TensorBoard可视化工具

$$TensorBoard可视化工具$$

一 keras版本

"""
该项目运行环境：Windows 10
python =3.6
相关算法包环境
tensorflow = 2.0.0
numpy =1.18.3
"""


from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow as tf

from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
import numpy as np
import datetime
print(tf.__version__)
print(np.__version__)

mnist = np.load("mnist.npz")
x_train, y_train, x_test, y_test = mnist['x_train'],mnist['y_train'],mnist['x_test'],mnist['y_test']

x_train, x_test = x_train / 255.0, x_test / 255.0

# Add a channels dimension
x_train = x_train[..., tf.newaxis]
x_test = x_test[..., tf.newaxis]

class MyModel(Model):
    def __init__(self):
        super(MyModel, self).__init__()
        self.conv1 = Conv2D(32, 3, activation='relu')
        self.flatten = Flatten()
        self.d1 = Dense(128, activation='relu')
        self.d2 = Dense(10, activation='softmax')
    @tf.function
    def call(self, x):
        x = self.conv1(x)
        x = self.flatten(x)
        x = self.d1(x)
        return self.d2(x)

model = MyModel()
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])


tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir="keras_logv2", 
                                                      histogram_freq=1,
                                                      profile_batch = 100000000)

model.fit(x=x_train, 
          y=y_train, 
          epochs=20, 
          validation_data=(x_test, y_test), 
          callbacks=[tensorboard_callback])

%load_ext tensorboard

%tensorboard --logdir keras_log

二 自定义模型训练

"""
该项目运行环境：Windows 10
python =3.6
相关算法包环境
tensorflow = 2.0.0
numpy =1.18.3
"""


from __future__ import absolute_import, division, print_function, unicode_literals

import tensorflow as tf

from tensorflow.keras.layers import Dense, Flatten, Conv2D
from tensorflow.keras import Model
import numpy as np
import datetime
print(tf.__version__)
print(np.__version__)

tf.test.is_gpu_available()

mnist = np.load("mnist.npz")
x_train, y_train, x_test, y_test = mnist['x_train'],mnist['y_train'],mnist['x_test'],mnist['y_test']

x_train, x_test = x_train / 255.0, x_test / 255.0

# Add a channels dimension
x_train = x_train[..., tf.newaxis]
x_test = x_test[..., tf.newaxis]


train_ds = tf.data.Dataset.from_tensor_slices(
    (x_train, y_train)).shuffle(10000).batch(32)
test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)

class MyModel(Model):
    def __init__(self,**kwargs):
        super(MyModel, self).__init__(**kwargs)
        self.conv1 = Conv2D(32, 3, activation='relu')
        self.flatten = Flatten()
        self.d1 = Dense(128, activation='relu')
        self.d2 = Dense(10, activation='softmax')
    @tf.function
    def call(self, x):
        x = self.conv1(x)
        x = self.flatten(x)
        x = self.d1(x)
        return self.d2(x)

# model = tf.keras.models.Sequential([
#     tf.keras.layers.Flatten(input_shape=(28, 28,1)),
#     tf.keras.layers.Dense(32, activation='relu'),
#     tf.keras.layers.Dropout(0.2),
#     tf.keras.layers.Dense(10, activation='softmax')
# ])

loss_object = tf.keras.losses.SparseCategoricalCrossentropy()

optimizer = tf.keras.optimizers.Adam()

train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')

test_loss = tf.keras.metrics.Mean(name='test_loss')
test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')


# @tf.function
def train_step(images, labels):
    with tf.GradientTape() as tape:
        predictions = model(images)
        loss = loss_object(labels, predictions)
    gradients = tape.gradient(loss, model.trainable_variables)
    optimizer.apply_gradients(zip(gradients, model.trainable_variables))

    train_loss(loss)
    train_accuracy(labels, predictions)


# @tf.function
def test_step(images, labels):
    predictions = model(images)
    t_loss = loss_object(labels, predictions)

    test_loss(t_loss)
    test_accuracy(labels, predictions)

model = MyModel()

stamp = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
import os
logdir = os.path.join("logs/"+stamp)
 

summary_writer = tf.summary.create_file_writer(logdir) 

EPOCHS = 1

for epoch in range(EPOCHS):
    for (x_train, y_train) in train_ds:

            train_step(x_train, y_train)
            
        
    with summary_writer.as_default():                               # 希望使用的记录器
        tf.summary.scalar('loss', train_loss.result(), step=epoch)
        tf.summary.scalar('accuracy', train_accuracy.result(), step=epoch)  # 还可以添加其他自定义的变量

#     for (x_test, y_test) in test_ds:
#         test_step(x_test, y_test)


#     template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
#     print(template.format(epoch + 1,
#                           train_loss.result(),
#                           train_accuracy.result() * 100,
#                           test_loss.result(),
#                           test_accuracy.result() * 100))

    # Reset metrics every epoch
    train_loss.reset_states()
    test_loss.reset_states()
    train_accuracy.reset_states()
    test_accuracy.reset_states()
    
with summary_writer.as_default():
    tf.summary.trace_on(graph=True, profiler=False)  # 开启Trace，可以记录图结构和profile信息
    
    tf.summary.trace_export(name="model_trace", step=3, profiler_outdir=None)    # 保存Trace信息到文件

!rm -rf ./logs/*

summary_writer = tf.summary.create_file_writer('./tensorboard') 
log_dir = "graph"

summary_writer = tf.summary.create_file_writer('./tensorboard') 

# train_summary_writer = tf.summary.create_file_writer(train_log_dir)
# test_summary_writer = tf.summary.create_file_writer(test_log_dir)

EPOCHS = 5

for epoch in range(EPOCHS):
    for (x_train, y_train) in train_ds:
        train_step(x_train, y_train)
    with train_summary_writer.as_default():
        tf.summary.scalar('loss', train_loss.result(), step=epoch)
        tf.summary.scalar('accuracy', train_accuracy.result(), step=epoch)

    for (x_test, y_test) in test_ds:
        test_step(x_test, y_test)
#     with test_summary_writer.as_default():
#         tf.summary.scalar('loss', test_loss.result(), step=epoch)
#         tf.summary.scalar('accuracy', test_accuracy.result(), step=epoch)

    tf.summary.trace_on(graph=True, profiler=True)  # 开启Trace，可以记录图结构和profile信息
    # 进行训练
    with summary_writer.as_default():
        tf.summary.trace_export(name="model_trace", step=0, profiler_outdir=log_dir)    # 保存Trace信息到文件


        
        
    template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
    print(template.format(epoch + 1,
                          train_loss.result(),
                          train_accuracy.result() * 100,
                          test_loss.result(),
                          test_accuracy.result() * 100))

    # Reset metrics every epoch
    train_loss.reset_states()
    test_loss.reset_states()
    train_accuracy.reset_states()
    test_accuracy.reset_states()