def train(train_dir, batch_size, num_batches, log_dir):
images, labels = inputs(train_dir,
batch_size,
num_batches,
one_hot_labels=True,
train=True)
predictions = simple(images)
slim.losses.softmax_cross_entropy(predictions, labels)
total_loss = tf.clip_by_value(slim.losses.get_total_loss(), 1e-10,
1000000.0)
tf.scalar_summary('loss', total_loss)
#optimizer = tf.train.RMSPropOptimizer(0.001, 0.9)
optimizer = tf.train.GradientDescentOptimizer(0.001)
train_op = slim.learning.create_train_op(total_loss,
optimizer,
summarize_gradients=True)
slim.learning.train(train_op, log_dir, save_summaries_secs=20)
import tensorflow as tf
import input_data
data = input_data.read_data_sets("/tmp/data/", one_hot=True)
# model
import model
with tf.variable_scope("simple"):
x = tf.placeholder("float", [None, 784])
y, variables = model.simple(x)
# train
y_ = tf.placeholder("float", [None, 10])
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
train_step = tf.train.GradientDescentOptimizer(0.01).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
saver = tf.train.Saver(variables)
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
for i in range(1000):
batch_xs, batch_ys = data.train.next_batch(100)
sess.run(train_step, feed_dict={x: batch_xs, y_: batch_ys})
print sess.run(accuracy, feed_dict={x: data.test.images, y_: data.test.labels})
path = saver.save(sess, "data/simple.ckpt")
print "Saved:", path
import os
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
data = input_data.read_data_sets("/tmp/data/", one_hot=True)
# model
import model
with tf.variable_scope("simple"):
x = tf.placeholder("float", [None, 784])
y, variables = model.simple(x)
# train
y_ = tf.placeholder("float", [None, 10])
cross_entropy = -tf.reduce_sum(y_ * tf.log(y))
#cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))
#train using the adam optimizer rather than gradient descent
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
saver = tf.train.Saver(variables)
init = tf.initialize_all_variables()
with tf.Session() as sess:
# Restore variables from disk.
saver.restore(sess, "data/simple.ckpt")
print("Model restored.")
print(
import argparse
import model
parser = argparse.ArgumentParser(description="Run the simple net on local.")
if __name__ == "__main__":
args = parser.parse_args()
# Create a parameter server.
net = model.simple()
# net = model.multilayer_perceptron()
# Download MNIST.
ds = model.load_data()
epoch = ds.train.epochs_completed
while True:
# Compute and apply gradients.
xs, ys = ds.train.next_batch(100)
net.sess.run(net.train_step, feed_dict={net.x: xs, net.y: ys})
if ds.train.epochs_completed != epoch:
# Evaluate the current model.
test_xs, test_ys = ds.test.next_batch(ds.test.num_examples)
accuracy = net.compute_accuracy(test_xs, test_ys)
print("Epoch {}: accuracy is {}".format(epoch, accuracy))
epoch = ds.train.epochs_completed
def __init__(self, options, paths):
"""Prepare the network, criterion, optimizer, and data.
Args:
options, dict<str, float/int>: Hyperparameters.
paths, dict<str, str>: Useful paths.
"""
print('Prepare the network and data.')
# Configurations.
self._options = options
self._paths = paths
# Network.
self._net = torch.nn.DataParallel(model.simple()).cuda()
# self._net.load_state_dict(torch.load(r'H:\LiJiaSen\python_project\simple\src\model\bcnn_all_epoch_34.pth'),
# strict=False)
print(self._net)
self._criterion = torch.nn.CrossEntropyLoss().cuda()
# Optimizer.
self._optimizer = torch.optim.SGD(
self._net.parameters(),
lr=self._options['base_lr'],
momentum=0.9,
weight_decay=self._options['weight_decay'])
self._scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
self._optimizer,
mode='max',
factor=0.1,
patience=8,
verbose=True,
threshold=1e-4)
# Data.
train_transforms = torchvision.transforms.Compose([
# torchvision.transforms.RandomResizedCrop(size=448,
# scale=(0.8, 1.0)),
torchvision.transforms.Resize(size=(224, 224)),
# torchvision.transforms.RandomCrop(size=448),
torchvision.transforms.RandomHorizontalFlip(),
torchvision.transforms.RandomVerticalFlip(),
torchvision.transforms.ToTensor(),
# torchvision.transforms.Normalize(mean=(0.485, 0.456, 0.406),
# std=(0.229, 0.224, 0.225)),
])
test_transforms = torchvision.transforms.Compose([
# torchvision.transforms.Resize(size=448),
# torchvision.transforms.CenterCrop(size=448),
torchvision.transforms.Resize(size=(224, 224)),
torchvision.transforms.ToTensor(),
# torchvision.transforms.Normalize(mean=(0.485, 0.456, 0.406),
# std=(0.229, 0.224, 0.225)),
])
train_data = Breast.BreastCancer(
root=r'I:\\Dataset_crop_224_into_five\400x',
train=True,
transform=train_transforms,
download=True)
test_data = Breast.BreastCancer(
root=r'I:\\Dataset_crop_224_into_five\400x',
train=False,
transform=test_transforms,
download=True)
self._train_loader = torch.utils.data.DataLoader(
train_data,
batch_size=self._options['batch_size'],
shuffle=True,
num_workers=4,
pin_memory=False)
self._test_loader = torch.utils.data.DataLoader(test_data,
batch_size=64,
shuffle=False,
num_workers=4,
pin_memory=False)
