unirep_tutorial.ipynb error

[miservilla]

Hi there,

Trying to follow instructions to run tutorial jupyter notebook with docker and I continue to get error in the following cell:

`import tensorflow as tf
import numpy as np

Set seeds

#tf.set_random_seed(42)
np.random.seed(42)

if USE_FULL_1900_DIM_MODEL:
# Sync relevant weight files
!aws s3 sync --no-sign-request --quiet s3://unirep-public/1900_weights/ 1900_weights/

# Import the mLSTM babbler model
from unirep import babbler1900 as babbler

# Where model weights are stored.
MODEL_WEIGHT_PATH = "./1900_weights"

else:
# Sync relevant weight files
!aws s3 sync --no-sign-request --quiet s3://unirep-public/64_weights/ 64_weights/

# Import the mLSTM babbler model
from unirep import babbler64 as babbler

# Where model weights are stored.
MODEL_WEIGHT_PATH = "./64_weights"`

---

AttributeError Traceback (most recent call last)
in ()
21
22 # Import the mLSTM babbler model
---> 23 from unirep import babbler64 as babbler
24
25 # Where model weights are stored.

/notebooks/unirep.py in ()
41
42 # Setup to initialize from the correctly named model files.
---> 43 class mLSTMCell1900(tf.compat.v1.nn.rnn_cell):
44
45 def init(self,

AttributeError: module 'tensorflow.python.util.compat' has no attribute 'v1'`

I am running the following in a conda env:
tf==1.3.0
pd==1.15.4

Please suggest anything to help. Thanks!