Hi, could you please provide the version you are using for lasagne and theano
I'm using Theano 0.9 and Lasagne master version but seems incompatible
Thank you.
They are the exact same versions that I used (I don't think Lasagne has seen an API breaking update since).
Can you please provide the error message that you are getting when you try to run this?
The error comes from layers.py, line 95
File "/git/ARC/carc.py", line 114, in
prediction = get_output(l_y)
File "anaconda/envs/dl-mini/lib/python3.5/site-packages/lasagne/layers/helper.py", line 197, in get_output
all_outputs[layer] = layer.get_output_for(layer_inputs, **kwargs)
File "git/ARC/layers.py", line 95, in get_output_for
odd_input = input[:B]
File "anaconda/envs/dl-mini/lib/python3.5/site-packages/theano/tensor/var.py", line 519, in getitem
theano.tensor.subtensor.Subtensor.convert(arg)
File "anaconda/envs/dl-mini/lib/python3.5/site-packages/theano/tensor/subtensor.py", line 378, in convert
slice_b = Subtensor.convert(b, False)
File "anaconda/envs/dl-mini/lib/python3.5/site-packages/theano/tensor/subtensor.py", line 349, in convert
raise TypeError("Expected an integer")
TypeError: Expected an integer
Exception ignored in: <function WeakValueDictionary.init..remove at 0x10d843048>
Traceback (most recent call last):
File "anaconda/envs/dl-mini/lib/python3.5/weakref.py", line 117, in remove
TypeError: 'NoneType' object is not callable
Hey, my code is in Python 2. You are running Python 3 and the division B = input.shape[0] / 2 is returning a float instead of an int. It is causing problems when indexing here: odd_input = input[:B]
pranv
