|
|
@@ -375,17 +375,6 @@ class NextConvGeN(GanBaseClass):
|
|
|
conv_samples = [conv_samples, maj_batch]
|
|
|
return conv_samples
|
|
|
|
|
|
- def trainDiscriminator(samples):
|
|
|
- concat_samples = tf.concat([samples[0], samples[1]], axis=0)
|
|
|
- self.timing["Fit"].start()
|
|
|
- ## switch on discriminator training
|
|
|
- discriminator.trainable = True
|
|
|
- ## train the discriminator with the concatenated samples and the one-hot encoded labels
|
|
|
- discriminator.fit(x=concat_samples, y=labels, verbose=0, batch_size=20)
|
|
|
- ## switch off the discriminator training again
|
|
|
- discriminator.trainable = False
|
|
|
- self.timing["Fit"].stop()
|
|
|
-
|
|
|
def genSamplesForDisc():
|
|
|
for min_idx in range(minSetSize):
|
|
|
yield createSamples(min_idx)
|
|
|
@@ -465,9 +454,6 @@ class NextConvGeN(GanBaseClass):
|
|
|
## min_idxs -> indices of points in minority class
|
|
|
## gen -> convex combinations generated from each neighbourhood
|
|
|
self.timing["BMB"].start()
|
|
|
- # indices = [i for i in range(self.minSetSize) if i not in min_idxs]
|
|
|
- # r = self.nmbMin.basePoints[shuffle(indices)[0:self.gen]]
|
|
|
-
|
|
|
indices = randomIndices(self.minSetSize, outputSize=self.gen, indicesToIgnore=min_idxs)
|
|
|
r = self.nmbMin.basePoints[indices]
|
|
|
self.timing["BMB"].stop()
|
