p = np.concatenate([
np.repeat(p_common_examples, n_common_examples),
np.repeat(p_subset_examples, n_subset_examples),
],
axis=0)
perm = np.random.choice(indices,
perm_length,
replace=self._sample_with_replacement,
p=p)
return perm_list
if __name__ == '__main__':
ilogger.setup_root_logger('/dev/null', logging.DEBUG)
minibatch_size = 1
learning_rate = 0.01
n_iterations = 100
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
mnist_classifier = MNISTConvNet(minibatch_size,
learning_rate,
n_iterations,
mnist.train,
model_name='UnifiedClassifier',
write_summary=False)
mnist_classifier.test_data = mnist.test
mnist_classifier.train_model()
accuracy = mnist_classifier.evaluate_model(mnist.test)
#!/usr/bin/python3
import scipy.io as sio
import numpy as np
import pickle
import logging
import pdb
from concurrent.futures import ProcessPoolExecutor
import input_data
import sys
import ilogger
import time
ilogger.setup_root_logger('/dev/null', logging.ERROR)
class Metrics(object):
def __init__(self, name):
self.name = name
def __getstate__(self):
state = self.__dict__.copy()
return state
def __setstate__(self, state):
self.__dict__.update(state)
def l2_error(weight1, weight2):
return np.linalg.norm(weight1 - weight2)