TypeError: __call__() got an unexpected keyword argument 'previous_alignments' issue

[KhinePisi]

I run the evaluation code for NQA commonsense on GoogleColab like this ,
!python CommonSenseMultiHopQA/src/config.py
--mode test
--version commonsense_nqa
--model_name CommonSenseMultiHopQA/out/NQACommonsense
--use_ckpt "epoch_0009_step00012500_bleu1(0.461571)_bleu4(0.217204)_meteor(0.210980)_rogue(0.495554).data-00000-of-00001"
--processed_dataset_train CommonSenseMultiHopQA/data/narrative_qa_train.jsonl
--processed_dataset_valid CommonSenseMultiHopQA/data/narrative_qa_valid.jsonl
--processed_dataset_test CommonSenseMultiHopQA/data/narrative_qa_test.jsonl
--batch_size 24
--max_target_iterations 15
--dropout_rate 0.2

and I got the error like this >>>
WARNING: Logging before flag parsing goes to stderr.
W0316 13:24:01.048576 140715097528192 module_wrapper.py:139] From CommonSenseMultiHopQA/src/config.py:96: The name tf.app.run is deprecated. Please use tf.compat.v1.app.run instead.

['CommonSenseMultiHopQA/src/config.py', '--mode', 'test', '--version', 'commonsense_nqa', '--model_name', 'CommonSenseMultiHopQA/out/NQACommonsense', '--use_ckpt', 'epoch_0009_step00012500_bleu1(0.461571)_bleu4(0.217204)_meteor(0.210980)_rogue(0.495554).data-00000-of-00001', '--processed_dataset_train', 'CommonSenseMultiHopQA/data/narrative_qa_train.jsonl', '--processed_dataset_valid', 'CommonSenseMultiHopQA/data/narrative_qa_valid.jsonl', '--processed_dataset_test', 'CommonSenseMultiHopQA/data/narrative_qa_test.jsonl', '--batch_size', '24', '--max_target_iterations', '15', '--dropout_rate', '0.2']
Evaluating!
W0316 13:24:01.678194 140715097528192 lazy_loader.py:50]
The TensorFlow contrib module will not be included in TensorFlow 2.0.
For more information, please see:

• https://github.com/tensorflow/community/blob/master/rfcs/20180907-contrib-sunset.md
• https://github.com/tensorflow/addons
• https://github.com/tensorflow/io (for I/O related ops)
  If you depend on functionality not listed there, please file an issue.

W0316 13:24:01.678544 140715097528192 deprecation.py:506] From /usr/local/lib/python2.7/dist-packages/tensorflow_core/python/keras/initializers.py:94: calling init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
Vocab built! Size (35965)
Data loaded!
W0316 13:24:05.527146 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/model_commonsense_nqa.py:36: The name tf.get_variable is deprecated. Please use tf.compat.v1.get_variable instead.

W0316 13:24:05.541138 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/model_commonsense_nqa.py:40: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.

W0316 13:24:05.602550 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/utils.py:258: The name tf.ConfigProto is deprecated. Please use tf.compat.v1.ConfigProto instead.

W0316 13:24:05.602858 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/main.py:295: The name tf.Session is deprecated. Please use tf.compat.v1.Session instead.

W0316 13:24:05.813936 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/elmo/model.py:276: The name tf.variable_scope is deprecated. Please use tf.compat.v1.variable_scope instead.

USING SKIP CONNECTIONS
W0316 13:24:06.421890 140715097528192 deprecation.py:323] From /content/CommonSenseMultiHopQA/src/elmo/model.py:520: init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
W0316 13:24:06.445024 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/elmo/model.py:564: The name tf.nn.rnn_cell.LSTMStateTuple is deprecated. Please use tf.compat.v1.nn.rnn_cell.LSTMStateTuple instead.

W0316 13:24:06.445283 140715097528192 deprecation.py:323] From /content/CommonSenseMultiHopQA/src/elmo/model.py:565: dynamic_rnn (from tensorflow.python.ops.rnn) is deprecated and will be removed in a future version.
Instructions for updating:
Please use keras.layers.RNN(cell), which is equivalent to this API
W0316 13:24:06.559309 140715097528192 deprecation.py:323] From /usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/rnn_cell_impl.py:958: add_variable (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use layer.add_weight method instead.
W0316 13:24:06.836575 140715097528192 deprecation.py:506] From /usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/rnn_cell_impl.py:962: calling init (from tensorflow.python.ops.init_ops) with dtype is deprecated and will be removed in a future version.
Instructions for updating:
Call initializer instance with the dtype argument instead of passing it to the constructor
W0316 13:24:06.906634 140715097528192 deprecation.py:323] From /usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/rnn.py:244: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
W0316 13:24:06.951582 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/elmo/model.py:589: The name tf.assign is deprecated. Please use tf.compat.v1.assign instead.

W0316 13:24:06.963304 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/elmo/model.py:534: The name tf.nn.rnn_cell.ResidualWrapper is deprecated. Please use tf.compat.v1.nn.rnn_cell.ResidualWrapper instead.

USING SKIP CONNECTIONS
W0316 13:24:09.593326 140715097528192 deprecation.py:506] From /usr/local/lib/python2.7/dist-packages/tensorflow_core/python/util/dispatch.py:180: calling squeeze (from tensorflow.python.ops.array_ops) with squeeze_dims is deprecated and will be removed in a future version.
Instructions for updating:
Use the axis argument instead
W0316 13:24:09.599205 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/elmo/elmo.py:94: The name tf.get_collection is deprecated. Please use tf.compat.v1.get_collection instead.

W0316 13:24:09.599404 140715097528192 module_wrapper.py:139] From /content/CommonSenseMultiHopQA/src/elmo/elmo.py:95: The name tf.GraphKeys is deprecated. Please use tf.compat.v1.GraphKeys instead.

ELMo shapes:
[24, None, 1024]
[24, None, 1024]
[24, None, 1280]
W0316 13:24:09.654242 140715097528192 deprecation.py:323] From /content/CommonSenseMultiHopQA/src/tf_utils/ops.py:372: dropout (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.dropout instead.
W0316 13:24:09.654836 140715097528192 deprecation.py:323] From /usr/local/lib/python2.7/dist-packages/tensorflow_core/python/layers/core.py:271: apply (from tensorflow.python.keras.engine.base_layer) is deprecated and will be removed in a future version.
Instructions for updating:
Please use layer.__call__ method instead.
[24, None, 256]
[24, None, 256]
[24, None, 1024]
W0316 13:24:16.173249 140715097528192 deprecation.py:323] From /content/CommonSenseMultiHopQA/src/model_commonsense_nqa.py:198: dense (from tensorflow.python.layers.core) is deprecated and will be removed in a future version.
Instructions for updating:
Use keras.layers.Dense instead.
projected Tensor("attn_layer_0/commonsense_encoder/commonsense_proj/Relu:0", shape=(24, 40, 1024), dtype=float32)
[24, None, 1024]
[24, None, 256]
[24, None, 256]
[24, None, 1024]
projected Tensor("attn_layer_1/commonsense_encoder/commonsense_proj/Relu:0", shape=(24, 40, 1024), dtype=float32)
[24, None, 1024]
[24, None, 256]
[24, None, 256]
[24, None, 1024]
projected Tensor("attn_layer_2/commonsense_encoder/commonsense_proj/Relu:0", shape=(24, 40, 1024), dtype=float32)
[24, None, 1024]
1024
[24, None, 1024]
[24, None, 256]
[b x n x n]
[24, None, None]
[b x n x h]
[24, None, 256]
[24, None, 768]
[24, None, 1024]
[24, None, 1024]
W0316 13:24:34.837351 140715097528192 deprecation.py:323] From /content/CommonSenseMultiHopQA/src/tf_utils/ops.py:41: init (from tensorflow.python.ops.rnn_cell_impl) is deprecated and will be removed in a future version.
Instructions for updating:
This class is equivalent as tf.keras.layers.LSTMCell, and will be replaced by that in Tensorflow 2.0.
W0316 13:24:34.958561 140715097528192 module_wrapper.py:139] From /usr/local/lib/python2.7/dist-packages/tensorflow_estimator/python/estimator/api/_v1/estimator/init.py:12: The name tf.estimator.inputs is deprecated. Please use tf.compat.v1.estimator.inputs instead.

<tensorflow.python.ops.tensor_array_ops.TensorArray object at 0x7ff9e515dd10>
Tensor("decode/decoder/while/BasicDecoderStep/decoder/attn_pointer_wrapper/checked_cell_output:0", shape=(24, 128), dtype=float32)
<tensorflow.python.layers.core.Dense object at 0x7ff9e5215310>
Tensor("decode/decoder/while/BasicDecoderStep/decoder/attn_pointer_wrapper/Softmax:0", shape=(24, 35965), dtype=float32)
Vocab dist history
<tensorflow.python.ops.tensor_array_ops.TensorArray object at 0x7ff9e5215210>
Traceback (most recent call last):
File "CommonSenseMultiHopQA/src/config.py", line 96, in
tf.app.run()
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/platform/app.py", line 40, in run
_run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef)
File "/usr/local/lib/python2.7/dist-packages/absl/app.py", line 300, in run
_run_main(main, args)
File "/usr/local/lib/python2.7/dist-packages/absl/app.py", line 251, in _run_main
sys.exit(main(argv))
File "CommonSenseMultiHopQA/src/config.py", line 93, in main
m(config)
File "/content/CommonSenseMultiHopQA/src/main.py", line 62, in main
_test(config)
File "/content/CommonSenseMultiHopQA/src/main.py", line 297, in _test
model.build_graph()
File "/content/CommonSenseMultiHopQA/src/model_commonsense_nqa.py", line 317, in build_graph
train_outputs, train_state, self.train_final_lengths = decode(train_helper, 'decode')
File "/content/CommonSenseMultiHopQA/src/model_commonsense_nqa.py", line 313, in decode
maximum_iterations = self.max_decoder_length)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/contrib/seq2seq/python/ops/decoder.py", line 469, in dynamic_decode
swap_memory=swap_memory)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2753, in while_loop
return_same_structure)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2245, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2170, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/control_flow_ops.py", line 2705, in
body = lambda i, lv: (i + 1, orig_body(*lv))
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/contrib/seq2seq/python/ops/decoder.py", line 412, in body
decoder_finished) = decoder.step(time, inputs, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/contrib/seq2seq/python/ops/basic_decoder.py", line 136, in step
cell_outputs, cell_state = self._cell(inputs, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/ops/rnn_cell_impl.py", line 244, in call
return super(RNNCell, self).call(inputs, state)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/layers/base.py", line 548, in call
outputs = super(Layer, self).call(inputs, *args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/keras/engine/base_layer.py", line 854, in call
outputs = call_fn(cast_inputs, *args, **kwargs)
File "/usr/local/lib/python2.7/dist-packages/tensorflow_core/python/autograph/impl/api.py", line 237, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: in converted code:
relative to /content/CommonSenseMultiHopQA/src/tf_utils:

pointer_wrapper.py:477 call  *
    attention, alignments = _compute_attention(
pointer_wrapper.py:54 _compute_attention  *
    alignments = attention_mechanism(

TypeError: __call__() got an unexpected keyword argument 'previous_alignments'

Can anyone please help me with this ??