文章目錄

• • 1. 使用 LeNet 預(yù)測
  • • 1.1 導(dǎo)入包
    • 1.2 建立 LeNet 模型
    • 1.3 讀入數(shù)據(jù)
    • 1.4 定義模型
    • 1.5 訓(xùn)練
    • 1.6 繪制訓(xùn)練曲線
    • 1.7 預(yù)測提交
  • 2. 使用 VGG16 遷移學(xué)習(xí)
  • • 2.1 導(dǎo)入包
    • 2.2 定義模型
    • 2.3 數(shù)據(jù)處理
    • 2.4 配置模型、訓(xùn)練
    • 2.5 預(yù)測提交

Digit Recognizer 練習(xí)地址

相關(guān)博文：
[Hands On ML] 3. 分類（MNIST手寫數(shù)字預(yù)測）
[Kaggle] Digit Recognizer 手寫數(shù)字識別
[Kaggle] Digit Recognizer 手寫數(shù)字識別（簡單神經(jīng)網(wǎng)絡(luò)）
04.卷積神經(jīng)網(wǎng)絡(luò) W1.卷積神經(jīng)網(wǎng)絡(luò)

上一篇的簡單神經(jīng)網(wǎng)絡(luò)，將28*28的圖片展平了，每個(gè)像素在空間上的位置關(guān)系是沒有考慮的，空間的信息丟失。

1. 使用 LeNet 預(yù)測

LeNet神經(jīng)網(wǎng)絡(luò) 參考博文

1.1 導(dǎo)入包

from keras import backend as K # 兼容不同后端的代碼 from keras.models import Sequential from keras.layers.convolutional import Conv2D from keras.layers.convolutional import MaxPooling2D from keras.layers.core import Activation from keras.layers.core import Dense from keras.layers.core import Flatten from keras.utils import np_utils from keras.optimizers import SGD, Adam, RMSpropimport numpy as np %matplotlib inline import matplotlib.pyplot as plt import pandas as pd

1.2 建立 LeNet 模型

# 圖片格式問題 # K.image_data_format() == 'channels_last' # 默認(rèn)是last是通道 K.set_image_dim_ordering("tf") # K.image_data_format() == 'channels_first' # K.set_image_dim_ordering("th")class LeNet:@staticmethoddef build(input_shape, classes):model = Sequential()model.add(Conv2D(20,kernel_size=5,padding='same',input_shape=input_shape,activation='relu'))model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2)))model.add(Conv2D(50,kernel_size=5,padding='same',activation='relu'))model.add(MaxPooling2D(pool_size=(2,2),strides=(2,2)))model.add(Flatten())model.add(Dense(500, activation='relu'))model.add(Dense(classes,activation='softmax'))return model

1.3 讀入數(shù)據(jù)

train = pd.read_csv('train.csv') y_train_full = train['label'] X_train_full = train.drop(['label'], axis=1) X_test_full = pd.read_csv('test.csv') X_train_full.shape

輸出：

(42000, 784)

• 數(shù)據(jù)格式轉(zhuǎn)換，增加一個(gè)通道維度

X_train = np.array(X_train_full).reshape(-1,28,28) / 255.0 X_test = np.array(X_test_full).reshape(-1,28,28)/255.0 y_train = np_utils.to_categorical(y_train_full, 10) # 轉(zhuǎn)成oh編碼X_train = X_train[:, :, :, np.newaxis] # m,28,28 --> m, 28, 28, 1(單通道) X_test = X_test[:, :, :, np.newaxis]

1.4 定義模型

model = LeNet.build(input_shape=(28, 28, 1), classes=10)

• 定義優(yōu)化器，配置模型

opt = Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, decay=0.01) model.compile(loss="categorical_crossentropy",optimizer=opt, metrics=["accuracy"])

注意：標(biāo)簽不采用 one-hot 編碼的話，這里使用 loss="sparse_categorical_crossentropy"

1.5 訓(xùn)練

history = model.fit(X_train, y_train, epochs=20, batch_size=128,validation_split=0.2) Epoch 1/20 263/263 [==============================] - 26s 98ms/step - loss: 0.2554 - accuracy: 0.9235 - val_loss: 0.0983 - val_accuracy: 0.9699 Epoch 2/20 263/263 [==============================] - 27s 103ms/step - loss: 0.0806 - accuracy: 0.9761 - val_loss: 0.0664 - val_accuracy: 0.9787 ... ... Epoch 20/20 263/263 [==============================] - 25s 97ms/step - loss: 0.0182 - accuracy: 0.9953 - val_loss: 0.0405 - val_accuracy: 0.9868

可以看見第2輪迭代結(jié)束，訓(xùn)練集準(zhǔn)確率就 97.6%了，效果比之前的簡單神經(jīng)網(wǎng)絡(luò)好很多

• 模型總結(jié)

model.summary() Model: "sequential" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= conv2d (Conv2D) (None, 28, 28, 20) 520 _________________________________________________________________ max_pooling2d (MaxPooling2D) (None, 14, 14, 20) 0 _________________________________________________________________ conv2d_1 (Conv2D) (None, 14, 14, 50) 25050 _________________________________________________________________ max_pooling2d_1 (MaxPooling2 (None, 7, 7, 50) 0 _________________________________________________________________ flatten (Flatten) (None, 2450) 0 _________________________________________________________________ dense (Dense) (None, 500) 1225500 _________________________________________________________________ dense_1 (Dense) (None, 10) 5010 ================================================================= Total params: 1,256,080 Trainable params: 1,256,080 Non-trainable params: 0 _________________________________________________________________

• 繪制模型結(jié)構(gòu)圖

from keras.utils import plot_model plot_model(model, './model.png', show_shapes=True)

1.6 繪制訓(xùn)練曲線

pd.DataFrame(history.history).plot(figsize=(8, 5)) plt.grid(True) plt.gca().set_ylim(0, 1) # set the vertical range to [0-1] plt.show()

1.7 預(yù)測提交

y_pred = model.predict(X_test) pred = y_pred.argmax(axis=1).reshape(-1) print(pred.shape)image_id = pd.Series(range(1,len(pred)+1)) output = pd.DataFrame({'ImageId':image_id, 'Label':pred}) output.to_csv("submission_NN.csv", index=False)

LeNet 模型得分 0.98607，比上一篇的簡單NN模型（得分 0.97546），好了 1.061%

2. 使用 VGG16 遷移學(xué)習(xí)

VGG16 help 文檔：

Help on function VGG16 in module tensorflow.python.keras.applications.vgg16:VGG16(include_top=True, weights='imagenet', input_tensor=None, input_shape=None, pooling=None, classes=1000, classifier_activation='softmax')Instantiates the VGG16 model.Reference paper:- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://arxiv.org/abs/1409.1556) (ICLR 2015)By default, it loads weights pre-trained on ImageNet. Check 'weights' forother options.This model can be built both with 'channels_first' data format(channels, height, width) or 'channels_last' data format(height, width, channels).The default input size for this model is 224x224.Caution: Be sure to properly pre-process your inputs to the application.Please see `applications.vgg16.preprocess_input` for an example.Arguments:include_top: whether to include the 3 fully-connectedlayers at the top of the network.weights: one of `None` (random initialization),'imagenet' (pre-training on ImageNet),or the path to the weights file to be loaded.input_tensor: optional Keras tensor(i.e. output of `layers.Input()`)to use as image input for the model.input_shape: optional shape tuple, only to be specifiedif `include_top` is False (otherwise the input shapehas to be `(224, 224, 3)`(with `channels_last` data format)or `(3, 224, 224)` (with `channels_first` data format).It should have exactly 3 input channels,and width and height should be no smaller than 32.E.g. `(200, 200, 3)` would be one valid value.pooling: Optional pooling mode for feature extractionwhen `include_top` is `False`.- `None` means that the output of the model will bethe 4D tensor output of thelast convolutional block.- `avg` means that global average poolingwill be applied to the output of thelast convolutional block, and thusthe output of the model will be a 2D tensor.- `max` means that global max pooling willbe applied.classes: optional number of classes to classify imagesinto, only to be specified if `include_top` is True, andif no `weights` argument is specified.classifier_activation: A `str` or callable. The activation function to useon the "top" layer. Ignored unless `include_top=True`. Set`classifier_activation=None` to return the logits of the "top" layer.Returns:A `keras.Model` instance.Raises:ValueError: in case of invalid argument for `weights`,or invalid input shape.ValueError: if `classifier_activation` is not `softmax` or `None` whenusing a pretrained top layer.

2.1 導(dǎo)入包

import numpy as np %matplotlib inline import matplotlib.pyplot as plt import pandas as pd import cv2 from keras.optimizers import Adam from keras.models import Model from keras.utils import np_utils from keras.models import Sequential from keras.layers import Flatten from keras.layers import Dense from keras.layers import Input from keras.layers import Dropout from keras.applications.vgg16 import VGG16

2.2 定義模型

vgg16 = VGG16(weights='imagenet',include_top=False,input_shape=(32, 32, 3)) # VGG16 模型在include_top=False時(shí)，可以自定義輸入大小，至少32x32，通道必須是3mylayer = vgg16.output mylayer = Flatten()(mylayer) mylayer = Dense(128, activation='relu')(mylayer) mylayer = Dropout(0.3)(mylayer) mylayer = Dense(10, activation='softmax')(mylayer)model = Model(inputs=vgg16.inputs, outputs=mylayer)for layer in vgg16.layers:layer.trainable = False # vgg16的各個(gè)層不訓(xùn)練

2.3 數(shù)據(jù)處理

train = pd.read_csv('train.csv') y_train_full = train['label'] X_train_full = train.drop(['label'], axis=1) X_test_full = pd.read_csv('test.csv')

• 將單通道的數(shù)據(jù)，復(fù)制成3通道的（vgg16要求3通道的），再resize成 32*32的，vgg16 要求圖片最低分辨率是 32*32

def process(data):data = np.array(data).reshape(-1,28,28)output = np.zeros((data.shape[0], 32, 32, 3))for i in range(data.shape[0]):img = data[i]rgb_array = np.zeros((img.shape[0], img.shape[1], 3), "uint8")rgb_array[:, :, 0], rgb_array[:, :, 1], rgb_array[:, :, 2] = img, img, imgpic = cv2.resize(rgb_array, (32, 32), interpolation=cv2.INTER_LINEAR)output[i] = picoutput = output.astype('float32')/255.0return output y_train = np_utils.to_categorical(y_train_full, 10) X_train = process(X_train_full) X_test = process(X_test_full)print(X_train.shape) print(X_test.shape)

輸出：

(42000, 32, 32, 3) (28000, 32, 32, 3)

• 看一看處理后的圖片

img = X_train[0] plt.imshow(img) np.set_printoptions(threshold=np.inf)# 全部顯示矩陣 # print(X_train[0])

2.4 配置模型、訓(xùn)練

opt = Adam(learning_rate=0.001, beta_1=0.9, beta_2=0.999, decay=0.01) model.compile(loss="categorical_crossentropy",optimizer=opt, metrics=["accuracy"]) history = model.fit(X_train, y_train, epochs=50, batch_size=128,validation_split=0.2)

輸出：

Epoch 1/50 263/263 [==============================] - 101s 384ms/step - loss: 0.9543 - accuracy: 0.7212 - val_loss: 0.5429 - val_accuracy: 0.8601 ... Epoch 10/50 263/263 [==============================] - 110s 417ms/step - loss: 0.3284 - accuracy: 0.9063 - val_loss: 0.2698 - val_accuracy: 0.9263 ... Epoch 40/50 263/263 [==============================] - 114s 433ms/step - loss: 0.2556 - accuracy: 0.9254 - val_loss: 0.2121 - val_accuracy: 0.9389 ... Epoch 50/50 263/263 [==============================] - 110s 420ms/step - loss: 0.2466 - accuracy: 0.9272 - val_loss: 0.2058 - val_accuracy: 0.9406

model.summary()

輸出：

Model: "functional_15" _________________________________________________________________ Layer (type) Output Shape Param # ================================================================= input_23 (InputLayer) [(None, 32, 32, 3)] 0 _________________________________________________________________ block1_conv1 (Conv2D) (None, 32, 32, 64) 1792 _________________________________________________________________ block1_conv2 (Conv2D) (None, 32, 32, 64) 36928 _________________________________________________________________ block1_pool (MaxPooling2D) (None, 16, 16, 64) 0 _________________________________________________________________ block2_conv1 (Conv2D) (None, 16, 16, 128) 73856 _________________________________________________________________ block2_conv2 (Conv2D) (None, 16, 16, 128) 147584 _________________________________________________________________ block2_pool (MaxPooling2D) (None, 8, 8, 128) 0 _________________________________________________________________ block3_conv1 (Conv2D) (None, 8, 8, 256) 295168 _________________________________________________________________ block3_conv2 (Conv2D) (None, 8, 8, 256) 590080 _________________________________________________________________ block3_conv3 (Conv2D) (None, 8, 8, 256) 590080 _________________________________________________________________ block3_pool (MaxPooling2D) (None, 4, 4, 256) 0 _________________________________________________________________ block4_conv1 (Conv2D) (None, 4, 4, 512) 1180160 _________________________________________________________________ block4_conv2 (Conv2D) (None, 4, 4, 512) 2359808 _________________________________________________________________ block4_conv3 (Conv2D) (None, 4, 4, 512) 2359808 _________________________________________________________________ block4_pool (MaxPooling2D) (None, 2, 2, 512) 0 _________________________________________________________________ block5_conv1 (Conv2D) (None, 2, 2, 512) 2359808 _________________________________________________________________ block5_conv2 (Conv2D) (None, 2, 2, 512) 2359808 _________________________________________________________________ block5_conv3 (Conv2D) (None, 2, 2, 512) 2359808 _________________________________________________________________ block5_pool (MaxPooling2D) (None, 1, 1, 512) 0 _________________________________________________________________ flatten_19 (Flatten) (None, 512) 0 _________________________________________________________________ dense_28 (Dense) (None, 128) 65664 _________________________________________________________________ dropout_9 (Dropout) (None, 128) 0 _________________________________________________________________ dense_29 (Dense) (None, 10) 1290 ================================================================= Total params: 14,781,642 Trainable params: 66,954 Non-trainable params: 14,714,688 _________________________________________________________________

• 繪制模型結(jié)構(gòu)

from keras.utils import plot_model plot_model(model, './model.png', show_shapes=True)

2.5 預(yù)測提交

y_pred = model.predict(X_test) pred = y_pred.argmax(axis=1).reshape(-1) print(pred.shape) print(pred) image_id = pd.Series(range(1,len(pred)+1)) output = pd.DataFrame({'ImageId':image_id, 'Label':pred}) output.to_csv("submission_NN.csv", index=False)

預(yù)測得分：0.93696

可能是由于 VGG16模型是用 224*224 的圖片訓(xùn)練的權(quán)重，我們使用的是 28*28 的圖片，可能不能很好的使用VGG16已經(jīng)訓(xùn)練好的權(quán)重

---

我的CSDN博客地址 https://michael.blog.csdn.net/

長按或掃碼關(guān)注我的公眾號（Michael阿明），一起加油、一起學(xué)習(xí)進(jìn)步！

總結(jié)

以上是生活随笔為你收集整理的[Kaggle] Digit Recognizer 手写数字识别（卷积神经网络）的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。