【tensorflow2.0】训练模型的三种方法

import numpy as np 
import pandas as pd 
import tensorflow as tf
from tensorflow.keras import * 
 
# 打印时间分割线
@tf.function
def printbar():
    ts = tf.timestamp()
    today_ts = ts%(24*60*60)
 
    hour = tf.cast(today_ts//3600+8,tf.int32)%tf.constant(24)
    minite = tf.cast((today_ts%3600)//60,tf.int32)
    second = tf.cast(tf.floor(today_ts%60),tf.int32)
 
    def timeformat(m):
        if tf.strings.length(tf.strings.format("{}",m))==1:
            return(tf.strings.format("0{}",m))
        else:
            return(tf.strings.format("{}",m))
 
    timestring = tf.strings.join([timeformat(hour),timeformat(minite),
                timeformat(second)],separator = ":")
    tf.print("=========="*8,end = "")
    tf.print(timestring)
 
MAX_LEN = 300
BATCH_SIZE = 32
(x_train,y_train),(x_test,y_test) = datasets.reuters.load_data()
x_train = preprocessing.sequence.pad_sequences(x_train,maxlen=MAX_LEN)
x_test = preprocessing.sequence.pad_sequences(x_test,maxlen=MAX_LEN)
 
MAX_WORDS = x_train.max()+1
CAT_NUM = y_train.max()+1
 
ds_train = tf.data.Dataset.from_tensor_slices((x_train,y_train)) 
          .shuffle(buffer_size = 1000).batch(BATCH_SIZE) 
          .prefetch(tf.data.experimental.AUTOTUNE).cache()
 
ds_test = tf.data.Dataset.from_tensor_slices((x_test,y_test)) 
          .shuffle(buffer_size = 1000).batch(BATCH_SIZE) 
          .prefetch(tf.data.experimental.AUTOTUNE).cache()

tf.keras.backend.clear_session()
def create_model():
 
    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(CAT_NUM,activation = "softmax"))
    return(model)
 
def compile_model(model):
    model.compile(optimizer=optimizers.Nadam(),
                loss=losses.SparseCategoricalCrossentropy(),
                metrics=[metrics.SparseCategoricalAccuracy(),metrics.SparseTopKCategoricalAccuracy(5)]) 
    return(model)
 
model = create_model()
model.summary()
model = compile_model(model)

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None, 300, 7)            216874    
_________________________________________________________________
conv1d (Conv1D)              (None, 296, 64)           2304      
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 148, 64)           0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 146, 32)           6176      
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 73, 32)            0         
_________________________________________________________________
flatten (Flatten)            (None, 2336)              0         
_________________________________________________________________
dense (Dense)                (None, 46)                107502    
=================================================================
Total params: 332,856
Trainable params: 332,856
Non-trainable params: 0
_________________________________________________________________

history = model.fit(ds_train,validation_data = ds_test,epochs = 10)

Epoch 1/10
281/281 [==============================] - 8s 28ms/step - loss: 1.9854 - sparse_categorical_accuracy: 0.4876 - sparse_top_k_categorical_accuracy: 0.7488 - val_loss: 1.6438 - val_sparse_categorical_accuracy: 0.5841 - val_sparse_top_k_categorical_accuracy: 0.7636
Epoch 2/10
281/281 [==============================] - 8s 28ms/step - loss: 1.4446 - sparse_categorical_accuracy: 0.6294 - sparse_top_k_categorical_accuracy: 0.8037 - val_loss: 1.5316 - val_sparse_categorical_accuracy: 0.6126 - val_sparse_top_k_categorical_accuracy: 0.7925
Epoch 3/10
281/281 [==============================] - 8s 28ms/step - loss: 1.1883 - sparse_categorical_accuracy: 0.6906 - sparse_top_k_categorical_accuracy: 0.8549 - val_loss: 1.6185 - val_sparse_categorical_accuracy: 0.6278 - val_sparse_top_k_categorical_accuracy: 0.8019
Epoch 4/10
281/281 [==============================] - 8s 28ms/step - loss: 0.9406 - sparse_categorical_accuracy: 0.7546 - sparse_top_k_categorical_accuracy: 0.9057 - val_loss: 1.7211 - val_sparse_categorical_accuracy: 0.6153 - val_sparse_top_k_categorical_accuracy: 0.8041
Epoch 5/10
281/281 [==============================] - 8s 29ms/step - loss: 0.7207 - sparse_categorical_accuracy: 0.8108 - sparse_top_k_categorical_accuracy: 0.9404 - val_loss: 1.9749 - val_sparse_categorical_accuracy: 0.6233 - val_sparse_top_k_categorical_accuracy: 0.7996
Epoch 6/10
281/281 [==============================] - 8s 28ms/step - loss: 0.5558 - sparse_categorical_accuracy: 0.8540 - sparse_top_k_categorical_accuracy: 0.9643 - val_loss: 2.2560 - val_sparse_categorical_accuracy: 0.6269 - val_sparse_top_k_categorical_accuracy: 0.7947
Epoch 7/10
281/281 [==============================] - 8s 28ms/step - loss: 0.4438 - sparse_categorical_accuracy: 0.8916 - sparse_top_k_categorical_accuracy: 0.9781 - val_loss: 2.4731 - val_sparse_categorical_accuracy: 0.6238 - val_sparse_top_k_categorical_accuracy: 0.7965
Epoch 8/10
281/281 [==============================] - 8s 29ms/step - loss: 0.3710 - sparse_categorical_accuracy: 0.9086 - sparse_top_k_categorical_accuracy: 0.9837 - val_loss: 2.6960 - val_sparse_categorical_accuracy: 0.6175 - val_sparse_top_k_categorical_accuracy: 0.7939
Epoch 9/10
281/281 [==============================] - 8s 28ms/step - loss: 0.3201 - sparse_categorical_accuracy: 0.9203 - sparse_top_k_categorical_accuracy: 0.9894 - val_loss: 3.1160 - val_sparse_categorical_accuracy: 0.6193 - val_sparse_top_k_categorical_accuracy: 0.7898
Epoch 10/10
281/281 [==============================] - 8s 28ms/step - loss: 0.2827 - sparse_categorical_accuracy: 0.9262 - sparse_top_k_categorical_accuracy: 0.9922 - val_loss: 2.9516 - val_sparse_categorical_accuracy: 0.6264 - val_sparse_top_k_categorical_accuracy: 0.7974

tf.keras.backend.clear_session()
 
def create_model():
    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(CAT_NUM,activation = "softmax"))
    return(model)
 
def compile_model(model):
    model.compile(optimizer=optimizers.Nadam(),
                loss=losses.SparseCategoricalCrossentropy(),
                metrics=[metrics.SparseCategoricalAccuracy(),metrics.SparseTopKCategoricalAccuracy(5)]) 
    return(model)
 
model = create_model()
model.summary()
model = compile_model(model)

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None, 300, 7)            216874    
_________________________________________________________________
conv1d (Conv1D)              (None, 296, 64)           2304      
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 148, 64)           0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 146, 32)           6176      
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 73, 32)            0         
_________________________________________________________________
flatten (Flatten)            (None, 2336)              0         
_________________________________________________________________
dense (Dense)                (None, 46)                107502    
=================================================================
Total params: 332,856
Trainable params: 332,856
Non-trainable params: 0
_________________________________________________________________

def train_model(model,ds_train,ds_valid,epoches):
 
    for epoch in tf.range(1,epoches+1):
        model.reset_metrics()
 
        # 在后期降低学习率
        if epoch == 5:
            model.optimizer.lr.assign(model.optimizer.lr/2.0)
            tf.print("Lowering optimizer Learning Rate...nn")
 
        for x, y in ds_train:
            train_result = model.train_on_batch(x, y)
 
        for x, y in ds_valid:
            valid_result = model.test_on_batch(x, y,reset_metrics=False)
 
        if epoch%1 ==0:
            printbar()
            tf.print("epoch = ",epoch)
            print("train:",dict(zip(model.metrics_names,train_result)))
            print("valid:",dict(zip(model.metrics_names,valid_result)))
            print("")
train_model(model,ds_train,ds_test,10)

================================================================================11:49:43
epoch =  1
train: {'loss': 2.0567171573638916, 'sparse_categorical_accuracy': 0.4545454680919647, 'sparse_top_k_categorical_accuracy': 0.6818181872367859}
valid: {'loss': 1.6894209384918213, 'sparse_categorical_accuracy': 0.5605521202087402, 'sparse_top_k_categorical_accuracy': 0.7617987394332886}

================================================================================11:49:53
epoch =  2
train: {'loss': 1.4644863605499268, 'sparse_categorical_accuracy': 0.6363636255264282, 'sparse_top_k_categorical_accuracy': 0.7727272510528564}
valid: {'loss': 1.5152910947799683, 'sparse_categorical_accuracy': 0.6157613396644592, 'sparse_top_k_categorical_accuracy': 0.7938557267189026}

================================================================================11:50:01
epoch =  3
train: {'loss': 1.0017579793930054, 'sparse_categorical_accuracy': 0.7727272510528564, 'sparse_top_k_categorical_accuracy': 0.9545454382896423}
valid: {'loss': 1.5588842630386353, 'sparse_categorical_accuracy': 0.6228851079940796, 'sparse_top_k_categorical_accuracy': 0.8058770895004272}

================================================================================11:50:10
epoch =  4
train: {'loss': 0.6004871726036072, 'sparse_categorical_accuracy': 0.9090909361839294, 'sparse_top_k_categorical_accuracy': 1.0}
valid: {'loss': 1.7447566986083984, 'sparse_categorical_accuracy': 0.6233303546905518, 'sparse_top_k_categorical_accuracy': 0.8174532651901245}

Lowering optimizer Learning Rate...


================================================================================11:50:19
epoch =  5
train: {'loss': 0.3866238594055176, 'sparse_categorical_accuracy': 0.9545454382896423, 'sparse_top_k_categorical_accuracy': 1.0}
valid: {'loss': 1.8871253728866577, 'sparse_categorical_accuracy': 0.6308993697166443, 'sparse_top_k_categorical_accuracy': 0.816117525100708}

================================================================================11:50:28
epoch =  6
train: {'loss': 0.27341774106025696, 'sparse_categorical_accuracy': 0.9545454382896423, 'sparse_top_k_categorical_accuracy': 1.0}
valid: {'loss': 2.0595862865448, 'sparse_categorical_accuracy': 0.6273375153541565, 'sparse_top_k_categorical_accuracy': 0.8089937567710876}

================================================================================11:50:37
epoch =  7
train: {'loss': 0.1923554539680481, 'sparse_categorical_accuracy': 0.9545454382896423, 'sparse_top_k_categorical_accuracy': 1.0}
valid: {'loss': 2.2238168716430664, 'sparse_categorical_accuracy': 0.6251112818717957, 'sparse_top_k_categorical_accuracy': 0.8085485100746155}

================================================================================11:50:46
epoch =  8
train: {'loss': 0.12688547372817993, 'sparse_categorical_accuracy': 0.9545454382896423, 'sparse_top_k_categorical_accuracy': 1.0}
valid: {'loss': 2.3778438568115234, 'sparse_categorical_accuracy': 0.6175423264503479, 'sparse_top_k_categorical_accuracy': 0.8072128295898438}

================================================================================11:50:55
epoch =  9
train: {'loss': 0.08024053275585175, 'sparse_categorical_accuracy': 0.9545454382896423, 'sparse_top_k_categorical_accuracy': 1.0}
valid: {'loss': 2.501840829849243, 'sparse_categorical_accuracy': 0.6135351657867432, 'sparse_top_k_categorical_accuracy': 0.8081033229827881}

================================================================================11:51:04
epoch =  10
train: {'loss': 0.05211604759097099, 'sparse_categorical_accuracy': 1.0, 'sparse_top_k_categorical_accuracy': 1.0}
valid: {'loss': 2.61771559715271, 'sparse_categorical_accuracy': 0.6126446723937988, 'sparse_top_k_categorical_accuracy': 0.8085485100746155}

tf.keras.backend.clear_session()
 
def create_model():
 
    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(CAT_NUM,activation = "softmax"))
    return(model)
 
model = create_model()
model.summary()
optimizer = optimizers.Nadam()
loss_func = losses.SparseCategoricalCrossentropy()
 
train_loss = metrics.Mean(name='train_loss')
train_metric = metrics.SparseCategoricalAccuracy(name='train_accuracy')
 
valid_loss = metrics.Mean(name='valid_loss')
valid_metric = metrics.SparseCategoricalAccuracy(name='valid_accuracy')
 
@tf.function
def train_step(model, features, labels):
    with tf.GradientTape() as tape:
        predictions = model(features,training = True)
        loss = loss_func(labels, predictions)
    gradients = tape.gradient(loss, model.trainable_variables)
    optimizer.apply_gradients(zip(gradients, model.trainable_variables))
 
    train_loss.update_state(loss)
    train_metric.update_state(labels, predictions)
 
 
@tf.function
def valid_step(model, features, labels):
    predictions = model(features)
    batch_loss = loss_func(labels, predictions)
    valid_loss.update_state(batch_loss)
    valid_metric.update_state(labels, predictions)
 
 
def train_model(model,ds_train,ds_valid,epochs):
    for epoch in tf.range(1,epochs+1):
 
        for features, labels in ds_train:
            train_step(model,features,labels)
 
        for features, labels in ds_valid:
            valid_step(model,features,labels)
 
        logs = 'Epoch={},Loss:{},Accuracy:{},Valid Loss:{},Valid Accuracy:{}'
 
        if epoch%1 ==0:
            printbar()
            tf.print(tf.strings.format(logs,
            (epoch,train_loss.result(),train_metric.result(),valid_loss.result(),valid_metric.result())))
            tf.print("")
 
        train_loss.reset_states()
        valid_loss.reset_states()
        train_metric.reset_states()
        valid_metric.reset_states()
 
train_model(model,ds_train,ds_test,10)

Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
embedding (Embedding)        (None, 300, 7)            216874    
_________________________________________________________________
conv1d (Conv1D)              (None, 296, 64)           2304      
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 148, 64)           0         
_________________________________________________________________
conv1d_1 (Conv1D)            (None, 146, 32)           6176      
_________________________________________________________________
max_pooling1d_1 (MaxPooling1 (None, 73, 32)            0         
_________________________________________________________________
flatten (Flatten)            (None, 2336)              0         
_________________________________________________________________
dense (Dense)                (None, 46)                107502    
=================================================================
Total params: 332,856
Trainable params: 332,856
Non-trainable params: 0
_________________________________________________________________

================================================================================11:52:04
Epoch=1,Loss:2.02564383,Accuracy:0.464707196,Valid Loss:1.68035507,Valid Accuracy:0.55921638

================================================================================11:52:11
Epoch=2,Loss:1.48306167,Accuracy:0.612781107,Valid Loss:1.52322364,Valid Accuracy:0.606411397

================================================================================11:52:18
Epoch=3,Loss:1.20491719,Accuracy:0.677243352,Valid Loss:1.56225574,Valid Accuracy:0.624666095

================================================================================11:52:25
Epoch=4,Loss:0.944778264,Accuracy:0.749387681,Valid Loss:1.7202934,Valid Accuracy:0.620658934

================================================================================11:52:32
Epoch=5,Loss:0.701866329,Accuracy:0.817635298,Valid Loss:1.97179747,Valid Accuracy:0.61843276

================================================================================11:52:39
Epoch=6,Loss:0.531810164,Accuracy:0.866844773,Valid Loss:2.25338316,Valid Accuracy:0.605075717

================================================================================11:52:46
Epoch=7,Loss:0.425013304,Accuracy:0.896236897,Valid Loss:2.47035336,Valid Accuracy:0.601068556

================================================================================11:52:53
Epoch=8,Loss:0.355143964,Accuracy:0.915609,Valid Loss:2.67822,Valid Accuracy:0.591718614

================================================================================11:53:00
Epoch=9,Loss:0.30812338,Accuracy:0.92785573,Valid Loss:2.86121941,Valid Accuracy:0.583704352

================================================================================11:53:07
Epoch=10,Loss:0.275565386,Accuracy:0.934535742,Valid Loss:2.99354172,Valid Accuracy:0.579252