AttributeError: 'NoOpActivation' object has no attribute '__name__'

Traceback (most recent call last):
File "train_mobilenetv2_quantization.py", line 368, in
base_model = quantize_model(base_model)
File "/home/huangfei/anaconda3/envs/ImageSearch2/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/quantize.py", line 138, in quantize_model
return quantize_apply(annotated_model)
File "/home/huangfei/anaconda3/envs/ImageSearch2/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/quantize.py", line 410, in quantize_apply
unwrapped_model, layer_quantize_map)
File "/home/huangfei/anaconda3/envs/ImageSearch2/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/default_8bit/default_8bit_quantize_layout_transform.py", line 73, in apply
set(layer_quantize_map.keys()), layer_quantize_map).transform()
File "/home/huangfei/anaconda3/envs/ImageSearch2/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/graph_transformations/model_transformer.py", line 529, in transform
copy.deepcopy(match_layer_node))
File "/home/huangfei/anaconda3/envs/ImageSearch2/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/default_8bit/default_8bit_transforms.py", line 250, in replacement
return self._replace(relu_layer_node, bn_layer_node, conv_layer_node)
File "/home/huangfei/anaconda3/envs/ImageSearch2/lib/python3.6/site-packages/tensorflow_model_optimization/python/core/quantization/keras/default_8bit/default_8bit_transforms.py", line 239, in _replace
keras.activations.serialize(quantize_aware_activation.NoOpActivation())
File "/home/huangfei/anaconda3/envs/ImageSearch2/lib/python3.6/site-packages/tensorflow/python/keras/activations.py", line 287, in serialize
if activation.name in _TF_ACTIVATIONS_V2:
AttributeError: 'NoOpActivation' object has no attribute 'name'

Start with the _replace method in tensorflow_model_optimization/python/core/quantization/keras/default_8bit/default_8bit_transforms.py and follow the call to keras.activations.serialize shown in the traceback. Reproduce the MobileNetV2 quantization failure, then verify that quantization no longer raises the NoOpActivation name AttributeError.