Python学习从0开始——Kaggle深度学习001代码参考

一、A Single Neuron

单个神经元

1) Input shape

# YOUR CODE HERE
input_shape = [11]
# Check your answer
q_1.check()

2) Define a linear model

from tensorflow import keras
from tensorflow.keras import layers
# YOUR CODE HERE
model = keras.Sequential([
    layers.Dense(units=1, input_shape=input_shape)
])
# Check your answer
q_2.check()

3) Look at the weights

# YOUR CODE HERE
w, b = model.weights
print("Weights\n{}\n\nBias\n{}".format(w, b))
# Check your answer
q_3.check()

二、Deep Neural Networks

深度神经网络

1) Input Shape

# YOUR CODE HERE
input_shape = [8]

# Check your answer
q_1.check()

2) Define a Model with Hidden Layers

from tensorflow import keras
from tensorflow.keras import layers

# YOUR CODE HERE
model =  keras.Sequential([
    # the hidden ReLU layers
    layers.Dense(units=512, activation='relu', input_shape=input_shape),
    layers.Dense(units=512, activation='relu', input_shape=input_shape),
    layers.Dense(units=512, activation='relu', input_shape=input_shape),
    # the linear output layer 
    layers.Dense(units=1),
])

# Check your answer
q_2.check()

3) Activation Layers

### YOUR CODE HERE: rewrite this to use activation layers
model = keras.Sequential([
    layers.Dense(units=32, input_shape=[8]),
    layers.Activation('relu'),
    layers.Dense(units=32),
    layers.Activation('relu'),
    layers.Dense(1),
])

# Check your answer
q_3.check()

三、Stochastic Gradient Descent

随机梯度下降

1) Add Loss and Optimizer

# YOUR CODE HERE
model.compile(
    optimizer='adam',
    loss='mae',
)
# Check your answer
q_1.check()

2) Train Model

# YOUR CODE HERE
history = model.fit(
    X, y,
    validation_data=(X, y),
    batch_size=128,
    epochs=200,
)

# Check your answer
q_2.check()

四、Overfitting and Underfitting

过拟合和欠拟合

3) Define Early Stopping Callback

from tensorflow.keras import callbacks

# YOUR CODE HERE: define an early stopping callback
early_stopping = callbacks.EarlyStopping(
    min_delta=0.001, # minimium amount of change to count as an improvement
    patience=5, # how many epochs to wait before stopping
    restore_best_weights=True,
)

# Check your answer
q_3.check()

五、Dropout and Batch Normalization

丢弃层和批量归一化

1) Add Dropout to Spotify Model

# YOUR CODE HERE: Add two 30% dropout layers, one after 128 and one after 64
model = keras.Sequential([
    layers.Dense(128, activation='relu', input_shape=input_shape),
    layers.Dropout(rate=0.3),
    layers.Dense(64, activation='relu'),
    layers.Dropout(rate=0.3),
    layers.Dense(1)
])

# Check your answer
q_1.check()

3) Add Batch Normalization Layers

# YOUR CODE HERE: Add a BatchNormalization layer before each Dense layer
model = keras.Sequential([
    layers.BatchNormalization(),
    layers.Dense(512, activation='relu', input_shape=input_shape),
    layers.BatchNormalization(),
    layers.Dense(512, activation='relu'),
    layers.BatchNormalization(),
    layers.Dense(512, activation='relu'),
    layers.BatchNormalization(),
    layers.Dense(1),
])

# Check your answer
q_3.check()

六、Binary Classification

二元分类

1) Define Model

from tensorflow import keras
from tensorflow.keras import layers

# YOUR CODE HERE: define the model given in the diagram
model = keras.Sequential([
    layers.BatchNormalization(input_shape=input_shape),
    layers.Dense(256, activation='relu'),
    layers.BatchNormalization(),
    layers.Dropout(rate=0.3),
    layers.Dense(256, activation='relu'),
    layers.BatchNormalization(),
    layers.Dropout(rate=0.3), 
    layers.Dense(1, activation='sigmoid'),
])

# Check your answer
q_1.check()

2) Add Optimizer, Loss, and Metric

# YOUR CODE HERE
model.compile(
    optimizer='adam',
    loss='binary_crossentropy',
    metrics=['binary_accuracy'],
)

# Check your answer
q_2.check()