AttributeError: module 'tensorflow' has no attribute 'placeholder_with_default'

[a0wsxz9]

Hello,there was a issue when I tried running the example.
DTQ:

Traceback (most recent call last):
File "train_val_script.py", line 74, in
model_weights = model.train(train_img, database_img, query_img, args)
File "C:\DeepHash-master\DeepHash-master\DeepHash\model\dtq_init_.py", line 5, in train
model = DTQ(config)
File "C:\DeepHash-master\DeepHash-master\DeepHash\model\dtq\dtq.py", line 24, in init
self.stage = tf.placeholder_with_default(tf.constant(0), [])
AttributeError: module 'tensorflow' has no attribute 'placeholder_with_default'

DCH:

Traceback (most recent call last):
File "train_val_script.py", line 61, in
model_weights = model.train(train_img, database_img, query_img, args)
File "C:\DeepHash-master\DeepHash-master\DeepHash\model\dch_init_.py", line 5, in train
model = DCH(config)
File "C:\DeepHash-master\DeepHash-master\DeepHash\model\dch\dch.py", line 29, in init
self.stage = tf.placeholder_with_default(tf.constant(0), [])
AttributeError: module 'tensorflow' has no attribute 'placeholder_with_default'

Is it because of my tensorflow's version?

And another thing,can I get the intermediate hash value from the model? I'm studying the secure scheme of image retrieve based on hash of hamming space.I want to use these models to make sure the precision, but I don't know if I could.I'd appreciate some help!

[a0wsxz9]

well,I found it is because my tensorflow version is 2.1. I want to know what the tensorflows's version well done is.

[Riya-11]

Had the same error. Changed tensorflow version to 1.14 and it worked. Hope it helps!