python - puzzling syntax with theano -
i followed tutorial logistic theano
import numpy import theano import theano.tensor t rng = numpy.random n = 400 # training sample size feats = 784 # number of input variables # initialize bias term b = theano.shared(0., name="b") print("initial model:") print(w.get_value()) print(b.get_value()) # construct theano expression graph p_1 = 1 / (1 + t.exp(-t.dot(x, w) - b)) # probability target = 1 prediction = p_1 > 0.5 # prediction thresholded xent = -y * t.log(p_1) - (1-y) * t.log(1-p_1) # cross-entropy loss function cost = xent.mean() + 0.01 * (w ** 2).sum()# cost minimize gw, gb = t.grad(cost, [w, b]) # compute gradient of cost # w.r.t weight vector w , # bias term b # (we shall return in # following section of tutorial)
but don't know code " prediction = p_1 > 0.5 " . when p_1 > 0.5 ,prediction = true ? or else ?
yes, saying prediction = p_1 > 0.5
equivalent to:
if p_1 > 0.5: prediction = true else: prediction = false
Comments
Post a Comment