getting unexpected keyword argument 'include_top'

[Heavy02011]

After using the example I get the following error:

`/keras_squeezenet/squeezenet.py in SqueezeNet(input_tensor, input_shape, weights, classes)
56
57
---> 58 input_shape = _obtain_input_shape(input_shape,default_size=227,min_size=48,data_format=K.image_data_format(),include_top=True)
59 #input_shape = _obtain_input_shape(input_shape,default_size=227,min_size=48,data_format=K.image_data_format())
60

TypeError: _obtain_input_shape() got an unexpected keyword argument 'include_top'`

Any idea what I'm overlooking? thx

[shunsuke227ono]

@Heavy02011

Are you using Keras v2.0.0?
Or you can change your keras version to 2.0.0 via doing like pip install keras==2.0.0.

Because it seems like the error depends on keras version. At keras 2.0.8, which i was using, _obtain_input_shape (from keras.applications.imagenet_utils import _obtain_input_shape) method does not expect to get include_top argument. At keras 2.0.0, the method has include_top argument. So I just changed keras version to 2.0.0 and it works now!

[ghost]

I am using keras==2.0.6, and i also got this error:
"TypeError: SqueezeNet() got an unexpected keyword argument 'include_top' "
and this error still exists while i changed keras==2.0.0

[Rafi-afridi]

change "include_top" to "require_flatten". Issue will resolved

[a6225301]

i made it success by degrade the keras version to 2.0.0 , and then change "include_top" to "require_flatten".

[creative-h]

1. clone this git repo: "https://github.com/keras-team/keras-applications"
2. then import it " from keras import applications"
3. Now import vgg16 "from keras.applications.vgg16 import VGG16"

this will work for keras 2.2.4