KeyError: "The name 'inputs_seq:0' refers to a Tensor which does not exist. The operation, 'inputs_seq', does not exist in the graph."

[sayakpaul]

When I run predict.py (after changing the ckpt identifier to model.ckpt.batch48) I get the following:

Traceback (most recent call last):
  File "predict.py", line 73, in <module>
    graph.get_tensor_by_name("inputs_seq:0"): inputs_seq_batch,
  File "/tensorflow-1.15.2/python3.7/tensorflow_core/python/framework/ops.py", line 3783, in get_tensor_by_name
    return self.as_graph_element(name, allow_tensor=True, allow_operation=False)
  File "/tensorflow-1.15.2/python3.7/tensorflow_core/python/framework/ops.py", line 3607, in as_graph_element
    return self._as_graph_element_locked(obj, allow_tensor, allow_operation)
  File "/tensorflow-1.15.2/python3.7/tensorflow_core/python/framework/ops.py", line 3649, in _as_graph_element_locked
    "graph." % (repr(name), repr(op_name)))
KeyError: "The name 'inputs_seq:0' refers to a Tensor which does not exist. The operation, 'inputs_seq', does not exist in the graph."

Anything I am missing out on? Note that I am running the scripts on the minimal dataset that's provided in the repository.