8. Dropout and Strides For Larger Models

Intro

这是深度学习第8课。

本科结束后，你将会理解并知道如何使用：

Stride lengths来快速建立模型并减少内存消耗；
Dropout 来对抗过拟合；

这两个技术在大型模型中很有用。

Lesson

[1]

from IPython.display import YouTubeVideo
YouTubeVideo('fwNLf4t7MR8', width=800, height=450)

Sample Code

[2]

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from tensorflow.python import keras
from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense, Flatten, Conv2D, Dropoutimg_rows, img_cols = 28, 28
num_classes = 10def data_prep(raw):out_y = keras.utils.to_categorical(raw.label, num_classes)num_images = raw.shape[0]x_as_array = raw.values[:,1:]x_shaped_array = x_as_array.reshape(num_images, img_rows, img_cols, 1)out_x = x_shaped_array / 255return out_x, out_ytrain_size = 30000
train_file = "../input/digit-recognizer/train.csv"
raw_data = pd.read_csv(train_file)x, y = data_prep(raw_data)model = Sequential()
model.add(Conv2D(30, kernel_size=(3, 3),strides=2,activation='relu',input_shape=(img_rows, img_cols, 1)))
model.add(Dropout(0.5))
model.add(Conv2D(30, kernel_size=(3, 3), strides=2, activation='relu'))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))model.compile(loss=keras.losses.categorical_crossentropy,optimizer='adam',metrics=['accuracy'])
model.fit(x, y,batch_size=128,epochs=2,validation_split = 0.2)

/opt/conda/lib/python3.6/site-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.from ._conv import register_converters as _register_convertersTrain on 33600 samples, validate on 8400 samples
Epoch 1/2
33600/33600 [==============================] - 14s 408us/step - loss: 0.6243 - acc: 0.8026 - val_loss: 0.2235 - val_acc: 0.9354
Epoch 2/2
33600/33600 [==============================] - 14s 417us/step - loss: 0.2664 - acc: 0.9176 - val_loss: 0.1315 - val_acc: 0.9630<tensorflow.python.keras._impl.keras.callbacks.History at 0x7f58d9f92c88>

Exercise: Dropout and Strides For Larger Models

Introduction

您已经构建了一个模型来识别MNIST for Fashion数据集中的服装类型。现在，您将使模型更大，指定更大的stride lengths并应用dropout。这些更改将使您的模型更快，更准确。

这是深度学习课程的最后一步。

Starter Code

Data Preparation

你需要运行以下单元

【3】

import numpy as np
from sklearn.model_selection import train_test_split
from tensorflow.python import kerasimg_rows, img_cols = 28, 28
num_classes = 10def prep_data(raw, train_size, val_size):y = raw[:, 0]out_y = keras.utils.to_categorical(y, num_classes)x = raw[:,1:]num_images = raw.shape[0]out_x = x.reshape(num_images, img_rows, img_cols, 1)out_x = out_x / 255return out_x, out_yfashion_file = "../input/fashionmnist/fashion-mnist_train.csv"
fashion_data = np.loadtxt(fashion_file, skiprows=1, delimiter=',')
x, y = prep_data(fashion_data, train_size=50000, val_size=5000)

Sample Model Code

[4]

fashion_model = Sequential()
fashion_model.add(Conv2D(12, kernel_size=(3, 3), strides=2,activation='relu',input_shape=(img_rows, img_cols, 1)))
fashion_model.add(Conv2D(12, (3, 3), strides=2, activation='relu'))
fashion_model.add(Flatten())
fashion_model.add(Dense(128, activation='relu'))
fashion_model.add(Dense(num_classes, activation='softmax'))fashion_model.compile(loss=keras.losses.categorical_crossentropy,optimizer='adam',metrics=['accuracy'])fashion_model.fit(train_x, train_y,batch_size=batch_size,epochs=epochs,validation_split = 0.2)

Adding Strides

指定，编译和拟合模型，与上面的模型非常相似，但为每个卷积层指定步长为2。调用你的新模型fashion_model_1。

【5】

from tensorflow.python.keras.models import Sequential
from tensorflow.python.keras.layers import Dense, Flatten, Conv2D, Dropoutfashion_model_1 = Sequential()
# Specify the rest of the model# Compile fashion_model_1# Fit fashion_model_1