def main(model, training_cnf, data_dir, start_epoch, resume_lr, weights_from,
clean, visuals):
util.check_required_program_args([model, training_cnf, data_dir])
model_def = util.load_module(model)
model = model_def.model
cnf = util.load_module(training_cnf).cnf
util.init_logging('train.log',
file_log_level=logging.INFO,
console_log_level=logging.INFO,
clean=clean)
if weights_from:
weights_from = str(weights_from)
data_set = DataSet(data_dir, model_def.image_size[0])
training_iter, validation_iter = create_training_iters(
cnf, data_set, model_def.crop_size, start_epoch,
cnf.get('iterator_type', 'queued') == 'parallel')
trainer = SupervisedTrainer(model,
cnf,
training_iter,
validation_iter,
classification=cnf['classification'])
trainer.fit(data_set,
weights_from,
start_epoch,
resume_lr,
verbose=1,
summary_every=cnf.get('summary_every', 10),
clean=clean,
visuals=visuals)
def main(model, training_cnf, data_dir, parallel, start_epoch, weights_from,
resume_lr, gpu_memory_fraction, is_summary):
model_def = util.load_module(model)
model = model_def.model
cnf = util.load_module(training_cnf).cnf
util.init_logging('train.log',
file_log_level=logging.INFO,
console_log_level=logging.INFO)
if weights_from:
weights_from = str(weights_from)
data_set = DataSet(data_dir, model_def.image_size[0])
standardizer = cnf.get('standardizer', NoOpStandardizer())
training_iter, validation_iter = create_training_iters(cnf,
data_set,
standardizer,
model_def.crop_size,
start_epoch,
parallel=parallel)
trainer = SupervisedTrainer(model,
cnf,
training_iter,
validation_iter,
resume_lr=resume_lr,
classification=cnf['classification'],
gpu_memory_fraction=gpu_memory_fraction,
is_summary=is_summary,
loss_type='kappa_log')
trainer.fit(data_set,
weights_from,
start_epoch,
verbose=1,
summary_every=399)
def train():
mnist = input_data.read_data_sets("MNIST_data/", one_hot=False)
width = 28
height = 28
train_images = mnist[0].images.reshape(-1, height, width, 1)
train_labels = mnist[0].labels
validation_images = mnist[1].images.reshape(-1, height, width, 1)
validation_labels = mnist[1].labels
data_set = DataSet(train_images, train_labels,
validation_images, validation_labels)
training_cnf = {
'classification': True,
'validation_scores': [('validation accuracy', util.accuracy_wrapper), ('validation kappa', util.kappa_wrapper)],
'num_epochs': 50,
'lr_policy': StepDecayPolicy(
schedule={
0: 0.01,
30: 0.001,
}
)
}
util.init_logging('train.log', file_log_level=logging.INFO,
console_log_level=logging.INFO)
trainer = SupervisedTrainer(model, training_cnf, classification=training_cnf[
'classification'], is_summary=True)
trainer.fit(data_set, weights_from=None,
start_epoch=1, verbose=1, summary_every=10)
def main(model, training_cnf, data_dir, start_epoch, resume_lr, weights_from, clean):
util.check_required_program_args([model, training_cnf, data_dir])
model_def = util.load_module(model)
model = model_def.model
cnf = util.load_module(training_cnf).cnf
util.init_logging('train.log', file_log_level=logging.INFO, console_log_level=logging.INFO, clean=clean)
if weights_from:
weights_from = str(weights_from)
data_set = DataSet(data_dir, model_def.image_size[0])
training_iter = BatchIterator(cnf['batch_size_train'], True)
validation_iter = BatchIterator(cnf['batch_size_test'], True)
trainer = SupervisedTrainer(model, cnf, training_iter, validation_iter, classification=cnf['classification'])
trainer.fit(data_set, weights_from, start_epoch, resume_lr, verbose=1,
summary_every=cnf.get('summary_every', 10), clean=clean)
return end_points(is_training)
training_cnf = {
'classification':
True,
'validation_scores': [('validation accuracy', util.accuracy_wrapper),
('validation kappa', util.kappa_wrapper)],
'num_epochs':
30,
'lr_policy':
StepDecayPolicy(schedule={
0: 0.001,
15: 0.0001,
}),
'optimizer':
tf.train.AdamOptimizer()
}
util.init_logging('train.log',
file_log_level=logging.INFO,
console_log_level=logging.INFO)
trainer = SupervisedTrainer(model,
training_cnf,
classification=training_cnf['classification'])
trainer.fit(data_set,
weights_from=None,
start_epoch=1,
verbose=1,
summary_every=10)