) #TODO better not to copy and play with indices, instead. whatever!
scores = disc_scores[:]
assert len(scores) == train_data[0].shape[0]
rng_state = np.random.get_state()
np.random.shuffle(images)
np.random.set_state(rng_state)
np.random.shuffle(targets)
np.random.set_state(rng_state)
np.random.shuffle(scores)
#sample the initial training set
daal_set_indices = random.sample(range(train_data[0].shape[0]),
INITIAL_TRAINING_SIZE)
#train the classifier with the initial set
daal_train_data = (images[daal_set_indices],
targets[daal_set_indices])
classifier_daal.train(daal_train_data,
MAX_ITER / len(daal_train_data))
acc = classifier_daal.evaluate(test_data)
#arr_range = np.arange(train_data[0].shape[0])
daal_accuracies.append(acc)
for step in range(ACTIVE_LEARNING_STEPS):
print "step", step
#get predicted probabilities of the unlabel set and compute the entropies
predictions = classifier_daal.predict(images)
entropies = get_entropy(predictions) #lower the better
entropies = normalize(entropies)
#entropies -> less better [0-1]
entropies = 1 - entropies
weighted_entropies = entropies * scores
# we would like to select the largest
argsorted = np.argsort(
weighted_entropies)[::-1] #increasing sort, then reversed
rng_state = np.random.get_state()
np.random.shuffle(images)
np.random.set_state(rng_state)
np.random.shuffle(targets)
np.random.set_state(rng_state)
np.random.shuffle(scores)
#sample the initial training set
train_set_indices = random.sample(range(train_data[0].shape[0]), INITIAL_TRAINING_SIZE)
score_argsort = np.argsort(scores[:])
daal_set_indices = score_argsort[-INITIAL_TRAINING_SIZE:].tolist()
print 'TRAIN_SET_INDICES', len(train_set_indices)
print 'DAAL_SET_INDICES', len(daal_set_indices)
#train the classifier with the initial set
my_train_data = (images[train_set_indices], targets[train_set_indices])
daal_train_data = (images[daal_set_indices], targets[daal_set_indices])
classifier_daal.train(daal_train_data)
classifier_entropy.train(my_train_data)
acc = classifier_entropy.evaluate(test_data)
entropy_accuracies.append(acc)
acc = classifier_daal.evaluate(test_data)
daal_accuracies.append(acc)
for step in range(ACTIVE_LEARNING_STEPS):
print "step", step
## Entropy:
#get predicted probabilities of the unlabel set and compute the entropies
print "making entropy decisions"
predictions = classifier_entropy.predict(images[train_set_indices])
entropies = get_entropy(predictions)#lower the better
argsorted = np.argsort(entropies)[::-1]#increasing sort
#start from the beginning and find the first 10 samples that are not already labelled
