ARCHIVED: Contains historical course materials/Homework materials for the FREE MOOC course on "Creative Applications of Deep Learning w/ Tensorflow" #CADL
The VAEGAN training code saves checkpoints using the value of the global training step, which results in checkpoints with names like 'vaegan.ckpt-800.index', for example. Any code that looks for an existing checkpoint also needs to account for this naming scheme, but the existence check used doesn't quite work with this scheme:
if os.path.exists(ckpt_name + '.index') or os.path.exists(ckpt_name):
I would suggest changing the check to something like this:
latest_checkpoint = tf.train.latest_checkpoint(os.path.dirname(ckpt_name))
if latest_checkpoint:
saver.restore(sess, latest_checkpoint)
print("Model restored from checkpoint {}.".format(latest_checkpoint))
else:
print("Model checkpoint not found.")
(This won't quite work if checkpoints from multiple models are created in the same directory, since it relies on the presence of a file named 'checkpoint'.)
The VAEGAN training code saves checkpoints using the value of the global training step, which results in checkpoints with names like 'vaegan.ckpt-800.index', for example. Any code that looks for an existing checkpoint also needs to account for this naming scheme, but the existence check used doesn't quite work with this scheme:
if os.path.exists(ckpt_name + '.index') or os.path.exists(ckpt_name):I would suggest changing the check to something like this:
(This won't quite work if checkpoints from multiple models are created in the same directory, since it relies on the presence of a file named 'checkpoint'.)