def predict_proba(self, X, batch_size=None):
if batch_size is None: batch_size = self.batch_size
yprobs = np.zeros((X.shape[0]), dtype=float)
idx = np.arange(X.shape[0])
vbatch = val_batch_gen([idx, X], batch_size)
for i, (thisidx, thisX) in enumerate(vbatch):
yprobs[thisidx] = self.sess.run(self.y_clf,
feed_dict={self.X: thisX, self.train: False, self.l: 1.0}).flatten()
return yprobs
def domains_predict_proba(self, X, batch_size=None):
if batch_size is None: batch_size = self.batch_size
dprobs = np.zeros((X.shape[0]), dtype=float)
idx = np.arange(X.shape[0])
vbatch = val_batch_gen([idx, X], batch_size)
for i, (thisidx, thisX) in enumerate(vbatch):
dprobs[thisidx] = self.sess.run(self.domain_clf,
feed_dict={
self.X: thisX
}).flatten()
return dprobs