江苏龙网

  1. 首页 > 人文 > >

tensorflow2.0教程与操作示例( 四 )

keras 预定义了卷积神经网络结构

  • tf.keras.applications中有很多经典的卷积神经网络结构 。 VGG16、VGG19、ResNet、MobileNet等 model = tf.keras.applications.MobileNetV2() 默认的参数包括：input_shape 默认大小是2242243,3232 或7575有长款至少限制；include_top:在网络最后是否包含全连接层 ， 默认是true；weights:预训练权值 ， 默认是’imagenet‘即为当前模型载入在ImageNet数据集上预训练的权值 。 classes:分类数 ， 默认1000,修改该参数需要include_top参数为True且weights参数为None 。
实例代码import tensorflow as tfimport tensorflow_datasets as tfdsnum_batches = 1000batch_size = 50learning_rate = 0.001dataset = tfds.load("tf_flowers", split=tfds.Split.TRAIN, as_supervised=True)dataset = dataset.map(lambda img, label: (tf.image.resize(img, [224, 224]) / 255.0, label)).shuffle(1024).batch(32)model = tf.keras.applications.MobileNetV2(weights=None, classes=5)optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)for images, labels in dataset:with tf.GradientTape() as tape:labels_pred = model(images)loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=labels, y_pred=labels_pred)loss = tf.reduce_mean(loss)print("loss %f" % loss.numpy())grads = tape.gradient(loss, model.trainable_variables)optimizer.apply_gradients(grads_and_vars=zip(grads, model.trainable_variables))
循环神经网络（RNN）
  • 循环神经网络（Recurrent Neural Network, RNN）是一种适宜于处理序列数据的神经网络 ， 被广泛用于语言模型、文本生成、机器翻译等 。
示例代码# -*- coding:utf-8 -*-# /usr/bin/python'''-------------------------------------------------File Name:RNNDescription :AIM:Functions: 1. 基本原理2. 概念3. 示例代码Envs:python == 3.7pip install tensorflow==2.1.0 -iAuthor:errolDate:2020/5/215:20CodeStyle:规范,简洁,易懂,可阅读,可维护,可移植!-------------------------------------------------Change Activity:2020/5/2 : text-------------------------------------------------'''import numpy as npimport tensorflow as tfclass DataLoader(object):def __init__(self,):path = tf.keras.utils.get_file('nietzsche.txt',origin='')with open(path, encoding='utf-8') as file:self.raw_text = file.read().lower()self.chars = sorted(list(set(self.raw_text)))self.char_indices = dic((c,i) for i,c in enumerate(self.chars))self.indices_char = dict((i, c) for i, c in enumerate(self.chars))self.text = [self.char_indices[c] for c in self.raw_text]def get_batch(self, seq_length, batch_size):seq = []next_char = []for i in range(batch_size):index = np.random.randint(0, len(self.text) - seq_length)seq.append(self.text[index:index + seq_length])next_char.append(self.text[index + seq_length])return np.array(seq), np.array(next_char)# [batch_size, seq_length], [num_batch]class RNN(tf.keras.Model):def __init__(self,num_chars,batch_size,seq_length):super().__init__()self.num_chars = num_charsself.seq_length = seq_lengthself.batch_size = batch_sizeself.cell = tf.keras.layers.LSTMCell(units=256)self.dense = tf.keras.layers.Dense(units=self.num_chars)def call(self,inputs,from_logits=False):inputs = tf.one_hot(inputs,depth=self.num_chars)state = self.cell.get_initial_state(batch_size=self.batch_size,dtype=tf.float32)for i in range(self.seq_length):output,stat = self.cell(inputs[:,t,:],state)logits =self.dense(output)if from_logits:return logitselse:return tf.nn.softmax(logits)num_batches = 1000seq_length = 40batch_size = 50learning_rate = 1e-3'''从 DataLoader 中随机取一批训练数据；将这批数据送入模型 ， 计算出模型的预测值；将模型预测值与真实值进行比较 ， 计算损失函数（loss）；计算损失函数关于模型变量的导数；使用优化器更新模型参数以最小化损失函数 。 '''data_loader = DataLoader()model = RNN(num_chars=len(data_loader.chars), batch_size=batch_size, seq_length=seq_length)optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)for batch_index in range(num_batches):X, y = data_loader.get_batch(seq_length, batch_size)with tf.GradientTape() as tape:y_pred = model(X)loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=y, y_pred=y_pred)loss = tf.reduce_mean(loss)print("batch %d: loss %f" % (batch_index, loss.numpy()))grads = tape.gradient(loss, model.variables)optimizer.apply_gradients(grads_and_vars=zip(grads, model.variables))def predict(self, inputs, temperature=1.):batch_size, _ = tf.shape(inputs)logits = self(inputs, from_logits=True)prob = tf.nn.softmax(logits / temperature).numpy()return np.array([np.random.choice(self.num_chars, p=prob[i, :])for i in range(batch_size.numpy())])X_, _ = data_loader.get_batch(seq_length, 1)for diversity in [0.2, 0.5, 1.0, 1.2]:X = X_print("diversity %f:" % diversity)for t in range(400):y_pred = model.predict(X, diversity)print(data_loader.indices_char[y_pred[0]], end='', flush=True)X = np.concatenate([X[:, 1:], np.expand_dims(y_pred, axis=1)], axis=-1)print("\n")


推荐阅读


上一篇：tmpwatch命令清除旧文件

下一篇：python3和Django3+admin搭建后台之埋坑路