tensorflow2.x第五篇--回顾

watch函数，测试gpu，numpy实现线性一元线性回归，手写数字识别，前向传播，计算预测准确度，keras高层API，自定义数据集训练

• 自动求导时当参数不是TensorFlow变量类型时使用watch函数

import tensorflow as tf


x = tf.constant(1.)
a = tf.constant(2.)
b = tf.constant(3.)
c = tf.constant(4.)

with tf.GradientTape() as tape:
    #当参数不是变量类型
    tape.watch([a,b,c])
    y = a**2*x + b*x + c

[dy_da, dy_db, dy_dc]= tape.gradient(y,[a,b,c])
print(dy_da, dy_db, dy_dc)

• 选择cpu，gpu进行运算

import tensorflow as tf
import timeit


with tf.device('/cpu:0'):
	cpu_a = tf.random.normal([10000, 1000])
	cpu_b = tf.random.normal([1000, 2000])
	print(cpu_a.device, cpu_b.device)

with tf.device('/gpu:0'):
	gpu_a = tf.random.normal([10000, 1000])
	gpu_b = tf.random.normal([1000, 2000])
	print(gpu_a.device, gpu_b.device)

def cpu_run():
	with tf.device('/cpu:0'):
		c = tf.matmul(cpu_a, cpu_b)
	return c 

def gpu_run():
	with tf.device('/gpu:0'):
		c = tf.matmul(gpu_a, gpu_b)
	return c 


# warm up
cpu_time = timeit.timeit(cpu_run, number=10)
gpu_time = timeit.timeit(gpu_run, number=10)
print('warmup:', cpu_time, gpu_time)


cpu_time = timeit.timeit(cpu_run, number=10)
gpu_time = timeit.timeit(gpu_run, number=10)
print('run time:', cpu_time, gpu_time)

• 测试gpu可使用，去除无用的日志

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf

a = tf.constant(1.)
b = tf.constant(2.)
print(a+b)

print('GPU:', tf.test.is_gpu_available())

• numpy实现线性一元线性回归

import numpy as np



#Step1. Compute Loss
# y = wx + b
def compute_error_for_line_given_points(b, w, points):
    totalError = 0
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        # computer mean-squared-error
        totalError += (y - (w * x + b)) ** 2
    # average loss for each point
    return totalError / float(len(points))


#Step2.Compute Gradient and update
def step_gradient(b_current, w_current, points, learningRate):
    b_gradient = 0
    w_gradient = 0
    N = float(len(points))
    for i in range(0, len(points)):
        x = points[i, 0]
        y = points[i, 1]
        # grad_b = 2(wx+b-y)
        b_gradient += (2/N) * ((w_current * x + b_current) - y)
        # grad_w = 2(wx+b-y)*x
        w_gradient += (2/N) * x * ((w_current * x + b_current) - y)
    # update w'
    new_b = b_current - (learningRate * b_gradient)
    new_w = w_current - (learningRate * w_gradient)
    return [new_b, new_w]

#Step3.Set w=w’ and loop
def gradient_descent_runner(points, starting_b, starting_w, learning_rate, num_iterations):
    b = starting_b
    w = starting_w
    # update for several times
    for i in range(num_iterations):
        b, w = step_gradient(b, w, np.array(points), learning_rate)
    return [b, w]


def run():
	
    points = np.genfromtxt("data.csv", delimiter=",")
    '''
    47.475639634786098,71.546632233567777
    59.813207869512318,87.230925133687393
    55.142188413943821,78.211518270799232
    52.211796692214001,79.64197304980874
    39.299566694317065,59.171489321869508
    48.10504169176825,75.331242297063056
    52.550014442733818,71.300879886850353
    '''
    learning_rate = 0.0001
    initial_b = 0 # initial y-intercept guess
    initial_w = 0 # initial slope guess
    num_iterations = 1000
    print("Starting gradient descent at b = {0}, w = {1}, error = {2}"
          .format(initial_b, initial_w,
                  compute_error_for_line_given_points(initial_b, initial_w, points))
          )
    print("Running...")
    [b, w] = gradient_descent_runner(points, initial_b, initial_w, learning_rate, num_iterations)
    print("After {0} iterations b = {1}, w = {2}, error = {3}".
          format(num_iterations, b, w,
                 compute_error_for_line_given_points(b, w, points))
          )

if __name__ == '__main__':
    run()
    
    out:
Starting gradient descent at b = 0, w = 0, error = 5565.107834483211
Running...
After 1000 iterations b = 0.08893651993741346, w = 1.4777440851894448, error = 112.61481011613473

• 手写数字识别

import  os
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

import  tensorflow as tf
from    tensorflow import keras
from    tensorflow.keras import layers, optimizers, datasets

(x, y), (x_val, y_val) = datasets.mnist.load_data() 
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)
y = tf.one_hot(y, depth=10)
print(x.shape, y.shape)
train_dataset = tf.data.Dataset.from_tensor_slices((x, y))
train_dataset = train_dataset.batch(200)

model = keras.Sequential([ 
    layers.Dense(512, activation='relu'),
    layers.Dense(256, activation='relu'),
    layers.Dense(10)])

optimizer = optimizers.SGD(learning_rate=0.001)


def train_epoch(epoch):
    # Step4.loop
    for step, (x, y) in enumerate(train_dataset):
        with tf.GradientTape() as tape:
            # [b, 28, 28] => [b, 784]
            x = tf.reshape(x, (-1, 28*28))
            # Step1. compute output
            # [b, 784] => [b, 10]
            out = model(x)
            # Step2. compute loss
            loss = tf.reduce_sum(tf.square(out - y)) / x.shape[0]
        # Step3. optimize and update w1, w2, w3, b1, b2, b3
        grads = tape.gradient(loss, model.trainable_variables)
        # w' = w - lr * grad
        optimizer.apply_gradients(zip(grads, model.trainable_variables))

        if step % 100 == 0:
            print(epoch, step, 'loss:', loss.numpy())

def train():

    for epoch in range(30):

        train_epoch(epoch)

if __name__ == '__main__':
    train()

• 前向传播

import  tensorflow as tf
from    tensorflow import keras
from    tensorflow.keras import datasets
import  os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

# x: [60k, 28, 28],
# y: [60k]
(x, y), _ = datasets.mnist.load_data()
# x: [0~255] => [0~1.]
x = tf.convert_to_tensor(x, dtype=tf.float32) / 255.
y = tf.convert_to_tensor(y, dtype=tf.int32)

print(x.shape, y.shape, x.dtype, y.dtype)
print(tf.reduce_min(x), tf.reduce_max(x))
print(tf.reduce_min(y), tf.reduce_max(y))


train_db = tf.data.Dataset.from_tensor_slices((x,y)).batch(128)
train_iter = iter(train_db)
sample = next(train_iter)
print('batch:', sample[0].shape, sample[1].shape)


# [b, 784] => [b, 256] => [b, 128] => [b, 10]
# [dim_in, dim_out], [dim_out]
w1 = tf.Variable(tf.random.truncated_normal([784, 256], stddev=0.1))
b1 = tf.Variable(tf.zeros([256]))
w2 = tf.Variable(tf.random.truncated_normal([256, 128], stddev=0.1))
b2 = tf.Variable(tf.zeros([128]))
w3 = tf.Variable(tf.random.truncated_normal([128, 10], stddev=0.1))
b3 = tf.Variable(tf.zeros([10]))

lr = 1e-3

for epoch in range(10): # iterate db for 10
    for step, (x, y) in enumerate(train_db): # for every batch
        # x:[128, 28, 28]
        # y: [128]

        # [b, 28, 28] => [b, 28*28]
        x = tf.reshape(x, [-1, 28*28])

        with tf.GradientTape() as tape: # tf.Variable
            # x: [b, 28*28]
            # h1 = x@w1 + b1
            # [b, 784]@[784, 256] + [256] => [b, 256] + [256] => [b, 256] + [b, 256]
            h1 = x@w1 + tf.broadcast_to(b1, [x.shape[0], 256])
            h1 = tf.nn.relu(h1)
            # [b, 256] => [b, 128]
            h2 = h1@w2 + b2
            h2 = tf.nn.relu(h2)
            # [b, 128] => [b, 10]
            out = h2@w3 + b3

            # compute loss
            # out: [b, 10]
            # y: [b] => [b, 10]
            y_onehot = tf.one_hot(y, depth=10)

            # mse = mean(sum(y-out)^2)
            # [b, 10]
            loss = tf.square(y_onehot - out)
            # mean: scalar
            loss = tf.reduce_mean(loss)

        # compute gradients
        grads = tape.gradient(loss, [w1, b1, w2, b2, w3, b3])
        # print(grads)
        # w1 = w1 - lr * w1_grad
        w1.assign_sub(lr * grads[0])
        b1.assign_sub(lr * grads[1])
        w2.assign_sub(lr * grads[2])
        b2.assign_sub(lr * grads[3])
        w3.assign_sub(lr * grads[4])
        b3.assign_sub(lr * grads[5])


        if step % 100 == 0:
            print(epoch, step, 'loss:', float(loss))

• 计算预测准确度

import tensorflow as tf
import os
#去掉无用的警告
os.environ['TF_CPP_MIN_LOG_LEVEL']='2'

def accuracy(output,target,topk=(1,)):

    maxk=max(topk)
    #统计一组label个数作为一个批次
    batch_size = target.shape[0]
    #返回output最内一层前k个元素对应的索引
    pred = tf.math.top_k(output,maxk).indices
    #将这个批次的标签纵向扩展批次大小
    pred = tf.transpose(pred,perm=[1,0])
    target_ = tf.broadcast_to(target,pred.shape)
    #将对应的类别比较
    correct = tf.equal(pred,target_)
    res = []
    for k in topk:
        correct_k = tf.cast(tf.reshape(correct[:k], [-1]), dtype=tf.float32)
        correct_k = tf.reduce_sum(correct_k)
        acc = float(correct_k * (100.0 / batch_size))
        res.append(acc)
    return res


output = tf.random.normal([10,6])
output = tf.math.softmax(output,axis=1)
target = tf.random.uniform([10],maxval=6,dtype=tf.int32)
print('prob:', output.numpy())
pred = tf.argmax(output, axis=1)
print('pred:', pred.numpy())
print('label:', target.numpy())
acc = accuracy(output, target, topk=(1,2,3,4,5,6))
print('top-1-6 acc:', acc)

• keras高层API

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


def preprocess(x, y):

    x = tf.cast(x, dtype=tf.float32) / 255.
    y = tf.cast(y, dtype=tf.int32)

    return x,y


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))
db = db.map(preprocess).shuffle(60000).batch(batchsz).repeat(10)

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




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()

optimizer = optimizers.Adam(lr=0.01)

acc_meter = metrics.Accuracy()
loss_meter = metrics.Mean()


for step, (x,y) in enumerate(db):

    with tf.GradientTape() as tape:
        # [b, 28, 28] => [b, 784]
        x = tf.reshape(x, (-1, 28*28))
        # [b, 784] => [b, 10]
        out = network(x)
        # [b] => [b, 10]
        y_onehot = tf.one_hot(y, depth=10) 
        # [b]
        loss = tf.reduce_mean(tf.losses.categorical_crossentropy(y_onehot, out, from_logits=True))

        loss_meter.update_state(loss)

 

    grads = tape.gradient(loss, network.trainable_variables)
    optimizer.apply_gradients(zip(grads, network.trainable_variables))


    if step % 100 == 0:

        print(step, 'loss:', loss_meter.result().numpy()) 
        loss_meter.reset_states()


    # evaluate
    if step % 500 == 0:
        total, total_correct = 0., 0
        acc_meter.reset_states()

        for step, (x, y) in enumerate(ds_val): 
            # [b, 28, 28] => [b, 784]
            x = tf.reshape(x, (-1, 28*28))
            # [b, 784] => [b, 10]
            out = network(x) 


            # [b, 10] => [b] 
            pred = tf.argmax(out, axis=1) 
            pred = tf.cast(pred, dtype=tf.int32)
            # bool type 
            correct = tf.equal(pred, y)
            # bool tensor => int tensor => numpy
            total_correct += tf.reduce_sum(tf.cast(correct, dtype=tf.int32)).numpy()
            total += x.shape[0]
            
            acc_meter.update_state(y, pred)

        print('Evaluate Acc:', total_correct/total, acc_meter.result().numpy())

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


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


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))
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)


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()




network.compile(optimizer=optimizers.Adam(lr=0.01),
		loss=tf.losses.CategoricalCrossentropy(from_logits=True),
		metrics=['accuracy']
	)

network.fit(db, epochs=5, validation_data=ds_val, validation_freq=2)
 
network.evaluate(ds_val)

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)

#自定义层
import  tensorflow as tf
from    tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
from 	tensorflow import keras

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


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))
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)


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()


class MyDense(layers.Layer):

	def __init__(self, inp_dim, outp_dim):
		super(MyDense, self).__init__()

		self.kernel = self.add_weight('w', [inp_dim, outp_dim])
		self.bias = self.add_weight('b', [outp_dim])

	def call(self, inputs, training=None):

		out = inputs @ self.kernel + self.bias

		return out 

class MyModel(keras.Model):

	def __init__(self):
		super(MyModel, self).__init__()

		self.fc1 = MyDense(28*28, 256)
		self.fc2 = MyDense(256, 128)
		self.fc3 = MyDense(128, 64)
		self.fc4 = MyDense(64, 32)
		self.fc5 = MyDense(32, 10)

	def call(self, inputs, training=None):

		x = self.fc1(inputs)
		x = tf.nn.relu(x)
		x = self.fc2(x)
		x = tf.nn.relu(x)
		x = self.fc3(x)
		x = tf.nn.relu(x)
		x = self.fc4(x)
		x = tf.nn.relu(x)
		x = self.fc5(x) 

		return x


network = MyModel()


network.compile(optimizer=optimizers.Adam(lr=0.01),
		loss=tf.losses.CategoricalCrossentropy(from_logits=True),
		metrics=['accuracy']
	)

network.fit(db, epochs=5, validation_data=ds_val,
              validation_freq=2)
 
network.evaluate(ds_val)

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)

• 自定义训练集

#制作数据集并在Tensorboard中监控
import  os, glob
import  random, csv

import tensorflow as tf

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

def load_csv(root,filename,name2label):
    if not os.path.exists(os.path.join(root,filename)):
        images = []
        for name in name2label.keys():
            images += glob.glob(os.path.join(root,name,'*.jpeg'))
            images += glob.glob(os.path.join(root,name,'*.jpg'))
            images += glob.glob(os.path.join(root,name,'*.png'))
        print(len(images))
        random.shuffle(images)

        with open(os.path.join(root,filename),mode='w',newline='') as f:
            writer = csv.writer(f)
            for image in images:
                name = os.path.split(os.sep)[-2]
                label = name2label[name]
                writer.writerow([image,label])
            print('Written into csv file')
    images,labels = [],[]
    with open(os.path.join(root,filename)) as f:
        reader = csv.reader(f)
        for row in reader:
            image,label = row
            images.append(image)
            labels.append(int(label))
    assert len(images)==len(labels)
    return images,labels

def load_pokemon(root,mode='train'):
    name2label = {}
    for name in sorted(os.listdir(os.path.join(root))):
        if not os.path.exists(os.path.join(root,name)):
            continue
        name2label[name] = len(name2label.keys())

    images,labels = load_csv(root,'images.csv',name2label)
    if mode == 'train':  # 60%
        images = images[:int(0.6 * len(images))]
        labels = labels[:int(0.6 * len(labels))]
    elif mode == 'val':  # 20% = 60%->80%
        images = images[int(0.6 * len(images)):int(0.8 * len(images))]
        labels = labels[int(0.6 * len(labels)):int(0.8 * len(labels))]
    else:  # 20% = 80%->100%
        images = images[int(0.8 * len(images)):]
        labels = labels[int(0.8 * len(labels)):]

    return images, labels, name2label


img_mean = tf.constant([0.485, 0.456, 0.406])
img_std = tf.constant([0.229, 0.224, 0.225])
def normalize(x,mean=img_mean,std=img_std):
    x = (x-mean)/std
    return x

def denormalize(x,mean=img_mean,std=img_std):
    x = x*std+mean
    return x

def preprocess(x,y):
    x = tf.io.read_file(x)
    x = tf.image.decode_jpeg(x,channels=3)
    x = tf.image.resize(x,[244,244])
    x = tf.image.random_flip_left_right(x)
    x = tf.image.random_crop(x,[224,224,3])
    x = tf.cast(x,tf.float32)
    x = normalize(x)
    y = tf.convert_to_tensor(y)
    y = tf.one_hot(y, depth=5)

    return x,y
if __name__ == '__main__':
    import time

    images, labels, table = load_pokemon('pokemon', 'train')
    print('images', len(images), images)
    print('labels', len(labels), labels)
    print(table)

    # images: string path
    # labels: number
    db = tf.data.Dataset.from_tensor_slices((images, labels))
    db = db.shuffle(1000).map(preprocess).batch(32)

    writter = tf.summary.create_file_writer('logs')

    for step, (x, y) in enumerate(db):
        # x: [32, 224, 224, 3]
        # y: [32]
        with writter.as_default():
            x = denormalize(x)
            tf.summary.image('img', x, step=step, max_outputs=9)
            time.sleep(5)

#resnet网络构建
import  os
import  tensorflow as tf
import  numpy as np
from    tensorflow import keras
from    tensorflow.keras import layers



tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')



class ResnetBlock(keras.Model):

    def __init__(self, channels, strides=1):
        super(ResnetBlock, self).__init__()

        self.channels = channels
        self.strides = strides

        self.conv1 = layers.Conv2D(channels, 3, strides=strides,
                                   padding=[[0,0],[1,1],[1,1],[0,0]])
        self.bn1 = keras.layers.BatchNormalization()
        self.conv2 = layers.Conv2D(channels, 3, strides=1,
                                   padding=[[0,0],[1,1],[1,1],[0,0]])
        self.bn2 = keras.layers.BatchNormalization()

        if strides!=1:
            self.down_conv = layers.Conv2D(channels, 1, strides=strides, padding='valid')
            self.down_bn = tf.keras.layers.BatchNormalization()

    def call(self, inputs, training=None):
        residual = inputs

        x = self.conv1(inputs)
        x = tf.nn.relu(x)
        x = self.bn1(x, training=training)
        x = self.conv2(x)
        x = tf.nn.relu(x)
        x = self.bn2(x, training=training)

        # 残差连接
        if self.strides!=1:
            residual = self.down_conv(inputs)
            residual = tf.nn.relu(residual)
            residual = self.down_bn(residual, training=training)

        x = x + residual
        x = tf.nn.relu(x)
        return x


class ResNet(keras.Model):

    def __init__(self, num_classes, initial_filters=16, **kwargs):
        super(ResNet, self).__init__(**kwargs)

        self.stem = layers.Conv2D(initial_filters, 3, strides=3, padding='valid')

        self.blocks = keras.models.Sequential([
            ResnetBlock(initial_filters * 2, strides=3),
            ResnetBlock(initial_filters * 2, strides=1),
            # layers.Dropout(rate=0.5),

            ResnetBlock(initial_filters * 4, strides=3),
            ResnetBlock(initial_filters * 4, strides=1),

            ResnetBlock(initial_filters * 8, strides=2),
            ResnetBlock(initial_filters * 8, strides=1),

            ResnetBlock(initial_filters * 16, strides=2),
            ResnetBlock(initial_filters * 16, strides=1),
        ])

        self.final_bn = layers.BatchNormalization()
        self.avg_pool = layers.GlobalMaxPool2D()
        self.fc = layers.Dense(num_classes)

    def call(self, inputs, training=None):
        # print('x:',inputs.shape)
        out = self.stem(inputs,training=training)
        out = tf.nn.relu(out)

        # print('stem:',out.shape)

        out = self.blocks(out, training=training)
        # print('res:',out.shape)

        out = self.final_bn(out, training=training)
        # out = tf.nn.relu(out)

        out = self.avg_pool(out)

        # print('avg_pool:',out.shape)
        out = self.fc(out)

        # print('out:',out.shape)

        return out

def main():
    num_classes = 5

    resnet18 = ResNet(5)
    resnet18.build(input_shape=(4,224,224,3))
    resnet18.summary()

if __name__ == '__main__':
    main()

#train
import os

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'

import tensorflow as tf
import numpy as np
from tensorflow import keras
from tensorflow.keras import layers,optimizers,losses
from tensorflow.keras.callbacks import EarlyStopping

from pokemon import load_pokemon,normalize,denormalize,preprocess
from resnet import ResNet

batchsz = 64

# creat train db
images, labels, table = load_pokemon('pokemon',mode='train')
db_train = tf.data.Dataset.from_tensor_slices((images, labels))
db_train = db_train.shuffle(1000).map(preprocess).batch(batchsz)
# crate validation db
images2, labels2, table = load_pokemon('pokemon',mode='val')
db_val = tf.data.Dataset.from_tensor_slices((images2, labels2))
db_val = db_val.map(preprocess).batch(batchsz)
# create test db
images3, labels3, table = load_pokemon('pokemon',mode='test')
db_test = tf.data.Dataset.from_tensor_slices((images3, labels3))
db_test = db_test.map(preprocess).batch(batchsz)

resnet = keras.Sequential([
    layers.Conv2D(16, 5, 3),
    layers.MaxPool2D(3, 3),
    layers.ReLU(),
    layers.Conv2D(64, 5, 3),
    layers.MaxPool2D(2, 2),
    layers.ReLU(),
    layers.Flatten(),
    layers.Dense(64),
    layers.ReLU(),
    layers.Dense(5)
])

resnet = ResNet(5)
resnet.build(input_shape=(4,224,224,3))
resnet.summary()

early_stopping = EarlyStopping(
    monitor='val_accuracy',
    min_delta=0.001,
    patience=5
)

resnet.compile(optimizer=optimizers.Adam(0.001),
               loss=losses.CategoricalCrossentropy(from_logits=True),
               metrics=['accuracy'])
resnet.fit(db_train,validation_data=db_val,validation_freq=1,epochs=100,callbacks=[early_stopping])
resnet.evaluate(db_test)

#迁移学习
import  os
import  tensorflow as tf
import  numpy as np
from    tensorflow import keras
from    tensorflow.keras import layers,optimizers,losses
from    tensorflow.keras.callbacks import EarlyStopping

tf.random.set_seed(22)
np.random.seed(22)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
assert tf.__version__.startswith('2.')


from pokemon import  load_pokemon,normalize



def preprocess(x,y):
    # x: 图片的路径，y：图片的数字编码
    x = tf.io.read_file(x)
    x = tf.image.decode_jpeg(x, channels=3) # RGBA
    x = tf.image.resize(x, [244, 244])

    # x = tf.image.random_flip_left_right(x)
    x = tf.image.random_flip_up_down(x)
    x = tf.image.random_crop(x, [224,224,3])

    # x: [0,255]=> -1~1
    x = tf.cast(x, dtype=tf.float32) / 255.
    x = normalize(x)
    y = tf.convert_to_tensor(y)
    y = tf.one_hot(y, depth=5)

    return x, y


batchsz = 64
# 创建训练集Datset对象
images, labels, table = load_pokemon('pokemon',mode='train')
db_train = tf.data.Dataset.from_tensor_slices((images, labels))
db_train = db_train.shuffle(1000).map(preprocess).batch(batchsz)
# 创建验证集Datset对象
images2, labels2, table = load_pokemon('pokemon',mode='val')
db_val = tf.data.Dataset.from_tensor_slices((images2, labels2))
db_val = db_val.map(preprocess).batch(batchsz)
# 创建测试集Datset对象
images3, labels3, table = load_pokemon('pokemon',mode='test')
db_test = tf.data.Dataset.from_tensor_slices((images3, labels3))
db_test = db_test.map(preprocess).batch(batchsz)

#
net = keras.applications.VGG19(weights='imagenet', include_top=False,
                               pooling='max')
net.trainable = False
newnet = keras.Sequential([
    net,
    layers.Dense(5)
])
newnet.build(input_shape=(4,224,224,3))
newnet.summary()


early_stopping = EarlyStopping(
    monitor='val_accuracy',
    min_delta=0.001,
    patience=5
)

newnet.compile(optimizer=optimizers.Adam(lr=1e-3),
               loss=losses.CategoricalCrossentropy(from_logits=True),
               metrics=['accuracy'])
newnet.fit(db_train, validation_data=db_val, validation_freq=1, epochs=100,
           callbacks=[early_stopping])
newnet.evaluate(db_test)