TypeError:unbound method <lambda>() must be called with o instance as first argument (got Tensor instance instead)

[MrCPlusPlus]

When I ran this code, I got the error listed as below.

mpiexec -n 1 --allow-run-as-root python train.py --problem celeba --image_size 256 --n_level 6 --depth 32 --flow_permutation 2 --flow_coupling 0 --seed 0 --learntop --lr 0.001 --n_bits_x 5
/usr/local/lib/python2.7/dist-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type.
from ._conv import register_converters as register_converters
Rank 0 Batch sizes Train 1 Test 1 Init 4
(3000, 1, 1)
Train epoch size: 49984
('Creating pad', '1_1[130, 130]')
Traceback (most recent call last):
File "train.py", line 386, in
main(hps)
File "train.py", line 162, in main
model = model.model(sess, hps, train_iterator, test_iterator, data_init)
File "/data/home/ervinchen/share/glow-master/model.py", line 238, in model
test_iterator, data_init, lr, f_loss)
File "/data/home/ervinchen/share/glow-master/model.py", line 25, in abstract_model_xy
loss_train, stats_train = f_loss(train_iterator, True)
File "/data/home/ervinchen/share/glow-master/model.py", line 226, in f_loss
bits_x, bits_y, pred_loss = _f_loss(x, y, is_training, reuse)
File "/data/home/ervinchen/share/glow-master/model.py", line 171, in _f_loss
z, objective = encoder(z, objective)
File "/data/home/ervinchen/share/glow-master/model.py", line 89, in encoder
z, objective = split2d("pool"+str(i), z, objective=objective)
File "/usr/local/lib/python2.7/dist-packages/tensorflow/contrib/framework/python/ops/arg_scope.py", line 183, in func_with_args
return func(*args, **current_args)
File "/data/home/ervinchen/share/glow-master/model.py", line 486, in split2d
objective += pz.logp(z2)
TypeError: unbound method () must be called with o instance as first argument (got Tensor instance instead)

[MrCPlusPlus]

The problem seems to be solved by changing python2 to python3...