Hi,
I am trying to run the code on a custom dataset, which has 13 classes. However, I am getting the following error:
''' ---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
in
7 utils.download_trained_weights(weights_path)
8
----> 9 model.load_weights(weights_path, by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox", "mrcnn_mask"])
10
11 train(model)
C:\Ajay\Codes_and_Outcomes\Mask_RCNN\mrcnn\model.py in load_weights(self, filepath, by_name, exclude)
2128
2129 if by_name:
-> 2130 saving.load_weights_from_hdf5_group_by_name(f, layers)
2131 else:
2132 saving.load_weights_from_hdf5_group(f, layers)
~\AppData\Local\anaconda3\envs\Mask_RCNN\lib\site-packages\keras\engine\saving.py in load_weights_from_hdf5_group_by_name(f, layers, skip_mismatch, reshape)
1081 """
1082 if 'keras_version' in f.attrs:
-> 1083 original_keras_version = f.attrs['keras_version'].decode('utf8')
1084 else:
1085 original_keras_version = '1'
AttributeError: 'str' object has no attribute 'decode'
'''
It looks like the error is originating from a function within keras, which I don't think I should edit.
Could you please suggest what might be happening here and how can I get this corrected?