def main():
"""Run Prediction"""
# Measures total program runtime by collecting start time
start_time = time.time()
# get input args
in_arg = get_input_args()
# Function that checks command line arguments using in_arg
print_command_line_arguments(in_arg)
print()
# get dataloader to load labels and process image
dataloader = ModelDataLoader('data')
category_names = dataloader.get_label_dict(in_arg.category_names)
# use modelloader to load checkpoint
loader = ModelLoader(in_arg.checkpoint_dir)
if loader.checkpoint_exists(in_arg.checkpoint):
print("Loading checkpoint %s" %
(loader.get_checkpoint_path(in_arg.checkpoint)))
model = loader.load_checkpoint(
in_arg.checkpoint, model_use_gpu=in_arg.gpu, with_trainer=False)
else:
print("Checkpoint '%s' does not exist. Exiting." %
(loader.get_checkpoint_path(in_arg.checkpoint)))
return
print()
# convert image
image = dataloader.process_image(in_arg.image)
# run prediction
probs, classes = model.predict(image, in_arg.top_k)
labels = [category_names[c] for c in classes]
for prob, clas, label in zip(probs, classes, labels):
print("%5.3f%% %s [%s]" % (prob*100, label, clas))
print()
print("Total Prediction Duration: %.3fs" % (time.time() - start_time))
def main():
"""Run Training Session"""
# Measures total program runtime by collecting start time
start_time = time.time()
# get input args
in_arg = get_input_args()
# Function that checks command line arguments using in_arg
print_command_line_arguments(in_arg)
print()
# load datasets
dataloader = ModelDataLoader(in_arg.data_dir)
train_dataset, train_dataloader = dataloader.get_train_data()
valid_dataset, valid_dataloader = dataloader.get_validation_data()
test_dataset, test_dataloader = dataloader.get_test_data()
# Use model loader to load existing checkpoint
loader = ModelLoader(in_arg.checkpoint_dir)
if loader.checkpoint_exists(in_arg.checkpoint):
# load checkpoint
print("Loading checkpoint %s" %
(loader.get_checkpoint_path(in_arg.checkpoint)))
model, trainer = loader.load_checkpoint(
in_arg.checkpoint, model_use_gpu=in_arg.gpu)
print("Epochs trained so far: %d" % (trainer.trained_epochs))
else:
# no checkpoint, create fresh model using input arguments
print("Checkpoint '%s' does not exist" %
(loader.get_checkpoint_path(in_arg.checkpoint)))
model = Model(train_dataset.class_to_idx,
arch=in_arg.arch, use_gpu=in_arg.gpu,
hidden_units_1=in_arg.hidden_units_1, hidden_units_2=in_arg.hidden_units_2,
dropout_1=in_arg.dropout_1, dropout_2=in_arg.dropout_2)
trainer = ModelTrainer(model, learning_rate=in_arg.learning_rate)
print()
print("Model training in session...")
print()
epochs = in_arg.epochs
# train model and print results
for result in trainer.train_epochs(epochs, train_dataloader, valid_dataloader):
print(
"Epoch: %3d/%3d" % (result['epoch']+1, epochs),
" | Train Loss: %10.5f" % (result['train_loss']),
" | Validation Loss: %10.5f" % (result['validation_loss']),
" | Validation Acc: %6.3f%%" % (
result['validation_accuracy'] * 100),
" | Duration: %10.3fs" % (result['duration'])
)
print()
print("Testing model against test data...")
print()
# test model against test data
test_result = trainer.test(test_dataloader)
print(
"Test Loss: %10.5f" % (test_result['test_loss']),
" | Test Acc: %6.3f%%" % (test_result['test_accuracy'] * 100),
" | Duration: %10.3fs" % (test_result['duration'])
)
# save checkpoint
loader.save_checkpoint(in_arg.checkpoint, model, trainer)
print()
print("Total Train Duration: %.3fs" % (time.time() - start_time))