def run(self):
imgs, labels = read_mnist(path=self.data_path, training=True)
imgs = binarize_mnist_images(imgs)
self.fit(imgs, labels)
imgs, labels = read_mnist(path=self.data_path, training=False)
imgs = binarize_mnist_images(imgs)
self.coding_cost = -self.score(imgs, labels)
def run(self):
# Fit training data.
imgs, labels = read_mnist(path=self.data_path, training=True)
imgs = binarize_mnist_images(imgs)
machines = self.fit(imgs, labels)
# Compute error rate on test set.
imgs, labels = read_mnist(path=self.data_path, training=False)
idx = np.in1d(labels, machines.keys())
imgs = binarize_mnist_images(imgs[idx])
labels = labels[idx]
predicted = self.predict(imgs)
self.error_rate = np.sum(predicted != labels) / float(len(imgs))
def run(self):
# Validate settings.
if len(self.digits) < 2:
raise ValueError("Must use at least 2 digit classes")
# Train the machine.
imgs, labels = read_mnist(path=self.data_path, training=True)
idx = np.in1d(labels, self.digits)
imgs = binarize_mnist_images(imgs[idx])
self.machine = machine = self.create_machine()
self.train(machine, imgs)
# Score the machine.
imgs, labels = read_mnist(path=self.data_path, training=False)
imgs = binarize_mnist_images(imgs)
self.score(imgs, labels)
def run(self):
imgs, labels = read_mnist(path=self.data_path, training=True)
imgs = binarize_mnist_images(imgs)
gs = GridSearchCV(self.base_runner, self.param_grid,
n_jobs = self.jobs, pre_dispatch = '2*n_jobs',
cv = self.cv, verbose = self.verbose)
gs.fit(imgs, labels)
self.param_scores = gs.grid_scores_
self.best_params = gs.best_params_
self.best_score = gs.best_score_
def prepare_mnist(n_train):
download_mnist()
X, Y = read_mnist()
X = image_to_vec(X)
X = X / 255
X = X.T
Y = Y.T
n_samples = X.shape[1]
shuffle_idx = np.random.permutation(n_samples)
X_shuffled = X[:, shuffle_idx]
Y_shuffled = Y[:, shuffle_idx]
X_train = X_shuffled[:, :n_train]
Y_train = Y_shuffled[:, :n_train]
X_test = X_shuffled[:, n_train:]
Y_test = Y_shuffled[:, n_train:]
Y_train = one_hot_encode(Y_train)
return X_train, Y_train, X_test, Y_test
from mnist import read_mnist
from sklearn.linear_model import LogisticRegression
import logging
logging.basicConfig(
level=logging.DEBUG,
format=
'%(asctime)s %(filename)s[line:%(lineno)d] %(levelname)s %(message)s',
datefmt='%a, %d %b %Y %H:%M:%S')
if __name__ == '__main__':
train_image, train_label, test_image, test_label = read_mnist()
clf = LogisticRegression()
logging.info("Fiting")
clf.fit(train_image, train_label)
logging.info("Scoring")
logging.info("Score: %lf\n", clf.score(test_image, test_label))
def train():
"""Train CIFAR-10 for a number of steps."""
data_sets = mnist.read_mnist(FLAGS.data_dir, FLAGS.fake_data)
with tf.Graph().as_default():
global_step = tf.Variable(0, trainable=False)
images_placeholder, labels_placeholder = placeholder_inputs(
FLAGS.batch_size)
# Build a Graph that computes the logits predictions from the
# inference model.
logits = partnet.inference(images_placeholder, is_training=True)
# Calculate loss.
loss = partnet.loss(logits, labels_placeholder, sparse_weight=0.01)
# Add the Op to compare the logits to the labels during evaluation.
eval_correct = partnet.evaluation(logits, labels_placeholder)
# Build a Graph that trains the model with one batch of examples and
# updates the model parameters.
train_op = partnet.train(loss, global_step)
# Create a saver.
saver = tf.train.Saver(tf.all_variables())
# Build the summary operation based on the TF collection of Summaries.
summary_op = tf.merge_all_summaries()
# Build an initialization operation to run below.
init = tf.initialize_all_variables()
# Start running operations on the Graph.
sess = tf.Session()
sess.run(init)
summary_writer = tf.train.SummaryWriter(FLAGS.train_dir, sess.graph)
for step in xrange(FLAGS.max_steps):
start_time = time.time()
feed_dict = fill_feed_dict(data_sets.train, images_placeholder,
labels_placeholder)
_, loss_value = sess.run([train_op, loss], feed_dict=feed_dict)
duration = time.time() - start_time
assert not np.isnan(loss_value), 'Model diverged with loss = NaN'
if step % 100 == 0:
num_examples_per_step = FLAGS.batch_size
examples_per_sec = num_examples_per_step / duration
sec_per_batch = float(duration)
format_str = (
'%s: step %d, loss = %.2f (%.1f examples/sec; %.3f '
'sec/batch)')
print(format_str % (datetime.now(), step, loss_value,
examples_per_sec, sec_per_batch))
summary_str = sess.run(summary_op, feed_dict=feed_dict)
summary_writer.add_summary(summary_str, step)
summary_writer.flush()
# Save the model checkpoint periodically.
if step % 1000 == 0 or (step + 1) == FLAGS.max_steps:
checkpoint_path = os.path.join(FLAGS.train_dir, 'model.ckpt')
saver.save(sess, checkpoint_path, global_step=step)
# Evaluate against the training set.
print('Training Data Eval:')
do_eval(sess, eval_correct, images_placeholder,
labels_placeholder, data_sets.train)
# Evaluate against the validation set.
print('Validation Data Eval:')
do_eval(sess, eval_correct, images_placeholder,
labels_placeholder, data_sets.validation)
# Evaluate against the test set.
print('Test Data Eval:')
do_eval(sess, eval_correct, images_placeholder,
labels_placeholder, data_sets.test)
sess.close() # free resource
import numpy as np
from mnist import read_mnist
from sklearn.linear_model import LogisticRegression
import logging
logging.basicConfig(level=logging.DEBUG, format='%(asctime)s %(filename)s[line:%(lineno)d] %(levelname)s %(message)s', datefmt='%a, %d %b %Y %H:%M:%S')
if __name__ == '__main__':
w = np.load('theta.npy')
train_image, train_label, test_image, test_label = read_mnist()
clf = LogisticRegression()
logging.info("Fiting")
clf.fit(np.dot(train_image, w), train_label)
logging.info("Scoring")
logging.info("Score: %lf\n", clf.score(np.dot(test_image, w), test_label))
# -*- coding: utf-8 -*-
"""
Created on Tue Feb 14 13:53:51 2017
@author: admin-congo
"""
import numpy as np
import mnist
import NNvars
full_dataset = [i for i in mnist.read_mnist("training")]
np.random.shuffle(full_dataset)
training_set = full_dataset[:NNvars.numSamples]
verification_set = full_dataset[NNvars.numSamples:NNvars.numVerification +
NNvars.numSamples]
test_set = [i for i in mnist.read_mnist("testing")]
