Cannot compute output Tensor issue

[hci-mkim]

I suceessfully import the training data but, stucked in the below error. anyone help?
My error message is

AssertionError: Could not compute output Tensor("mrcnn_class_loss/Reshape:0", shape=(1, 1), dtype=float32)

++
Traceback (most recent call last):
File "human_pose.py", line 42, in
model = modellib.MaskRCNN(mode="training", model_dir=MODEL_DIR, config=config)
File "C:\Users\min\Desktop\MaskRCNN_HumanPose_Estimation-master\model.py", line 2516, in init
self.keras_model = self.build(mode=mode, config=config)
File "C:\Users\min\Desktop\MaskRCNN_HumanPose_Estimation-master\model.py", line 2784, in build
model = ParallelModel(model, config.GPU_COUNT)
File "C:\Users\min\Desktop\MaskRCNN_HumanPose_Estimation-master\parallel_model.py", line 37, in init
merged_outputs = self.make_parallel()
File "C:\Users\min\Desktop\MaskRCNN_HumanPose_Estimation-master\parallel_model.py", line 81, in make_parallel
outputs = self.inner_model(inputs)
File "C:\Anaconda3\lib\site-packages\keras\engine\topology.py", line 602, in call
output = self.call(inputs, **kwargs)
File "C:\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2058, in call
output_tensors, _, _ = self.run_internal_graph(inputs, masks)
File "C:\Anaconda3\lib\site-packages\keras\engine\topology.py", line 2262, in run_internal_graph
assert str(id(x)) in tensor_map, 'Could not compute output ' + str(x)
AssertionError: Could not compute output Tensor("mrcnn_class_loss/Reshape:0", shape=(1, 1), dtype=float32)
++