Images in tensorboard
I know that you can show your training result images inside Tensorboard, but can't find a way how to do it properly with the Keras framework. What is the best way to show images?
I'm using Keras 2.1.4 and Tensorflow 1.13.1
1 Answers
JO
2It is easy. You just need to get the matrix representation of that image and pass it to the log writer like this.
# Sets up a timestamped log directory.
logdir = "logs/train_data/log_event"
# Creates a file writer for the log directory.
file_writer = tf.summary.create_file_writer(logdir)
# Using the file writer, log the reshaped image.
with file_writer.as_default():
tf.summary.image("Input Image", img, step=iter)Reply
Couldn't find what you were looking for?and we will find an expert to answer.
How helpful was this page?