【tensorflow2.0】处理图片数据-cifar2分类

import tensorflow as tf 
from tensorflow.keras import datasets,layers,models
 
BATCH_SIZE = 100
 
def load_image(img_path,size = (32,32)):
    label = tf.constant(1,tf.int8) if tf.strings.regex_full_match(img_path,".*/automobile/.*") \
            else tf.constant(0,tf.int8)
    img = tf.io.read_file(img_path)
    img = tf.image.decode_jpeg(img) #注意此处为jpeg格式
    img = tf.image.resize(img,size)/255.0
    return(img,label)
 
# 使用并行化预处理num_parallel_calls 和预存数据prefetch来提升性能
ds_train = tf.data.Dataset.list_files("./data/cifar2/train/*/*.jpg") \
           .map(load_image, num_parallel_calls=tf.data.experimental.AUTOTUNE) \
           .shuffle(buffer_size = 1000).batch(BATCH_SIZE) \
           .prefetch(tf.data.experimental.AUTOTUNE)  
 
ds_test = tf.data.Dataset.list_files("./data/cifar2/test/*/*.jpg") \
           .map(load_image, num_parallel_calls=tf.data.experimental.AUTOTUNE) \
           .batch(BATCH_SIZE) \
           .prefetch(tf.data.experimental.AUTOTUNE) 

for x,y in ds_train.take(1):
    print(x.shape,y.shape)

tf.keras.backend.clear_session() #清空会话
 
inputs = layers.Input(shape=(32,32,3))
x = layers.Conv2D(32,kernel_size=(3,3))(inputs)
x = layers.MaxPool2D()(x)
x = layers.Conv2D(64,kernel_size=(5,5))(x)
x = layers.MaxPool2D()(x)
x = layers.Dropout(rate=0.1)(x)
x = layers.Flatten()(x)
x = layers.Dense(32,activation='relu')(x)
outputs = layers.Dense(1,activation = 'sigmoid')(x)
 
model = models.Model(inputs = inputs,outputs = outputs)
 
model.summary()

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)
 
model.compile(
        optimizer=tf.keras.optimizers.Adam(learning_rate=0.001),
        loss=tf.keras.losses.binary_crossentropy,
        metrics=["accuracy"]
    )
 
history = model.fit(ds_train,epochs= 10,validation_data=ds_test,
                    callbacks = [tensorboard_callback],workers = 4)

Epoch 1/10
100/100 [==============================] - 2205s 22s/step - loss: 0.4632 - accuracy: 0.7786 - val_loss: 0.3375 - val_accuracy: 0.8620
Epoch 2/10
100/100 [==============================] - 11s 110ms/step - loss: 0.3346 - accuracy: 0.8565 - val_loss: 0.2617 - val_accuracy: 0.8965
Epoch 3/10
100/100 [==============================] - 11s 111ms/step - loss: 0.2687 - accuracy: 0.8883 - val_loss: 0.2183 - val_accuracy: 0.9165
Epoch 4/10
100/100 [==============================] - 11s 110ms/step - loss: 0.2171 - accuracy: 0.9128 - val_loss: 0.1811 - val_accuracy: 0.9280
Epoch 5/10
100/100 [==============================] - 11s 114ms/step - loss: 0.1860 - accuracy: 0.9268 - val_loss: 0.1798 - val_accuracy: 0.9265
Epoch 6/10
100/100 [==============================] - 11s 112ms/step - loss: 0.1646 - accuracy: 0.9358 - val_loss: 0.1818 - val_accuracy: 0.9260
Epoch 7/10
100/100 [==============================] - 11s 113ms/step - loss: 0.1443 - accuracy: 0.9426 - val_loss: 0.1740 - val_accuracy: 0.9290
Epoch 8/10
100/100 [==============================] - 11s 113ms/step - loss: 0.1301 - accuracy: 0.9469 - val_loss: 0.1635 - val_accuracy: 0.9325
Epoch 9/10
100/100 [==============================] - 11s 112ms/step - loss: 0.1096 - accuracy: 0.9585 - val_loss: 0.1758 - val_accuracy: 0.9315
Epoch 10/10
100/100 [==============================] - 11s 113ms/step - loss: 0.0961 - accuracy: 0.9628 - val_loss: 0.1595 - val_accuracy: 0.9415

# %load_ext tensorboard
# %tensorboard --logdir ./data/keras_model
from tensorboard import notebook
notebook.list() 
# 在tensorboard中查看模型
notebook.start("--logdir ./data/keras_model")

import pandas as pd 
dfhistory = pd.DataFrame(history.history)
dfhistory.index = range(1,len(dfhistory) + 1)
dfhistory.index.name = 'epoch'
dfhistory 

%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,"loss")
plot_metric(history,"accuracy")

# 可以使用evaluate对数据进行评估
val_loss,val_accuracy = model.evaluate(ds_test,workers=4)
print(val_loss,val_accuracy)

model.predict(ds_test)

array([[1.1052408e-01],
       [3.4282297e-02],
       [2.7046111e-04],
       ...,
       [2.7544077e-03],
       [3.4654222e-04],
       [9.9993896e-01]], dtype=float32)

for x,y in ds_test.take(1):
    print(model.predict_on_batch(x[0:20]))

[[9.8728174e-01]
 [2.0267103e-02]
 [9.0806475e-03]
 [9.9996555e-01]
 [4.5376007e-02]
 [1.2818890e-03]
 [1.8698535e-03]
 [2.2900696e-03]
 [8.6169255e-01]
 [6.2768459e-06]
 [1.2383183e-02]
 [4.3949869e-02]
 [7.9778886e-01]
 [9.9822074e-01]
 [9.9993134e-01]
 [8.6685091e-02]
 [3.7480664e-02]
 [9.9652690e-01]
 [9.2210865e-01]
 [1.6160560e-03]]

# 保存权重，该方式仅仅保存权重张量
model.save_weights('./data/tf_model_weights.ckpt',save_format = "tf")
# 保存模型结构与模型参数到文件,该方式保存的模型具有跨平台性便于部署
 
model.save('./data/tf_model_savedmodel', save_format="tf")
print('export saved model.')
 
model_loaded = tf.keras.models.load_model('./data/tf_model_savedmodel')
model_loaded.evaluate(ds_test)