SystemError: unknown opcode

[ybxbupt]

Namespace(flip=True, glob_path=None, id='0', input_path='example_images/cityscapes.png', input_size=500, model='pspnet50_ade20k', output_path='example_results/cityscapes.jpg', weights=None)
weights/keras/pspnet50_ade20k.json
Keras model & weights found, loading...
XXX lineno: 18, opcode: 0
Traceback (most recent call last):
File "/home/jiurui/temp/PSPNet-Keras-tensorflow-master/pspnet.py", line 186, in
weights=args.model)
File "/home/jiurui/temp/PSPNet-Keras-tensorflow-master/pspnet.py", line 133, in init
input_shape=input_shape, weights=weights)
File "/home/jiurui/temp/PSPNet-Keras-tensorflow-master/pspnet.py", line 34, in init
self.model = model_from_json(file_handle.read())
File "/home/jiurui/env_mask_rcnn/lib/python3.6/site-packages/keras/models.py", line 345, in model_from_json
return layer_module.deserialize(config, custom_objects=custom_objects)
File "/home/jiurui/env_mask_rcnn/lib/python3.6/site-packages/keras/layers/init.py", line 54, in deserialize
printable_module_name='layer')
File "/home/jiurui/env_mask_rcnn/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 139, in deserialize_keras_object
list(custom_objects.items())))
File "/home/jiurui/env_mask_rcnn/lib/python3.6/site-packages/keras/engine/topology.py", line 2497, in from_config
process_node(layer, node_data)
File "/home/jiurui/env_mask_rcnn/lib/python3.6/site-packages/keras/engine/topology.py", line 2454, in process_node
layer(input_tensors[0], **kwargs)
File "/home/jiurui/env_mask_rcnn/lib/python3.6/site-packages/keras/engine/topology.py", line 602, in call
output = self.call(inputs, **kwargs)
File "/home/jiurui/env_mask_rcnn/lib/python3.6/site-packages/keras/layers/core.py", line 650, in call
return self.function(inputs, **arguments)
File "/media/tatsch/DataSSD1/workspace/PSPNet-Keras-tensorflow/pspnet/layers_builder.py", line 18, in Interp
return BatchNormalization(momentum=0.95, name=name, epsilon=1e-5)
SystemError: unknown opcode

[ktnguyen2]

I have this error too. I am on CentosOS with keras 2.0.6, tensorflow 1.11, and python 3.6

[anieuwland]

I also encounter this error, has anyone found out what goes wrong yet? Could it be a Python / TF / Keras version error?

[hwchen2009]

I have this error too. Anyone solved this yet?

[anieuwland]

I fixed it by using python 3.5. Both 2.7 and 3.6 didn't work for me.

[ktnguyen2]

I also fixed it by using python 3.5

[hwchen2009]

Thanks! that worked

[Vladkryvoruchko]

Trying dig info how to workaround to deal with this on Python3.6+

Currently found, which states that this is Keras/TF/Theano error when loading .h5 models with Python 3.6+:
keras-team/keras#9595
But WIP

[Vladkryvoruchko]

Okay, found old discussion here:
#25 (comment)

Apparently this issue is caused by the marshal serial format having changed a bit between Python 3.5 and 3.6 as discovered in keras-team/keras#9595 . Converting the weights from numpy with python 3.6 should work around it.