我想用tensorboard查看神经的网络结构

您可以使用以下代码在TensorBoard中查看神经网络结构：

import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense

# Define your model
model = Sequential()
model.add(Dense(64, activation='relu', input_dim=784))
model.add(Dense(10, activation='softmax'))

# Compile your model
model.compile(optimizer='adam',
              loss='categorical_crossentropy',
              metrics=['accuracy'])

# Create a summary writer
log_dir = "/path/to/log/dir"
summary_writer = tf.summary.create_file_writer(log_dir)

# Use the summary writer to write the graph to TensorBoard
with summary_writer.as_default():
    tf.summary.trace_on(graph=True, profiler=True)
    model(tf.zeros([1, 784]))
    tf.summary.trace_export(name="model_trace", step=0)

# Launch TensorBoard
%tensorboard --logdir=/path/to/log/dir

这将在指定的日志目录中创建一个TensorBoard，并将模型的计算图写入TensorBoard。您可以在TensorBoard中查看计算图，以便更好地了解模型的结构。