tensorflow.keras.Model compile fit evaluate应用

1
2
import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metrics

数据预处理

1
2
3
4
5
6
7
8
9
def preprocess(x, y):
    """
    x is a simple image, not a batch
    """
    x = tf.cast(x, dtype=tf.float32) / 255.
    x = tf.reshape(x, [28*28])
    y = tf.cast(y, dtype=tf.int32)
    y = tf.one_hot(y, depth=10)
    return x,y
1
2
3
4
5
6
7
8
9
10
11
12
13
14
batchsz = 128
(x, y), (x_val, y_val) = datasets.mnist.load_data()
print('datasets:', x.shape, y.shape, x.min(), x.max())


db = tf.data.Dataset.from_tensor_slices((x,y))
# 使用preprocess函数处理数据集
db = db.map(preprocess).shuffle(60000).batch(batchsz)

ds_val = tf.data.Dataset.from_tensor_slices((x_val, y_val))
ds_val = ds_val.map(preprocess).batch(batchsz) 

sample = next(iter(db))
print(sample[0].shape, sample[1].shape)
datasets: (60000, 28, 28) (60000,) 0 255
(128, 784) (128, 10)

模型构建

1
2
3
4
5
6
7
8
network = Sequential([layers.Dense(256, activation='relu'),
                     layers.Dense(128, activation='relu'),
                     layers.Dense(64, activation='relu'),
                     layers.Dense(32, activation='relu'),
                     layers.Dense(10)])
network.build(input_shape=(None, 28*28))
network.summary()

Model: "sequential_2"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_10 (Dense)             multiple                  200960    
_________________________________________________________________
dense_11 (Dense)             multiple                  32896     
_________________________________________________________________
dense_12 (Dense)             multiple                  8256      
_________________________________________________________________
dense_13 (Dense)             multiple                  2080      
_________________________________________________________________
dense_14 (Dense)             multiple                  330       
=================================================================
Total params: 244,522
Trainable params: 244,522
Non-trainable params: 0
_________________________________________________________________

使用compile设置模型的优化器，损失函数，metrics

1
2
3
4
5
network.compile(optimizer=optimizers.Adam(lr=0.01),
		loss=tf.losses.CategoricalCrossentropy(from_logits=True),
		metrics=['accuracy'] # accuracy用来计算准确度
	)

使用fit配置模型的训练数据集，训练轮次，验证数据集，验证频次

1
network.fit(db, epochs=5, validation_data=ds_val, validation_freq=2)
Epoch 1/5
469/469 [==============================] - 11s 24ms/step - loss: 0.2834 - accuracy: 0.9153
Epoch 2/5
469/469 [==============================] - 12s 27ms/step - loss: 0.1356 - accuracy: 0.9628 - val_loss: 0.1399 - val_accuracy: 0.9614
Epoch 3/5
469/469 [==============================] - 9s 19ms/step - loss: 0.1134 - accuracy: 0.9696
Epoch 4/5
469/469 [==============================] - 12s 26ms/step - loss: 0.1001 - accuracy: 0.9736 - val_loss: 0.1208 - val_accuracy: 0.9685
Epoch 5/5
469/469 [==============================] - 10s 21ms/step - loss: 0.0846 - accuracy: 0.9773





<tensorflow.python.keras.callbacks.History at 0x7f893e44de90>

使用evaluate评估模型

1
network.evaluate(ds_val)
79/79 [==============================] - 3s 36ms/step - loss: 0.1085 - accuracy: 0.9738





[0.10845260255486716, 0.9738]

使用predict预测

1
2
3
4
5
6
7
8
9
10
sample = next(iter(ds_val))
x = sample[0]
y = sample[1] # one-hot
pred = network.predict(x) # [b, 10]
# convert back to number 
y = tf.argmax(y, axis=1)
pred = tf.argmax(pred, axis=1)

print(pred)
print(y)
tf.Tensor(
[7 2 1 0 4 1 4 9 5 9 0 6 9 0 1 5 9 7 3 4 9 6 6 5 4 0 7 4 0 1 3 1 3 0 7 2 7
 1 2 1 1 7 4 2 3 5 1 2 4 4 6 3 5 5 6 0 4 1 9 5 7 8 9 3 7 9 6 4 3 0 7 0 2 9
 1 7 3 2 9 7 7 6 2 7 8 4 7 3 6 1 3 6 9 3 1 4 1 7 6 9 6 0 5 4 9 9 2 1 9 4 8
 7 3 9 7 9 4 4 9 2 5 4 7 6 7 9 0 5], shape=(128,), dtype=int64)
tf.Tensor(
[7 2 1 0 4 1 4 9 5 9 0 6 9 0 1 5 9 7 3 4 9 6 6 5 4 0 7 4 0 1 3 1 3 4 7 2 7
 1 2 1 1 7 4 2 3 5 1 2 4 4 6 3 5 5 6 0 4 1 9 5 7 8 9 3 7 4 6 4 3 0 7 0 2 9
 1 7 3 2 9 7 7 6 2 7 8 4 7 3 6 1 3 6 9 3 1 4 1 7 6 9 6 0 5 4 9 9 2 1 9 4 8
 7 3 9 7 4 4 4 9 2 5 4 7 6 7 9 0 5], shape=(128,), dtype=int64)