I am predicting a value, I have 2 input layer and an output layer. Here is my code in which I have trained a PyBrain network and then tested it, I am missing how should I give a set of input to the network and how do I get the result. Please help me to proceed forward.
ds = SupervisedDataSet(2,1)
tf = open('data.csv','r')
for line in tf.readlines():
data = [float(x) for x in line.strip().split(',') if x != '']
indata = tuple(data[:2])
outdata = tuple(data[2:])
ds.addSample(indata,outdata)
n = buildNetwork(ds.indim,8,8,ds.outdim,recurrent=True)
t = BackpropTrainer(n,learningrate=0.01,momentum=0.5,verbose=True)
t.trainOnDataset(ds,1000)
t.testOnData(verbose=True)
what I should do next to give an input and predict on the input, How do I get the result for that set of input. Thanks!!
What Is Training Data? In a real-life scenario, training samples consist of measured data of some kind combined with the “solutions” that will help the neural network to generalize all this information into a consistent input–output relationship.
PyBrain already includes a function that does just that, gradientCheck(). You can pass it to any network containing a structural component that you have programmed. It will check if the numeric gradients are (roughly) equal to the gradient specified by the _backwardImplementation() methods.
By calling the .activate() method of the network supplying your input. There's also a more practicle activate on dataset.
And a little tip, you may use the python's native csv module
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With