tf2.x的tensorboard可视化

在model.fit里加入参数就可以可视化了
首先进入相应的conda虚拟环境，然后输入命令：

tensorboard --logdir logs

再在浏览器里输入网址：

http://localhost:6006/

完整tf2.0可视化代码：

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


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_test, y_test) = datasets.mnist.load_data()

x_train, x_val = tf.split(x, num_or_size_splits=[50000, 10000])
y_train, y_val = tf.split(y, num_or_size_splits=[50000, 10000])
db_train = tf.data.Dataset.from_tensor_slices((x_train, y_train))
db_train = db_train.map(preprocess).shuffle(50000).batch(batchsz)

db_val = tf.data.Dataset.from_tensor_slices((x_val, y_val))
db_val = db_val.map(preprocess).shuffle(10000).batch(batchsz)

db_test = tf.data.Dataset.from_tensor_slices((x_test, y_test))
db_test = db_test.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()

network.compile(optimizer=optimizers.Adam(lr=0.001),
                loss=tf.losses.CategoricalCrossentropy(from_logits=True),
                metrics=['accuracy']
                )

# 运用tensorboard可视化
current_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
log_dir = 'logs/' + current_time
tensorboard_callback = callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1, write_images=True)

network.fit(db_train, epochs=30, validation_data=db_val, validation_freq=1,
            callbacks=[tensorboard_callback])

print("Test performance")
network.evaluate(db_test)

结果：

本站所有文章均为原创，欢迎转载，请注明文章出处：https://blog.csdn.net/weixin_45092662。百度和各类采集站皆不可信，搜索请谨慎鉴别。技术类文章一般都有时效性，本人习惯不定期对自己的博文进行修正和更新，因此请访问出处以查看本文的最新版本。