【tensorflow2.0】构建模型的三种方法

import numpy as np 
import pandas as pd 
import tensorflow as tf
from tqdm import tqdm 
from tensorflow.keras import *
 
 
train_token_path = "./data/imdb/train_token.csv"
test_token_path = "./data/imdb/test_token.csv"
 
MAX_WORDS = 10000  # We will only consider the top 10,000 words in the dataset
MAX_LEN = 200  # We will cut reviews after 200 words
BATCH_SIZE = 20 
 
# 构建管道
def parse_line(line):
    t = tf.strings.split(line,"t")
    label = tf.reshape(tf.cast(tf.strings.to_number(t[0]),tf.int32),(-1,))
    features = tf.cast(tf.strings.to_number(tf.strings.split(t[1]," ")),tf.int32)
    return (features,label)
 
ds_train=  tf.data.TextLineDataset(filenames = [train_token_path]) 
   .map(parse_line,num_parallel_calls = tf.data.experimental.AUTOTUNE) 
   .shuffle(buffer_size = 1000).batch(BATCH_SIZE) 
   .prefetch(tf.data.experimental.AUTOTUNE)
 
ds_test=  tf.data.TextLineDataset(filenames = [test_token_path]) 
   .map(parse_line,num_parallel_calls = tf.data.experimental.AUTOTUNE) 
   .shuffle(buffer_size = 1000).batch(BATCH_SIZE) 
   .prefetch(tf.data.experimental.AUTOTUNE)

f.keras.backend.clear_session()
 
model = models.Sequential()
 
model.add(layers.Embedding(MAX_WORDS,7,input_length=MAX_LEN))
model.add(layers.Conv1D(filters = 64,kernel_size = 5,activation = "relu"))
model.add(layers.MaxPool1D(2))
model.add(layers.Conv1D(filters = 32,kernel_size = 3,activation = "relu"))
model.add(layers.MaxPool1D(2))
model.add(layers.Flatten())
model.add(layers.Dense(1,activation = "sigmoid"))
 
model.compile(optimizer='Nadam',
            loss='binary_crossentropy',
            metrics=['accuracy',"AUC"])
 
model.summary()

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None, 200, 7)            70000     
_________________________________________________________________
conv1d (Conv1D)              (None, 196, 64)           2304      
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 98, 64)            0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 96, 32)            6176      
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 48, 32)            0         
_________________________________________________________________
flatten (Flatten)            (None, 1536)              0         
_________________________________________________________________
dense (Dense)                (None, 1)                 1537      
=================================================================
Total params: 80,017
Trainable params: 80,017
Non-trainable params: 0
_________________________________________________________________

import datetime
baselogger = callbacks.BaseLogger(stateful_metrics=["auc"])
logdir = "./data/keras_model/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
history = model.fit(ds_train,validation_data = ds_test,
        epochs = 6,callbacks=[baselogger,tensorboard_callback])
 
%matplotlib inline
%config InlineBackend.figure_format = 'svg'
 
import matplotlib.pyplot as plt
 
def plot_metric(history, metric):
    train_metrics = history.history[metric]
    val_metrics = history.history['val_'+metric]
    epochs = range(1, len(train_metrics) + 1)
    plt.plot(epochs, train_metrics, 'bo--')
    plt.plot(epochs, val_metrics, 'ro-')
    plt.title('Training and validation '+ metric)
    plt.xlabel("Epochs")
    plt.ylabel(metric)
    plt.legend(["train_"+metric, 'val_'+metric])
    plt.show()
plot_metric(history,"auc")

Epoch 1/6
   1000/Unknown - 17s 17ms/step - loss: 0.1133 - accuracy: 0.9588 - auc: 0.9918
---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-17-8cd49fdfb6d8> in <module>()
      4 tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
      5 history = model.fit(ds_train,validation_data = ds_test,
----> 6         epochs = 6,callbacks=[baselogger,tensorboard_callback])
      7 """ 
      8 %matplotlib inline

3 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py in on_epoch_end(self, epoch, logs)
    795   def on_epoch_end(self, epoch, logs=None):
    796     if logs is not None:
--> 797       for k in self.params['metrics']:
    798         if k in self.totals:
    799           # Make value available to next callbacks.

KeyError: 'metrics'

import datetime
logdir = "./data/keras_model/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
history = model.fit(ds_train,validation_data = ds_test,epochs = 6,callbacks=[tensorboard_callback])

Epoch 1/6
1000/1000 [==============================] - 44s 44ms/step - loss: 0.0058 - accuracy: 0.9980 - auc: 0.9999 - val_loss: 1.5239 - val_accuracy: 0.8598 - val_auc: 0.8961
Epoch 2/6
1000/1000 [==============================] - 44s 44ms/step - loss: 0.0011 - accuracy: 0.9996 - auc: 1.0000 - val_loss: 1.7804 - val_accuracy: 0.8610 - val_auc: 0.8920
Epoch 3/6
1000/1000 [==============================] - 44s 44ms/step - loss: 0.0034 - accuracy: 0.9990 - auc: 0.9999 - val_loss: 1.8452 - val_accuracy: 0.8524 - val_auc: 0.8861
Epoch 4/6
1000/1000 [==============================] - 43s 43ms/step - loss: 0.0107 - accuracy: 0.9969 - auc: 0.9995 - val_loss: 1.6515 - val_accuracy: 0.8582 - val_auc: 0.8901
Epoch 5/6
1000/1000 [==============================] - 44s 44ms/step - loss: 0.0022 - accuracy: 0.9994 - auc: 1.0000 - val_loss: 1.7680 - val_accuracy: 0.8522 - val_auc: 0.8864
Epoch 6/6
1000/1000 [==============================] - 44s 44ms/step - loss: 0.0052 - accuracy: 0.9979 - auc: 0.9999 - val_loss: 1.7506 - val_accuracy: 0.8554 - val_auc: 0.8918

tf.keras.backend.clear_session()
 
inputs = layers.Input(shape=[MAX_LEN])
x  = layers.Embedding(MAX_WORDS,7)(inputs)
 
branch1 = layers.SeparableConv1D(64,3,activation="relu")(x)
branch1 = layers.MaxPool1D(3)(branch1)
branch1 = layers.SeparableConv1D(32,3,activation="relu")(branch1)
branch1 = layers.GlobalMaxPool1D()(branch1)
 
branch2 = layers.SeparableConv1D(64,5,activation="relu")(x)
branch2 = layers.MaxPool1D(5)(branch2)
branch2 = layers.SeparableConv1D(32,5,activation="relu")(branch2)
branch2 = layers.GlobalMaxPool1D()(branch2)
 
branch3 = layers.SeparableConv1D(64,7,activation="relu")(x)
branch3 = layers.MaxPool1D(7)(branch3)
branch3 = layers.SeparableConv1D(32,7,activation="relu")(branch3)
branch3 = layers.GlobalMaxPool1D()(branch3)
 
concat = layers.Concatenate()([branch1,branch2,branch3])
outputs = layers.Dense(1,activation = "sigmoid")(concat)
 
model = models.Model(inputs = inputs,outputs = outputs)
 
model.compile(optimizer='Nadam',
            loss='binary_crossentropy',
            metrics=['accuracy',"AUC"])
 
model.summary()

Model: "model"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_1 (InputLayer)            [(None, 200)]        0                                            
__________________________________________________________________________________________________
embedding (Embedding)           (None, 200, 7)       70000       input_1[0][0]                    
__________________________________________________________________________________________________
separable_conv1d (SeparableConv (None, 198, 64)      533         embedding[0][0]                  
__________________________________________________________________________________________________
separable_conv1d_2 (SeparableCo (None, 196, 64)      547         embedding[0][0]                  
__________________________________________________________________________________________________
separable_conv1d_4 (SeparableCo (None, 194, 64)      561         embedding[0][0]                  
__________________________________________________________________________________________________
max_pooling1d (MaxPooling1D)    (None, 66, 64)       0           separable_conv1d[0][0]           
__________________________________________________________________________________________________
max_pooling1d_1 (MaxPooling1D)  (None, 39, 64)       0           separable_conv1d_2[0][0]         
__________________________________________________________________________________________________
max_pooling1d_2 (MaxPooling1D)  (None, 27, 64)       0           separable_conv1d_4[0][0]         
__________________________________________________________________________________________________
separable_conv1d_1 (SeparableCo (None, 64, 32)       2272        max_pooling1d[0][0]              
__________________________________________________________________________________________________
separable_conv1d_3 (SeparableCo (None, 35, 32)       2400        max_pooling1d_1[0][0]            
__________________________________________________________________________________________________
separable_conv1d_5 (SeparableCo (None, 21, 32)       2528        max_pooling1d_2[0][0]            
__________________________________________________________________________________________________
global_max_pooling1d (GlobalMax (None, 32)           0           separable_conv1d_1[0][0]         
__________________________________________________________________________________________________
global_max_pooling1d_1 (GlobalM (None, 32)           0           separable_conv1d_3[0][0]         
__________________________________________________________________________________________________
global_max_pooling1d_2 (GlobalM (None, 32)           0           separable_conv1d_5[0][0]         
__________________________________________________________________________________________________
concatenate (Concatenate)       (None, 96)           0           global_max_pooling1d[0][0]       
                                                                 global_max_pooling1d_1[0][0]     
                                                                 global_max_pooling1d_2[0][0]     
__________________________________________________________________________________________________
dense (Dense)                   (None, 1)            97          concatenate[0][0]                
==================================================================================================
Total params: 78,938
Trainable params: 78,938
Non-trainable params: 0
__________________________________________________________________________________________________

import datetime
logdir = "./data/keras_model/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
history = model.fit(ds_train,validation_data = ds_test,epochs = 6,callbacks=[tensorboard_callback])

Epoch 1/6
1000/1000 [==============================] - 28s 28ms/step - loss: 0.5210 - accuracy: 0.7120 - auc: 0.8098 - val_loss: 0.3512 - val_accuracy: 0.8482 - val_auc: 0.9254
Epoch 2/6
1000/1000 [==============================] - 27s 27ms/step - loss: 0.2842 - accuracy: 0.8805 - auc: 0.9510 - val_loss: 0.3302 - val_accuracy: 0.8588 - val_auc: 0.9384
Epoch 3/6
1000/1000 [==============================] - 27s 27ms/step - loss: 0.1931 - accuracy: 0.9265 - auc: 0.9772 - val_loss: 0.3955 - val_accuracy: 0.8512 - val_auc: 0.9336
Epoch 4/6
1000/1000 [==============================] - 27s 27ms/step - loss: 0.1203 - accuracy: 0.9594 - auc: 0.9906 - val_loss: 0.4669 - val_accuracy: 0.8494 - val_auc: 0.9273
Epoch 5/6
1000/1000 [==============================] - 27s 27ms/step - loss: 0.0664 - accuracy: 0.9798 - auc: 0.9965 - val_loss: 0.5963 - val_accuracy: 0.8476 - val_auc: 0.9158
Epoch 6/6
1000/1000 [==============================] - 27s 27ms/step - loss: 0.0305 - accuracy: 0.9934 - auc: 0.9987 - val_loss: 0.7246 - val_accuracy: 0.8440 - val_auc: 0.9063

plot_metric(history,"auc")

# 先自定义一个残差模块，为自定义Layer
 
class ResBlock(layers.Layer):
    def __init__(self, kernel_size, **kwargs):
        super(ResBlock, self).__init__(**kwargs)
        self.kernel_size = kernel_size
 
    def build(self,input_shape):
        self.conv1 = layers.Conv1D(filters=64,kernel_size=self.kernel_size,
                                   activation = "relu",padding="same")
        self.conv2 = layers.Conv1D(filters=32,kernel_size=self.kernel_size,
                                   activation = "relu",padding="same")
        self.conv3 = layers.Conv1D(filters=input_shape[-1],
                                   kernel_size=self.kernel_size,activation = "relu",padding="same")
        self.maxpool = layers.MaxPool1D(2)
        super(ResBlock,self).build(input_shape) # 相当于设置self.built = True
 
    def call(self, inputs):
        x = self.conv1(inputs)
        x = self.conv2(x)
        x = self.conv3(x)
        x = layers.Add()([inputs,x])
        x = self.maxpool(x)
        return x
 
    #如果要让自定义的Layer通过Functional API 组合成模型时可以序列化，需要自定义get_config方法。
    def get_config(self):  
        config = super(ResBlock, self).get_config()
        config.update({'kernel_size': self.kernel_size})
        return config
# 测试ResBlock
resblock = ResBlock(kernel_size = 3)
resblock.build(input_shape = (None,200,7))
resblock.compute_output_shape(input_shape=(None,200,7))

# 自定义模型，实际上也可以使用Sequential或者FunctionalAPI
 
class ImdbModel(models.Model):
    def __init__(self):
        super(ImdbModel, self).__init__()
 
    def build(self,input_shape):
        self.embedding = layers.Embedding(MAX_WORDS,7)
        self.block1 = ResBlock(7)
        self.block2 = ResBlock(5)
        self.dense = layers.Dense(1,activation = "sigmoid")
        super(ImdbModel,self).build(input_shape)
 
    def call(self, x):
        x = self.embedding(x)
        x = self.block1(x)
        x = self.block2(x)
        x = layers.Flatten()(x)
        x = self.dense(x)
        return(x)
 
tf.keras.backend.clear_session()
 
model = ImdbModel()
model.build(input_shape =(None,200))
model.summary()
 
model.compile(optimizer='Nadam',
            loss='binary_crossentropy',
            metrics=['accuracy',"AUC"])
 
 
import datetime
 
logdir = "./tflogs/keras_model/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
history = model.fit(ds_train,validation_data = ds_test,
                    epochs = 6,callbacks=[tensorboard_callback])
 
plot_metric(history,"auc")

odel: "imdb_model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        multiple                  70000     
_________________________________________________________________
res_block (ResBlock)         multiple                  19143     
_________________________________________________________________
res_block_1 (ResBlock)       multiple                  13703     
_________________________________________________________________
dense (Dense)                multiple                  351       
=================================================================
Total params: 103,197
Trainable params: 103,197
Non-trainable params: 0
_________________________________________________________________
Epoch 1/6
1000/1000 [==============================] - 44s 44ms/step - loss: 0.5311 - accuracy: 0.6953 - auc: 0.7931 - val_loss: 0.3333 - val_accuracy: 0.8522 - val_auc: 0.9352
Epoch 2/6
1000/1000 [==============================] - 43s 43ms/step - loss: 0.2507 - accuracy: 0.8985 - auc: 0.9619 - val_loss: 0.3906 - val_accuracy: 0.8404 - val_auc: 0.9427
Epoch 3/6
1000/1000 [==============================] - 43s 43ms/step - loss: 0.1448 - accuracy: 0.9465 - auc: 0.9868 - val_loss: 0.3965 - val_accuracy: 0.8742 - val_auc: 0.9403
Epoch 4/6
1000/1000 [==============================] - 43s 43ms/step - loss: 0.0758 - accuracy: 0.9745 - auc: 0.9958 - val_loss: 0.5496 - val_accuracy: 0.8648 - val_auc: 0.9279
Epoch 5/6
1000/1000 [==============================] - 43s 43ms/step - loss: 0.0296 - accuracy: 0.9898 - auc: 0.9990 - val_loss: 0.8675 - val_accuracy: 0.8592 - val_auc: 0.9111
Epoch 6/6
1000/1000 [==============================] - 43s 43ms/step - loss: 0.0208 - accuracy: 0.9927 - auc: 0.9995 - val_loss: 0.9153 - val_accuracy: 0.8578 - val_auc: 0.9094