
ax1[1, 1].get_yaxis().set_ticks([])
ax1[1, 1].set_title("L1-Map2ReLU")
ax1[2, 0].imshow(l1_feature_map_relu_pool[:, :, 0]).set_cmap("gray")
ax1[2, 0].get_xaxis().set_ticks([])
ax1[2, 0].get_yaxis().set_ticks([])
ax1[2, 0].set_title("L1-Map1ReLUPool")
ax1[2, 1].imshow(l1_feature_map_relu_pool[:, :, 1]).set_cmap("gray")
ax1[2, 0].get_xaxis().set_ticks([])
ax1[2, 0].get_yaxis().set_ticks([])
ax1[2, 1].set_title("L1-Map2ReLUPool")
plt.show()
plt.savefig("L1.png", bbox_inches="tight")
plt.close(fig1)
# 第二层
fig2, ax2 = plt.subplots(nrows=3, ncols=3)
ax2[0, 0].imshow(l2_feature_map[:, :, 0]).set_cmap("gray")
ax2[0, 0].get_xaxis().set_ticks([])
ax2[0, 0].get_yaxis().set_ticks([])
ax2[0, 0].set_title("L2-Map1")
ax2[0, 1].imshow(l2_feature_map[:, :, 1]).set_cmap("gray")
ax2[0, 1].get_xaxis().set_ticks([])
ax2[0, 1].get_yaxis().set_ticks([])
ax2[0, 1].set_title("L2-Map2")
ax2[0, 2].imshow(l2_feature_map[:, :, 2]).set_cmap("gray")
ax2[0, 2].get_xaxis().set_ticks([])
ax2[0, 2].get_yaxis().set_ticks([])
ax2[0, 2].set_title("L2-Map3")
ax2[1, 0].imshow(l2_feature_map_relu[:, :, 0]).set_cmap("gray")
ax2[1, 0].get_xaxis().set_ticks([])
ax2[1, 0].get_yaxis().set_ticks([])
ax2[1, 0].set_title("L2-Map1ReLU")
ax2[1, 1].imshow(l2_feature_map_relu[:, :, 1]).set_cmap("gray")
ax2[1, 1].get_xaxis().set_ticks([])
ax2[1, 1].get_yaxis().set_ticks([])
ax2[1, 1].set_title("L2-Map2ReLU")
ax2[1, 2].imshow(l2_feature_map_relu[:, :, 2]).set_cmap("gray")
ax2[1, 2].get_xaxis().set_ticks([])
ax2[1, 2].get_yaxis().set_ticks([])
ax2[1, 2].set_title("L2-Map3ReLU")
ax2[2, 0].imshow(l2_feature_map_relu_pool[:, :, 0]).set_cmap("gray")
ax2[2, 0].get_xaxis().set_ticks([])
ax2[2, 0].get_yaxis().set_ticks([])
ax2[2, 0].set_title("L2-Map1ReLUPool")
ax2[2, 1].imshow(l2_feature_map_relu_pool[:, :, 1]).set_cmap("gray")
ax2[2, 1].get_xaxis().set_ticks([])
ax2[2, 1].get_yaxis().set_ticks([])
ax2[2, 1].set_title("L2-Map2ReLUPool")
ax2[2, 2].imshow(l2_feature_map_relu_pool[:, :, 2]).set_cmap("gray")
ax2[2, 2].get_xaxis().set_ticks([])
ax2[2, 2].get_yaxis().set_ticks([])
ax2[2, 2].set_title("L2-Map3ReLUPool")
plt.show()
plt.savefig("L2.png", bbox_inches="tight")
plt.close(fig2)
# 第三层
fig3, ax3 = plt.subplots(nrows=1, ncols=3)
ax3[0].imshow(l3_feature_map[:, :, 0]).set_cmap("gray")
ax3[0].get_xaxis().set_ticks([])
ax3[0].get_yaxis().set_ticks([])
ax3[0].set_title("L3-Map1")
ax3[1].imshow(l3_feature_map_relu[:, :, 0]).set_cmap("gray")
ax3[1].get_xaxis().set_ticks([])
ax3[1].get_yaxis().set_ticks([])
ax3[1].set_title("L3-Map1ReLU")
ax3[2].imshow(l3_feature_map_relu_pool[:, :, 0]).set_cmap("gray")
ax3[2].get_xaxis().set_ticks([])
ax3[2].get_yaxis().set_ticks([])
ax3[2].set_title("L3-Map1ReLUPool")
plt.show()
plt.savefig("L3.png", bbox_inches="tight")
plt.close(fig3)