使用 keras 图表启动 Tensorboard（用于可视化准确性、损失和预测结果）

Question

我不明白如何使用张量板来可视化我的 keras 网络的训练步骤。

我已经使用命令行启动了张量板：tensorboard --logdir=/run1 但是他提出了这个错误：

No dashboards are active for the current data set. Probable causes:You haven’t written any data to your event files. TensorBoard can’t find your event files.

import tensorflow as tf
from tensorflow import keras
import numpy as np

# Create the array of data

train_data = [[1.0,2.0,3.0],[4.0,5.0,6.0]]
train_data_np = np.asarray(train_data)

train_label = [[1,2,3],[4,5,6]]

train_label_np = np.asarray(train_data)

### Build the model

model = keras.Sequential([
    keras.layers.Dense(3,input_shape =(3,2)),
    keras.layers.Dense(3,activation=tf.nn.sigmoid)
])

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

#Train the model

tensorboard = TensorBoard(log_dir="run1")
model.fit(train_data_np,train_label_np,epochs=10,callbacks=tensorboard)

#test the model
restest = model.evaluate(test_data_np,test_label_np)

Answer 1

在此处添加正式答案；看起来 tensorboard logdir 参数中有错字。您需要删除目录开头的斜线

tensorboard --logdir=run1

使用 keras 图表启动 Tensorboard（用于可视化准确性、损失和预测结果）

Launch Tensorboard with keras graph (for visualize accuracy, loss and predict result)

python

keras

tensorflow

tensorboard