TensorFlow2_200729系列---18、手写数字识别（层方式）
一、总结
一句话总结：
之前是张量（tensor）的方式，体现细节和原理，现在是层方式，更加简便简洁
model = Sequential([ layers.Dense(256, activation=tf.nn.relu), # [b, 784] => [b, 256] layers.Dense(128, activation=tf.nn.relu), # [b, 256] => [b, 128] layers.Dense(64, activation=tf.nn.relu), # [b, 128] => [b, 64] layers.Dense(32, activation=tf.nn.relu), # [b, 64] => [b, 32] layers.Dense(10) # [b, 32] => [b, 10], 330 = 32*10 + 10 ]) model.build(input_shape=[None, 28*28]) model.summary() 使用模型： logits = model(x)
1、tensorflow的keras模块包括datasets, layers, optimizers, Sequential, metrics？
from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics
二、手写数字识别（层方式）
博客对应课程的视频位置：
import os os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2' import tensorflow as tf from tensorflow import keras from tensorflow.keras import datasets, layers, optimizers, Sequential, metrics assert tf.__version__.startswith('2.') # 预处理函数 # 数据归一化 def preprocess(x, y): x = tf.cast(x, dtype=tf.float32) / 255. y = tf.cast(y, dtype=tf.int32) return x,y # 自动加载数据 (x, y), (x_test, y_test) = datasets.fashion_mnist.load_data() print(x.shape, y.shape) # batch size：一批的大小 batchsz = 128 # 训练数据 # Creates a `Dataset` whose elements are slices of the given tensors. db = tf.data.Dataset.from_tensor_slices((x,y)) # shuffle打乱并且分batch db = db.map(preprocess).shuffle(10000).batch(batchsz) # 测试数据 db_test = tf.data.Dataset.from_tensor_slices((x_test,y_test)) # 测试数据不需要打乱 db_test = db_test.map(preprocess).batch(batchsz) # 迭代器 db_iter = iter(db) sample = next(db_iter) print('batch:', sample[0].shape, sample[1].shape) # batch: (128, 28, 28) (128,) model = Sequential([ layers.Dense(256, activation=tf.nn.relu), # [b, 784] => [b, 256] layers.Dense(128, activation=tf.nn.relu), # [b, 256] => [b, 128] layers.Dense(64, activation=tf.nn.relu), # [b, 128] => [b, 64] layers.Dense(32, activation=tf.nn.relu), # [b, 64] => [b, 32] layers.Dense(10) # [b, 32] => [b, 10], 330 = 32*10 + 10 ]) model.build(input_shape=[None, 28*28]) model.summary() # w = w - lr*grad optimizer = optimizers.Adam(lr=1e-3) def main(): for epoch in range(30): for step, (x,y) in enumerate(db): # x: [b, 28, 28] => [b, 784] # y: [b] x = tf.reshape(x, [-1, 28*28]) with tf.GradientTape() as tape: # [b, 784] => [b, 10] logits = model(x) y_onehot = tf.one_hot(y, depth=10) # [b] loss_mse = tf.reduce_mean(tf.losses.MSE(y_onehot, logits)) loss_ce = tf.losses.categorical_crossentropy(y_onehot, logits, from_logits=True) loss_ce = tf.reduce_mean(loss_ce) # model.trainable_variables：表示参数，也就是w和b grads = tape.gradient(loss_ce, model.trainable_variables) # 原地更新 optimizer.apply_gradients(zip(grads, model.trainable_variables)) if step % 100 == 0: print(epoch, step, 'loss:', float(loss_ce), float(loss_mse)) # test total_correct = 0 total_num = 0 for x,y in db_test: # x: [b, 28, 28] => [b, 784] # y: [b] x = tf.reshape(x, [-1, 28*28]) # [b, 10] logits = model(x) # logits => prob, [b, 10] prob = tf.nn.softmax(logits, axis=1) # [b, 10] => [b], int64 pred = tf.argmax(prob, axis=1) pred = tf.cast(pred, dtype=tf.int32) # pred:[b] # y: [b] # correct: [b], True: equal, False: not equal correct = tf.equal(pred, y) correct = tf.reduce_sum(tf.cast(correct, dtype=tf.int32)) total_correct += int(correct) total_num += x.shape[0] acc = total_correct / total_num print(epoch, 'test acc:', acc) if __name__ == '__main__': main()