error in running Demo.py

[bardia-esm]

Hi,
when I try to run Demo.py I get an error in line of model_from_json(open('model.json').read())
the error is as bellow:
Exception has occurred: ValueError
Improper config format: {'l2': 0.0010000000474974513, 'name': 'WeightRegularizer', 'l1': 0.0}
File "/home/bardia/Desktop/Untitled-1.py", line 3, in
model = model_from_json(open(json_path).read())

the error is in model.json file in line of W_regularizer:

W_regularizer": {"l2": 0.0010000000474974513, "name": "WeightRegularizer", "l1": 0.0}

I search the error and it looks like that for version 2.2 Keras I have to use custome_object paramter inside model_from_json(open('model.json').read()) .

So In a new file, I changed the code to:

from keras.models import model_from_json
model = model_from_json(open('model.json').read(), custom_objects={'WeightRegularizer':W_regularizer}

However, I get the following error:
Exception has occurred: NameError
name 'W_regularizer' is not defined

I would really appreciate it if you share a solution
thanks a lot

[WaqasSultani]

I think you have different keras ( and backend theano version) compared to what I used in experiments

[bardia-esm]

Hello @WaqasSultani thanks for your great work, so I guess I have to use the older version of keras

[Singapore-mor]

Hello @WaqasSultani thanks for your great work, so I guess I have to use the older version of keras

Hi BaRdia-eSm i ,
when I try to run Demo.py, i confronted the same problem
Exception has occurred: ValueError
I tried to use the older version of keras, keras 1.10
but it occurs
AttributeError: module 'tensorflow' has no attribute 'python'
I don't know what happened

[libb999]

Hello @WaqasSultani thanks for your great work, so I guess I have to use the older version of keras

Hi BaRdia-eSm i ,
when I try to run Demo.py, i confronted the same problem
Exception has occurred: ValueError
I tried to use the older version of keras, keras 1.10
but it occurs
AttributeError: module 'tensorflow' has no attribute 'python'
I don't know what happened

Hi，I meet the same problem： AttributeError: module 'tensorflow' has no attribute 'python'
can you tell me how to solve it?
thank you very much

[iShahad97]

@libb999 & @Singapore-mor, you have to change the backend from tensorflow to theano, there are two ways:

1. Configure the file "$ HOME / .keras / keras.json" and set "theano" as back-end:

{
"image_data_format": "channels_last",
"epsilon": 1e-07,
"floatx": "float32",
"backend": "theano"
}
2. Use this code:
def set_keras_backend(backend):

if K.backend() != backend:
os.environ['KERAS_BACKEND'] = backend
importlib.reload(K)
assert K.backend() == backend

set_keras_backend("theano")

[sahilsingh31]

File "/home/sahilsingh/.local/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 129, in deserialize_keras_object
raise ValueError('Improper config format: ' + str(config))

ValueError: Improper config format: {'l2': 0.0010000000474974513, 'name': 'WeightRegularizer', 'l1': 0.0}

how to solve this error, i tried for various solutions over internet but didn't got one

[sanjayroka05]

File "/home/sahilsingh/.local/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 129, in deserialize_keras_object
raise ValueError('Improper config format: ' + str(config))

ValueError: Improper config format: {'l2': 0.0010000000474974513, 'name': 'WeightRegularizer', 'l1': 0.0}

how to solve this error, i tried for various solutions over internet but didn't got one

I'm also having the same errror...

ValueError: Improper config format: {'l2': 0.0010000000474974513, 'name': 'WeightRegularizer', 'l1': 0.0}

[Angel3636]

File "/home/sahilsingh/.local/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 129, in deserialize_keras_object
raise ValueError('Improper config format: ' + str(config))
ValueError: Improper config format: {'l2': 0.0010000000474974513, 'name': 'WeightRegularizer', 'l1': 0.0}
how to solve this error, i tried for various solutions over internet but didn't got one

I'm also having the same errror...

ValueError: Improper config format: {'l2': 0.0010000000474974513, 'name': 'WeightRegularizer', 'l1': 0.0}

Hello, is anyone got the solution for this?

[jiafeixiaoye]

File "/home/sahilsingh/.local/lib/python3.6/site-packages/keras/utils/generic_utils.py", line 129, in deserialize_keras_object
raise ValueError('Improper config format: ' + str(config))

ValueError: Improper config format: {'l2': 0.0010000000474974513, 'name': 'WeightRegularizer', 'l1': 0.0}

how to solve this error, i tried for various solutions over internet but didn't got one

It seems the official model is written by Keras1 and you installed Keras2. You can modify the model file with Keras2 format.
Here I replace "W_regularizer": {"l2": 0.0010000000474974513, "name": "WeightRegularizer", "l1": 0.0}
with "kernel_regularizer": {"class_name": "L1L2", "config": {"l2": 0.0010000000474974513, "l1": 0.0}}
and it works.