Lasagna regression: error
I am trying to run a regression using lasagne / nolearn. I'm having trouble finding documentation on how to do this (new to deep learning in general).
Launch from a simple network (one hidden layer)
from lasagne import layers
from lasagne.nonlinearities import softmax
from lasagne.updates import nesterov_momentum
from nolearn.lasagne import NeuralNet
print(np.shape(X)) # (137, 43)
print(np.shape(y)) # (137,)
layers_s = [('input', layers.InputLayer),
('dense0', layers.DenseLayer),
('output', layers.DenseLayer)]
net_s = NeuralNet(layers=layers_s,
input_shape=(None, num_features),
dense0_num_units=43,
output_num_units=1,
output_nonlinearity=None,
regression=True,
update=nesterov_momentum,
update_learning_rate=0.001,
update_momentum=0.9,
eval_size=0.2,
verbose=1,
max_epochs=100)
net_s.fit(X, y)
I am getting the following error:
TypeError Traceback (most recent call last)
<ipython-input-23-23c15ceec104> in <module>()
----> 1 net_s.fit(X, y)
/home/alex/anaconda3/lib/python3.4/site-packages/nolearn/lasagne.py in fit(self, X, y)
148 out, self.loss, self.update,
149 self.X_tensor_type,
--> 150 self.y_tensor_type,
151 )
152 self.train_iter_, self.eval_iter_, self.predict_iter_ = iter_funcs
/home/alex/anaconda3/lib/python3.4/site-packages/nolearn/lasagne.py in _create_iter_funcs(self, output_layer, loss_func, update, input_type, output_type)
298 all_params = get_all_params(output_layer)
299 update_params = self._get_params_for('update')
--> 300 updates = update(loss_train, all_params, **update_params)
301
302 train_iter = theano.function(
/home/alex/src/lasagne/lasagne/updates.py in nesterov_momentum(loss, all_params, learning_rate, momentum)
38 # such that the gradient can be evaluated at the current parameters.
39 def nesterov_momentum(loss, all_params, learning_rate, momentum=0.9):
---> 40 all_grads = theano.grad(loss, all_params)
41 updates = []
42
/home/alex/anaconda3/lib/python3.4/site-packages/theano/gradient.py in grad(cost, wrt, consider_constant, disconnected_inputs, add_names, known_grads, return_disconnected)
431
432 if cost is not None and cost.ndim != 0:
--> 433 raise TypeError("cost must be a scalar.")
434
435 if isinstance(wrt, set):
TypeError: cost must be a scalar.
Thank!..
source to share
Make sure you are using the nolearn and Lasagne versions that work together .
Say you followed Using Convolutional Neural Networks to Define Curriculum by Keyword. Then the right thing to do is install the dependencies from that requirements.txt file , for example:
pip uninstall Lasagne
pip uninstall nolearn
pip install -r https://raw.githubusercontent.com/dnouri/kfkd-tutorial/master/requirements.txt
If, however, you are using nolearn from the Git master, then make sure you have installed the Lasagne version found in the requirements .txt file :
pip uninstall Lasagne
pip install -r https://raw.githubusercontent.com/dnouri/nolearn/master/requirements.txt
source to share
Not sure which version of nolearn and lasagne you are using. I noticed that it y
has a shape (137,)
. From my use, this should be (137, 1)
to work in your case, and in general dim 2 should match output_num_units
.
Try it y.reshape((-1, 1))
.
If that doesn't work, it might be a Python 3 compatibility issue.
source to share