"../normalizedData/trainingSetY.npy",
"../normalizedData/testSetX.npy",
"../normalizedData/testSetY.npy")
model = Model([40])
log_model = LogisticRegressionModel()
soft_model = SoftmaxRegressionModel()
plot_x = list()
plot_y = list()
plot_y_log = list()
plot_y_soft = list()
with tf.Session() as session:
session.run(tf.global_variables_initializer())
epoch_index = 0
while epoch_index < epochs:
samples, labels = batcher.get_batch(batch_size)
model.train_model(session, samples, labels)
log_model.train_model(session, samples, labels)
soft_model.train_model(session, samples, labels)
if batcher.epoch_finished():
batcher.reset_epoch()
test_samples, test_labels = batcher.get_test_batch()
fp = 0
fn = 0
pred = np.argmax(model.predict(session, test_samples), axis=1)
for index, i in enumerate(np.argmax(test_labels, axis=1)):
if pred[index] == 1 and i != pred[index]:
fp += 1
if pred[index] == 0 and i != pred[index]:
fn += 1
accuracy += model.get_accuracy(session, image_batches[i],
label_batches[i])
accuracy /= len(image_batches)
train_accuracy = 0
image_batches, label_batches = batcher.get_test_training_batches(
50)
for i in range(len(image_batches)):
train_accuracy += model.get_accuracy(session, image_batches[i],
label_batches[i])
train_accuracy /= len(image_batches)
accuracy_data.append(accuracy)
train_accuracy_data.append(train_accuracy)
print("Epoch %i \t| test_acc: %f | train_acc: %f | time: %f" %
(epoch_index, accuracy, train_accuracy,
time() - epoch_start_time))
saver.save(session, os.path.join("checkpoints/resnet_basic.ckpt"))
batcher.prepare_epoch()
step_index = 0
epoch_start_time = time()
if epoch_index == epochs:
break
epoch_index += 1
images, labels = batcher.get_batch(batch_size)
model.train_model(session, images, labels)
# print("Step %i" % step_index)
# step_index += 1
print("Training complete")
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
from data_batcher import DataBatcher
from vae_model import VAEModel
from time import time
import numpy as np
import tensorflow as tf
print("Finding training data...")
batcher = DataBatcher("generated_data")
print("Building model...")
model = VAEModel(50, [40, 35, 30])
batch_size = 5000
training_steps = 200000
print("Starting training...")
with tf.Session() as session:
session.run(tf.global_variables_initializer())
for i in range(training_steps):
batch, epoch_complete = batcher.get_batch(batch_size)
model.train_model(session, inputs=batch)
if epoch_complete:
test_batch = batcher.get_test_batch()
loss = model.get_loss(session, inputs=test_batch)
print("Epoch complete - loss: {}".format(loss))
if i % 500 == 0:
test_batch = batcher.get_test_batch()
loss = model.get_loss(session, inputs=test_batch)
print("Step {} - loss: {}".format(i, loss))
batcher = DataBatcher("normalizedData/trainingSetX.npy",
"normalizedData/trainingSetY.npy",
"normalizedData/testSetX.npy",
"normalizedData/testSetY.npy")
epochs = 500
batch_size = 20
plot_x = list()
plot_y = list()
with tf.Session() as session:
session.run(tf.global_variables_initializer())
epoch_index = 0
while epoch_index < epochs:
samples, classes_labels = batcher.get_batch(batch_size)
session.run(train, feed_dict={inputs: samples, labels: classes_labels})
if batcher.epoch_finished():
batcher.reset_epoch()
test_samples, test_labels = batcher.get_test_batch()
class_loss = session.run(loss,
feed_dict={
inputs: test_samples,
labels: test_labels
})
acc = session.run(accuracy,
feed_dict={
inputs: test_samples,
labels: test_labels
})
plot_x.append(epoch_index + 1)
