卷积、下采样、经典卷积网络
1. 对图像进行卷积处理
import cv2 path = 'data\instance\p67.jpg' input_img = cv2.imread(path)
import cv2 import numpy as np #分别将三个通道进行卷积,然后合并通道 def conv(image, kernel): conv_b = convolve(image[:, :, 0], kernel) conv_g = convolve(image[:, :, 1], kernel) conv_r = convolve(image[:, :, 2], kernel) output = np.dstack([conv_b, conv_g, conv_r]) return output #卷积处理 def convolve(image, kernel): h_kernel, w_kernel = kernel.shape h_image, w_image = image.shape h_output = h_image - h_kernel + 1 w_output = w_image - w_kernel + 1 output = np.zeros((h_output, w_output), np.uint8) for i in range(h_output): for j in range(w_output): output[i, j] = np.multiply(image[i:i + h_kernel, j:j + w_kernel], kernel).sum() return output if __name__ == '__main__': path = 'data\instance\p67.jpg' input_img = cv2.imread(path) # 1.锐化卷积核 #kernel = np.array([[-1,-1,-1],[-1,9,-1],[-1,-1,-1]]) # 2.模糊卷积核 kernel = np.array([[0.1,0.1,0.1],[0.1,0.2,0.1],[0.1,0.1,0.1]]) output_img = conv(input_img, kernel) cv2.imwrite(path.replace('.jpg', '-processed.jpg'), output_img) cv2.imshow('Output Image', output_img) cv2.waitKey(0)
2. 池化
img = cv2.imread('data\instance\dog.jpg') img.shape
(4064, 3216, 3)
import numpy as np from PIL import Image import cv2 import matplotlib.pyplot as plt #均值池化 def AVGpooling(imgData, strdW, strdH): W,H = imgData.shape newImg = [] for i in range(0,W,strdW): line = [] for j in range(0,H,strdH): x = imgData[i:i+strdW,j:j+strdH] #获取当前待池化区域 avgValue=np.sum(x)/(strdW*strdH) #求该区域的均值 line.append(avgValue) newImg.append(line) return np.array(newImg) #最大池化 def MAXpooling(imgData, strdW, strdH): W,H = imgData.shape newImg = [] for i in range(0,W,strdW): line = [] for j in range(0,H,strdH): x = imgData[i:i+strdW,j:j+strdH] #获取当前待池化区域 maxValue=np.max(x) #求该区域的最大值 line.append(maxValue) newImg.append(line) return np.array(newImg) img = cv2.imread('data\instance\dog.jpg') imgData= img[:,:,1] #绿色通道 #显示原图 plt.subplot(221) plt.imshow(img) plt.axis('off') #显示原始绿通道图 plt.subplot(222) plt.imshow(imgData) plt.axis('off') #显示平均池化结果图 AVGimg = AVGpooling(imgData, 2, 2) plt.subplot(223) plt.imshow(AVGimg) plt.axis('off') #显示最大池化结果图 MAXimg = MAXpooling(imgData, 2, 2) plt.subplot(224) plt.imshow(MAXimg) plt.axis('off') plt.show()
3. VGGNET
import numpy as np from tensorflow.keras import backend as K import matplotlib.pyplot as plt from tensorflow.keras.applications import vgg16 # Keras内置 VGG-16模块,直接可调用。 from tensorflow.keras.preprocessing import image from tensorflow.keras.applications.vgg16 import preprocess_input import math input_size = 224 # 网络输入图像的大小,长宽相等 kernel_size = 64 # 可视化卷积核的大小,长宽相等 layer_vis = True # 特征图是否可视化 kernel_vis = True # 卷积核是否可视化 each_layer = False # 卷积核可视化是否每层都做 which_layer = 1 # 如果不是每层都做,那么第几个卷积层 path = 'data\instance\p67.jpg' img = image.load_img(path, target_size=(input_size, input_size)) img = image.img_to_array(img) img = np.expand_dims(img, axis=0) img = preprocess_input(img) #标准化预处理 model = vgg16.VGG16(include_top=True, weights='imagenet') def network_configuration(): all_channels = [64, 64, 64, 128, 128, 128, 256, 256, 256, 256, 512, 512, 512, 512, 512, 512, 512, 512] down_sampling = [1, 1, 1 / 2, 1 / 2, 1 / 2, 1 / 4, 1 / 4, 1 / 4, 1 / 4, 1 / 8, 1 / 8, 1 / 8, 1 / 8, 1 / 16, 1 / 16, 1 / 16, 1 / 16, 1 / 32] conv_layers = [1, 2, 4, 5, 7, 8, 9, 11, 12, 13, 15, 16, 17] conv_channels = [64, 64, 128, 128, 256, 256, 256, 512, 512, 512, 512, 512, 512] return all_channels, down_sampling, conv_layers, conv_channels def layer_visualization(model, img, layer_num, channel, ds): # 设置可视化的层 layer = K.function([model.layers[0].input], [model.layers[layer_num].output]) f = layer([img])[0] feature_aspect = math.ceil(math.sqrt(channel)) single_size = int(input_size * ds) plt.figure(figsize=(8, 8.5)) plt.suptitle('Layer-' + str(layer_num), fontsize=22) plt.subplots_adjust(left=0.02, bottom=0.02, right=0.98, top=0.94, wspace=0.05, hspace=0.05) for i_channel in range(channel): print('Channel-{} in Layer-{} is running.'.format(i_channel + 1, layer_num)) show_img = f[:, :, :, i_channel] show_img = np.reshape(show_img, (single_size, single_size)) plt.subplot(feature_aspect, feature_aspect, i_channel + 1) plt.imshow(show_img) plt.axis('off') fig = plt.gcf() fig.savefig('data/instance/feature_kernel_images/layer_' + str(layer_num).zfill(2) + '.png', format='png', dpi=300) plt.show() all_channels, down_sampling, conv_layers, conv_channels = network_configuration() if layer_vis: for i in range(len(all_channels)): layer_visualization(model, img, i + 1, all_channels[i], down_sampling[i])
4. 采用预训练的Resnet实现猫狗识别
from tensorflow.keras.applications.resnet50 import ResNet50 from tensorflow.keras.preprocessing import image from tensorflow.keras.applications.resnet50 import preprocess_input, decode_predictions import numpy as np from PIL import ImageFont, ImageDraw, Image import cv2
img_path = 'data\instance\dog.jpg' #进行狗的判断 #img_path = 'cat.jpg' #进行猫的判断 #img_path = 'deer.jpg' #进行鹿的判断
weights_path = 'resnet50_weights.h5'
img = image.load_img(img_path, target_size=(224, 224)) x = image.img_to_array(img) x = np.expand_dims(x, axis=0) x = preprocess_input(x)
def get_model(): model = ResNet50(weights=weights_path) # 导入模型以及预训练权重 print(model.summary()) # 打印模型概况 return model model = get_model()
Model: "resnet50" __________________________________________________________________________________________________ Layer (type) Output Shape Param # Connected to ================================================================================================== input_4 (InputLayer) [(None, 224, 224, 3 0 [] )] conv1_pad (ZeroPadding2D) (None, 230, 230, 3) 0 ['input_4[0][0]'] conv1_conv (Conv2D) (None, 112, 112, 64 9472 ['conv1_pad[0][0]'] ) conv1_bn (BatchNormalization) (None, 112, 112, 64 256 ['conv1_conv[0][0]'] ) conv1_relu (Activation) (None, 112, 112, 64 0 ['conv1_bn[0][0]'] ) pool1_pad (ZeroPadding2D) (None, 114, 114, 64 0 ['conv1_relu[0][0]'] ) pool1_pool (MaxPooling2D) (None, 56, 56, 64) 0 ['pool1_pad[0][0]'] conv2_block1_1_conv (Conv2D) (None, 56, 56, 64) 4160 ['pool1_pool[0][0]'] conv2_block1_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block1_1_conv[0][0]'] ization) conv2_block1_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block1_1_bn[0][0]'] n) conv2_block1_2_conv (Conv2D) (None, 56, 56, 64) 36928 ['conv2_block1_1_relu[0][0]'] conv2_block1_2_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block1_2_conv[0][0]'] ization) conv2_block1_2_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block1_2_bn[0][0]'] n) conv2_block1_0_conv (Conv2D) (None, 56, 56, 256) 16640 ['pool1_pool[0][0]'] conv2_block1_3_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block1_2_relu[0][0]'] conv2_block1_0_bn (BatchNormal (None, 56, 56, 256) 1024 ['conv2_block1_0_conv[0][0]'] ization) conv2_block1_3_bn (BatchNormal (None, 56, 56, 256) 1024 ['conv2_block1_3_conv[0][0]'] ization) conv2_block1_add (Add) (None, 56, 56, 256) 0 ['conv2_block1_0_bn[0][0]', 'conv2_block1_3_bn[0][0]'] conv2_block1_out (Activation) (None, 56, 56, 256) 0 ['conv2_block1_add[0][0]'] conv2_block2_1_conv (Conv2D) (None, 56, 56, 64) 16448 ['conv2_block1_out[0][0]'] conv2_block2_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block2_1_conv[0][0]'] ization) conv2_block2_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block2_1_bn[0][0]'] n) conv2_block2_2_conv (Conv2D) (None, 56, 56, 64) 36928 ['conv2_block2_1_relu[0][0]'] conv2_block2_2_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block2_2_conv[0][0]'] ization) conv2_block2_2_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block2_2_bn[0][0]'] n) conv2_block2_3_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block2_2_relu[0][0]'] conv2_block2_3_bn (BatchNormal (None, 56, 56, 256) 1024 ['conv2_block2_3_conv[0][0]'] ization) conv2_block2_add (Add) (None, 56, 56, 256) 0 ['conv2_block1_out[0][0]', 'conv2_block2_3_bn[0][0]'] conv2_block2_out (Activation) (None, 56, 56, 256) 0 ['conv2_block2_add[0][0]'] conv2_block3_1_conv (Conv2D) (None, 56, 56, 64) 16448 ['conv2_block2_out[0][0]'] conv2_block3_1_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block3_1_conv[0][0]'] ization) conv2_block3_1_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block3_1_bn[0][0]'] n) conv2_block3_2_conv (Conv2D) (None, 56, 56, 64) 36928 ['conv2_block3_1_relu[0][0]'] conv2_block3_2_bn (BatchNormal (None, 56, 56, 64) 256 ['conv2_block3_2_conv[0][0]'] ization) conv2_block3_2_relu (Activatio (None, 56, 56, 64) 0 ['conv2_block3_2_bn[0][0]'] n) conv2_block3_3_conv (Conv2D) (None, 56, 56, 256) 16640 ['conv2_block3_2_relu[0][0]'] conv2_block3_3_bn (BatchNormal (None, 56, 56, 256) 1024 ['conv2_block3_3_conv[0][0]'] ization) conv2_block3_add (Add) (None, 56, 56, 256) 0 ['conv2_block2_out[0][0]', 'conv2_block3_3_bn[0][0]'] conv2_block3_out (Activation) (None, 56, 56, 256) 0 ['conv2_block3_add[0][0]'] conv3_block1_1_conv (Conv2D) (None, 28, 28, 128) 32896 ['conv2_block3_out[0][0]'] conv3_block1_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block1_1_conv[0][0]'] ization) conv3_block1_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block1_1_bn[0][0]'] n) conv3_block1_2_conv (Conv2D) (None, 28, 28, 128) 147584 ['conv3_block1_1_relu[0][0]'] conv3_block1_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block1_2_conv[0][0]'] ization) conv3_block1_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block1_2_bn[0][0]'] n) conv3_block1_0_conv (Conv2D) (None, 28, 28, 512) 131584 ['conv2_block3_out[0][0]'] conv3_block1_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block1_2_relu[0][0]'] conv3_block1_0_bn (BatchNormal (None, 28, 28, 512) 2048 ['conv3_block1_0_conv[0][0]'] ization) conv3_block1_3_bn (BatchNormal (None, 28, 28, 512) 2048 ['conv3_block1_3_conv[0][0]'] ization) conv3_block1_add (Add) (None, 28, 28, 512) 0 ['conv3_block1_0_bn[0][0]', 'conv3_block1_3_bn[0][0]'] conv3_block1_out (Activation) (None, 28, 28, 512) 0 ['conv3_block1_add[0][0]'] conv3_block2_1_conv (Conv2D) (None, 28, 28, 128) 65664 ['conv3_block1_out[0][0]'] conv3_block2_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block2_1_conv[0][0]'] ization) conv3_block2_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block2_1_bn[0][0]'] n) conv3_block2_2_conv (Conv2D) (None, 28, 28, 128) 147584 ['conv3_block2_1_relu[0][0]'] conv3_block2_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block2_2_conv[0][0]'] ization) conv3_block2_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block2_2_bn[0][0]'] n) conv3_block2_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block2_2_relu[0][0]'] conv3_block2_3_bn (BatchNormal (None, 28, 28, 512) 2048 ['conv3_block2_3_conv[0][0]'] ization) conv3_block2_add (Add) (None, 28, 28, 512) 0 ['conv3_block1_out[0][0]', 'conv3_block2_3_bn[0][0]'] conv3_block2_out (Activation) (None, 28, 28, 512) 0 ['conv3_block2_add[0][0]'] conv3_block3_1_conv (Conv2D) (None, 28, 28, 128) 65664 ['conv3_block2_out[0][0]'] conv3_block3_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block3_1_conv[0][0]'] ization) conv3_block3_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block3_1_bn[0][0]'] n) conv3_block3_2_conv (Conv2D) (None, 28, 28, 128) 147584 ['conv3_block3_1_relu[0][0]'] conv3_block3_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block3_2_conv[0][0]'] ization) conv3_block3_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block3_2_bn[0][0]'] n) conv3_block3_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block3_2_relu[0][0]'] conv3_block3_3_bn (BatchNormal (None, 28, 28, 512) 2048 ['conv3_block3_3_conv[0][0]'] ization) conv3_block3_add (Add) (None, 28, 28, 512) 0 ['conv3_block2_out[0][0]', 'conv3_block3_3_bn[0][0]'] conv3_block3_out (Activation) (None, 28, 28, 512) 0 ['conv3_block3_add[0][0]'] conv3_block4_1_conv (Conv2D) (None, 28, 28, 128) 65664 ['conv3_block3_out[0][0]'] conv3_block4_1_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block4_1_conv[0][0]'] ization) conv3_block4_1_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block4_1_bn[0][0]'] n) conv3_block4_2_conv (Conv2D) (None, 28, 28, 128) 147584 ['conv3_block4_1_relu[0][0]'] conv3_block4_2_bn (BatchNormal (None, 28, 28, 128) 512 ['conv3_block4_2_conv[0][0]'] ization) conv3_block4_2_relu (Activatio (None, 28, 28, 128) 0 ['conv3_block4_2_bn[0][0]'] n) conv3_block4_3_conv (Conv2D) (None, 28, 28, 512) 66048 ['conv3_block4_2_relu[0][0]'] conv3_block4_3_bn (BatchNormal (None, 28, 28, 512) 2048 ['conv3_block4_3_conv[0][0]'] ization) conv3_block4_add (Add) (None, 28, 28, 512) 0 ['conv3_block3_out[0][0]', 'conv3_block4_3_bn[0][0]'] conv3_block4_out (Activation) (None, 28, 28, 512) 0 ['conv3_block4_add[0][0]'] conv4_block1_1_conv (Conv2D) (None, 14, 14, 256) 131328 ['conv3_block4_out[0][0]'] conv4_block1_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block1_1_conv[0][0]'] ization) conv4_block1_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block1_1_bn[0][0]'] n) conv4_block1_2_conv (Conv2D) (None, 14, 14, 256) 590080 ['conv4_block1_1_relu[0][0]'] conv4_block1_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block1_2_conv[0][0]'] ization) conv4_block1_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block1_2_bn[0][0]'] n) conv4_block1_0_conv (Conv2D) (None, 14, 14, 1024 525312 ['conv3_block4_out[0][0]'] ) conv4_block1_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block1_2_relu[0][0]'] ) conv4_block1_0_bn (BatchNormal (None, 14, 14, 1024 4096 ['conv4_block1_0_conv[0][0]'] ization) ) conv4_block1_3_bn (BatchNormal (None, 14, 14, 1024 4096 ['conv4_block1_3_conv[0][0]'] ization) ) conv4_block1_add (Add) (None, 14, 14, 1024 0 ['conv4_block1_0_bn[0][0]', ) 'conv4_block1_3_bn[0][0]'] conv4_block1_out (Activation) (None, 14, 14, 1024 0 ['conv4_block1_add[0][0]'] ) conv4_block2_1_conv (Conv2D) (None, 14, 14, 256) 262400 ['conv4_block1_out[0][0]'] conv4_block2_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block2_1_conv[0][0]'] ization) conv4_block2_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block2_1_bn[0][0]'] n) conv4_block2_2_conv (Conv2D) (None, 14, 14, 256) 590080 ['conv4_block2_1_relu[0][0]'] conv4_block2_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block2_2_conv[0][0]'] ization) conv4_block2_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block2_2_bn[0][0]'] n) conv4_block2_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block2_2_relu[0][0]'] ) conv4_block2_3_bn (BatchNormal (None, 14, 14, 1024 4096 ['conv4_block2_3_conv[0][0]'] ization) ) conv4_block2_add (Add) (None, 14, 14, 1024 0 ['conv4_block1_out[0][0]', ) 'conv4_block2_3_bn[0][0]'] conv4_block2_out (Activation) (None, 14, 14, 1024 0 ['conv4_block2_add[0][0]'] ) conv4_block3_1_conv (Conv2D) (None, 14, 14, 256) 262400 ['conv4_block2_out[0][0]'] conv4_block3_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block3_1_conv[0][0]'] ization) conv4_block3_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block3_1_bn[0][0]'] n) conv4_block3_2_conv (Conv2D) (None, 14, 14, 256) 590080 ['conv4_block3_1_relu[0][0]'] conv4_block3_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block3_2_conv[0][0]'] ization) conv4_block3_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block3_2_bn[0][0]'] n) conv4_block3_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block3_2_relu[0][0]'] ) conv4_block3_3_bn (BatchNormal (None, 14, 14, 1024 4096 ['conv4_block3_3_conv[0][0]'] ization) ) conv4_block3_add (Add) (None, 14, 14, 1024 0 ['conv4_block2_out[0][0]', ) 'conv4_block3_3_bn[0][0]'] conv4_block3_out (Activation) (None, 14, 14, 1024 0 ['conv4_block3_add[0][0]'] ) conv4_block4_1_conv (Conv2D) (None, 14, 14, 256) 262400 ['conv4_block3_out[0][0]'] conv4_block4_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block4_1_conv[0][0]'] ization) conv4_block4_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block4_1_bn[0][0]'] n) conv4_block4_2_conv (Conv2D) (None, 14, 14, 256) 590080 ['conv4_block4_1_relu[0][0]'] conv4_block4_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block4_2_conv[0][0]'] ization) conv4_block4_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block4_2_bn[0][0]'] n) conv4_block4_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block4_2_relu[0][0]'] ) conv4_block4_3_bn (BatchNormal (None, 14, 14, 1024 4096 ['conv4_block4_3_conv[0][0]'] ization) ) conv4_block4_add (Add) (None, 14, 14, 1024 0 ['conv4_block3_out[0][0]', ) 'conv4_block4_3_bn[0][0]'] conv4_block4_out (Activation) (None, 14, 14, 1024 0 ['conv4_block4_add[0][0]'] ) conv4_block5_1_conv (Conv2D) (None, 14, 14, 256) 262400 ['conv4_block4_out[0][0]'] conv4_block5_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block5_1_conv[0][0]'] ization) conv4_block5_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block5_1_bn[0][0]'] n) conv4_block5_2_conv (Conv2D) (None, 14, 14, 256) 590080 ['conv4_block5_1_relu[0][0]'] conv4_block5_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block5_2_conv[0][0]'] ization) conv4_block5_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block5_2_bn[0][0]'] n) conv4_block5_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block5_2_relu[0][0]'] ) conv4_block5_3_bn (BatchNormal (None, 14, 14, 1024 4096 ['conv4_block5_3_conv[0][0]'] ization) ) conv4_block5_add (Add) (None, 14, 14, 1024 0 ['conv4_block4_out[0][0]', ) 'conv4_block5_3_bn[0][0]'] conv4_block5_out (Activation) (None, 14, 14, 1024 0 ['conv4_block5_add[0][0]'] ) conv4_block6_1_conv (Conv2D) (None, 14, 14, 256) 262400 ['conv4_block5_out[0][0]'] conv4_block6_1_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block6_1_conv[0][0]'] ization) conv4_block6_1_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block6_1_bn[0][0]'] n) conv4_block6_2_conv (Conv2D) (None, 14, 14, 256) 590080 ['conv4_block6_1_relu[0][0]'] conv4_block6_2_bn (BatchNormal (None, 14, 14, 256) 1024 ['conv4_block6_2_conv[0][0]'] ization) conv4_block6_2_relu (Activatio (None, 14, 14, 256) 0 ['conv4_block6_2_bn[0][0]'] n) conv4_block6_3_conv (Conv2D) (None, 14, 14, 1024 263168 ['conv4_block6_2_relu[0][0]'] ) conv4_block6_3_bn (BatchNormal (None, 14, 14, 1024 4096 ['conv4_block6_3_conv[0][0]'] ization) ) conv4_block6_add (Add) (None, 14, 14, 1024 0 ['conv4_block5_out[0][0]', ) 'conv4_block6_3_bn[0][0]'] conv4_block6_out (Activation) (None, 14, 14, 1024 0 ['conv4_block6_add[0][0]'] ) conv5_block1_1_conv (Conv2D) (None, 7, 7, 512) 524800 ['conv4_block6_out[0][0]'] conv5_block1_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block1_1_conv[0][0]'] ization) conv5_block1_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block1_1_bn[0][0]'] n) conv5_block1_2_conv (Conv2D) (None, 7, 7, 512) 2359808 ['conv5_block1_1_relu[0][0]'] conv5_block1_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block1_2_conv[0][0]'] ization) conv5_block1_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block1_2_bn[0][0]'] n) conv5_block1_0_conv (Conv2D) (None, 7, 7, 2048) 2099200 ['conv4_block6_out[0][0]'] conv5_block1_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block1_2_relu[0][0]'] conv5_block1_0_bn (BatchNormal (None, 7, 7, 2048) 8192 ['conv5_block1_0_conv[0][0]'] ization) conv5_block1_3_bn (BatchNormal (None, 7, 7, 2048) 8192 ['conv5_block1_3_conv[0][0]'] ization) conv5_block1_add (Add) (None, 7, 7, 2048) 0 ['conv5_block1_0_bn[0][0]', 'conv5_block1_3_bn[0][0]'] conv5_block1_out (Activation) (None, 7, 7, 2048) 0 ['conv5_block1_add[0][0]'] conv5_block2_1_conv (Conv2D) (None, 7, 7, 512) 1049088 ['conv5_block1_out[0][0]'] conv5_block2_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block2_1_conv[0][0]'] ization) conv5_block2_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block2_1_bn[0][0]'] n) conv5_block2_2_conv (Conv2D) (None, 7, 7, 512) 2359808 ['conv5_block2_1_relu[0][0]'] conv5_block2_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block2_2_conv[0][0]'] ization) conv5_block2_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block2_2_bn[0][0]'] n) conv5_block2_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block2_2_relu[0][0]'] conv5_block2_3_bn (BatchNormal (None, 7, 7, 2048) 8192 ['conv5_block2_3_conv[0][0]'] ization) conv5_block2_add (Add) (None, 7, 7, 2048) 0 ['conv5_block1_out[0][0]', 'conv5_block2_3_bn[0][0]'] conv5_block2_out (Activation) (None, 7, 7, 2048) 0 ['conv5_block2_add[0][0]'] conv5_block3_1_conv (Conv2D) (None, 7, 7, 512) 1049088 ['conv5_block2_out[0][0]'] conv5_block3_1_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block3_1_conv[0][0]'] ization) conv5_block3_1_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block3_1_bn[0][0]'] n) conv5_block3_2_conv (Conv2D) (None, 7, 7, 512) 2359808 ['conv5_block3_1_relu[0][0]'] conv5_block3_2_bn (BatchNormal (None, 7, 7, 512) 2048 ['conv5_block3_2_conv[0][0]'] ization) conv5_block3_2_relu (Activatio (None, 7, 7, 512) 0 ['conv5_block3_2_bn[0][0]'] n) conv5_block3_3_conv (Conv2D) (None, 7, 7, 2048) 1050624 ['conv5_block3_2_relu[0][0]'] conv5_block3_3_bn (BatchNormal (None, 7, 7, 2048) 8192 ['conv5_block3_3_conv[0][0]'] ization) conv5_block3_add (Add) (None, 7, 7, 2048) 0 ['conv5_block2_out[0][0]', 'conv5_block3_3_bn[0][0]'] conv5_block3_out (Activation) (None, 7, 7, 2048) 0 ['conv5_block3_add[0][0]'] avg_pool (GlobalAveragePooling (None, 2048) 0 ['conv5_block3_out[0][0]'] 2D) predictions (Dense) (None, 1000) 2049000 ['avg_pool[0][0]'] ================================================================================================== Total params: 25,636,712 Trainable params: 25,583,592 Non-trainable params: 53,120 __________________________________________________________________________________________________ None
preds = model.predict(x)
1/1 [==============================] - 1s 854ms/step
print('Predicted:', decode_predictions(preds, top=5)[0])
Predicted: [('n02108422', 'bull_mastiff', 0.3921146), ('n02110958', 'pug', 0.2944119), ('n02093754', 'Border_terrier', 0.14356579), ('n02108915', 'French_bulldog', 0.057976846), ('n02099712', 'Labrador_retriever', 0.052499186)]
TensorFlow2.2基本应用
import tensorflow as tf x=tf.random.normal([2,16]) w1=tf.Variable(tf.random.truncated_normal([16,8],stddev=0.1)) b1=tf.Variable(tf.zeros([8])) o1=tf.matmul(x,w1)+b1 o1=tf.nn.relu(o1) o1
<tf.Tensor: id=8263, shape=(2, 8), dtype=float32, numpy=
array([[0.16938789, 0. , 0.08883161, 0.14095941, 0.34751543,
0.353898 , 0. , 0.13356908],
[0. , 0. , 0.48546872, 0.37623546, 0.5447475 ,
0.21755993, 0.40121362, 0. ]], dtype=float32)>
from tensorflow.keras import layers x=tf.random.normal([4,16*16]) fc=layers.Dense(5,activation=tf.nn.relu) h1=fc(x) h1
<tf.Tensor: id=8296, shape=(4, 5), dtype=float32, numpy=
array([[0. , 0. , 0. , 0.14286758, 0. ],
[0. , 2.2727172 , 0. , 0. , 0.34961763],
[0.1311972 , 0. , 1.4005635 , 0. , 0. ],
[0. , 1.7266206 , 0.64711714, 1.3494569 , 0. ]],
dtype=float32)>
#获取权值矩阵w fc.kernel
<tf.Variable ‘dense/kernel:0’ shape=(256, 5) dtype=float32, numpy=
array([[-0.0339304 , 0.02273461, -0.12746884, 0.14963049, 0.00773269],
[-0.05978647, 0.07886668, -0.09110804, 0.14902723, 0.13007113],
[ 0.10187459, 0.13089484, 0.14367685, 0.12212327, -0.06235344],
…,
[ 0.10417426, 0.05112691, 0.12206474, 0.01141772, -0.05271714],
[ 0.03493455, -0.13473712, -0.01317982, -0.09485313, 0.04731715],
[ 0.12421742, 0.00030141, -0.00211757, -0.04196439, -0.03638943]],
dtype=float32)>
fc.bias
<tf.Variable ‘dense/bias:0’ shape=(5,) dtype=float32, numpy=array([0., 0., 0., 0., 0.], dtype=float32)>
fc.trainable_variables
[<tf.Variable ‘dense/kernel:0’ shape=(256, 5) dtype=float32, numpy=
array([[-0.0339304 , 0.02273461, -0.12746884, 0.14963049, 0.00773269],
[-0.05978647, 0.07886668, -0.09110804, 0.14902723, 0.13007113],
[ 0.10187459, 0.13089484, 0.14367685, 0.12212327, -0.06235344],
…,
[ 0.10417426, 0.05112691, 0.12206474, 0.01141772, -0.05271714],
[ 0.03493455, -0.13473712, -0.01317982, -0.09485313, 0.04731715],
[ 0.12421742, 0.00030141, -0.00211757, -0.04196439, -0.03638943]],
dtype=float32)>,
<tf.Variable ‘dense/bias:0’ shape=(5,) dtype=float32, numpy=array([0., 0., 0., 0., 0.], dtype=float32)>]
fc.variables
[<tf.Variable ‘dense/kernel:0’ shape=(256, 5) dtype=float32, numpy=
array([[-0.0339304 , 0.02273461, -0.12746884, 0.14963049, 0.00773269],
[-0.05978647, 0.07886668, -0.09110804, 0.14902723, 0.13007113],
[ 0.10187459, 0.13089484, 0.14367685, 0.12212327, -0.06235344],
…,
[ 0.10417426, 0.05112691, 0.12206474, 0.01141772, -0.05271714],
[ 0.03493455, -0.13473712, -0.01317982, -0.09485313, 0.04731715],
[ 0.12421742, 0.00030141, -0.00211757, -0.04196439, -0.03638943]],
dtype=float32)>,
<tf.Variable ‘dense/bias:0’ shape=(5,) dtype=float32, numpy=array([0., 0., 0., 0., 0.], dtype=float32)>]
5. 使用深度学习进行手写数字识别
import tensorflow as tf #载入MNIST 数据集。 mnist = tf.keras.datasets.mnist #拆分数据集 (x_train, y_train), (x_test, y_test) = mnist.load_data() #将样本进行预处理,并从整数转换为浮点数 x_train, x_test = x_train / 255.0, x_test / 255.0 #使用tf.keras.Sequential将模型的各层堆叠,并设置参数 model = tf.keras.models.Sequential([ tf.keras.layers.Flatten(input_shape=(28, 28)), tf.keras.layers.Dense(128, activation='relu'), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation='softmax') ]) #设置模型的优化器和损失函数 model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) #训练并验证模型 model.fit(x_train, y_train, epochs=5) model.evaluate(x_test, y_test, verbose=2)
Train on 60000 samples Epoch 1/5 60000/60000 [==============================] - 6s 95us/sample - loss: 0.2931 - accuracy: 0.9146 Epoch 2/5 60000/60000 [==============================] - 5s 77us/sample - loss: 0.1419 - accuracy: 0.9592 Epoch 3/5 60000/60000 [==============================] - 5s 78us/sample - loss: 0.1065 - accuracy: 0.9683 Epoch 4/5 60000/60000 [==============================] - 5s 78us/sample - loss: 0.0852 - accuracy: 0.9738 Epoch 5/5 60000/60000 [==============================] - 6s 100us/sample - loss: 0.0735 - accuracy: 0.9769 10000/1 - 0s - loss: 0.0338 - accuracy: 0.9795 [0.0666636555833742, 0.9795]