tf1.1.14之tensorboard debug

一、启动tensorboard debug 

       tensorboard --logdir=C:\Users\86188\IdeaProjects\yolo1\log  --debugger_port=6007

 

打开浏览器会弹出

 

Debugger is waiting for Session.run() connections...

tf.Session:

import tensorflow as tf
from tensorflow.python import debug as tf_debug

sess = tf.Session()
sess = tf_debug.TensorBoardDebugWrapperSession(sess, "balaluolaq:6007")
sess.run(my_fetches)
          

Estimator | MonitoredSession:

import tensorflow as tf
from tensorflow.python import debug as tf_debug

hook = tf_debug.TensorBoardDebugHook("balaluolaq:6007")
my_estimator.fit(x=x_data, y=y_data, steps=1000, monitors=[hook])
            

Keras Model:

import tensorflow as tf
from tensorflow.python import debug as tf_debug
import keras

keras.backend.set_session(
    tf_debug.TensorBoardDebugWrapperSession(tf.Session(), "balaluolaq:6007"))
# Define your keras model, called "model".
model.fit(...)