New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
AttributeError: 'Convolution2D' object has no attribute 'get_output' #3166
Comments
The new backend API requires the output to also be a list, not sure if this applies to using the pure theano.function. You should also pass in the learning phase (e.g. train vs test). Try using this function from here
|
What could I pass as an argument to this |
|
Thanks a ton! But what about other usages like: |
Just pass in that layer number as the 2nd parameter
You could also modify it to use the layer name, to accept a list of layers (and get a list of activations), or also to return the backend function that you can call with data yourself |
I am getting this error for w model.layers[0].w.get_value() #weights of the parameters AttributeError Traceback (most recent call last) AttributeError: 'Convolution2D' object has no attribute 'w' |
same issue as above.. |
Hello. I arranged my code as above
but then I get this error
What's wrong with imshow? Please help |
@fragiacalone Hi, did you find whats wrong with imshow I am stuck on the same. |
hello everyboby I have some error after executing this part of code: visualizing intermediate layersoutput_layer = model.layers[0].get_output() It give me this error: Traceback (most recent call last): File "", line 1, in AttributeError: 'Conv2D' object has no attribute 'get_output' Need someone help Ps: the full code==>https://learnandshare645.blogspot.com/2016/06/feeding-your-own-data-set-into-cnn.html?showComment=1519292737662#c3337302287175052994 |
Error:
File "./VGG_Keras.py", line 86, in <module> get_activations = theano.function([model.layers[0].input], model.layers[1].get_output(train=False), allow_input_downcast=True) AttributeError: 'Convolution2D' object has no attribute 'get_output'
I have also tried
.output
and.get_out_at
both of which aren't working. I have the updated versions of keras and theano. Please help.The text was updated successfully, but these errors were encountered: