def main():
# prepare data
train, valid = utility.prepare_data()
# get model
model = nvidia_model()
model.summary()
# generators for training and validation
BATCH = 128
train_gen = utility.next_train_batch(train, BATCH)
valid_gen = utility.next_valid_batch(valid, BATCH)
# training
EPOCHS = 5
TRAINS = 20480
VALIDS = 4096
model.compile(optimizer=Adam(1e-2), loss="mse")
history = model.fit_generator(train_gen,
samples_per_epoch=TRAINS,
nb_epoch=EPOCHS,
validation_data=valid_gen,
nb_val_samples=VALIDS,
verbose=1)
# save model, weights
model.save_weights('model.h5')
with open('model.json', 'w') as f:
f.write(model.to_json())
def train():
args = utility.get_inputs()
image_dataset, dataloader = utility.prepare_data(args.datadir)
model = build_model(args.arch, args.hidden_units)
criterion = nn.NLLLoss()
optimizer = optim.Adam(model.classifier.parameters(),
lr=args.learning_rate)
model.to(args.gpu)
with active_session():
steps = 0
running_loss = 0
print_every = 40
for e in range(args.epochs):
for images, labels in dataloader['train']:
model.train()
steps += 1
images, labels = images.to(args.gpu), labels.to(args.gpu)
optimizer.zero_grad()
output = model.forward(images)
loss = criterion(output, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if steps % print_every == 0:
model.eval()
with torch.no_grad():
test_loss, accuracy = validation(
model, dataloader['test'], criterion, args.gpu)
print(
"Epoch: {}/{}.. ".format(e + 1, args.epochs),
"Training Loss: {:.3f}.. ".format(running_loss /
print_every),
"Validation Loss: {:.3f}.. ".format(
test_loss / len(dataloader['test'])),
"Test Accuracy: {:.3f}".format(
accuracy / len(dataloader['test'])))
running_loss = 0
model.train()
model.optimizer_state_dict = optimizer.state_dict()
model.class_to_idx = image_dataset['train'].class_to_idx
return model, args.save_dir
type=int,
help='the number of hidden units')
args = parser.parse_args()
data_dir = args.datadirectory
save_dir = args.save_dir
arch = args.arch
hidden_units = args.hidden_units
epochs = args.epochs if args.epochs else 10
lr = args.learning_rate if args.learning_rate else 0.001
use_gpu = True if args.gpu else False
if hidden_units:
model = network.Model(arch, hidden_units, pretrained=True)
else:
model = network.Model(arch, pretrained=True)
train_data = prepare_data(data_dir + '/train/', True)
validation_data = prepare_data(data_dir + '/valid/', False)
train_dataloader = dataloader(train_data, True)
validation_dataloader = dataloader(validation_data, False)
trained_model = train(model, lr, train_dataloader, validation_dataloader,
epochs, use_gpu)
if save_dir:
save_checkpoints(train_data, trained_model, save_dir)
else:
print('Training is finished, no directory found to save model')
# From:https://campus.datacamp.com # Import the libraries import utility as u train, test = u.load_data() train = u.prepare_data(train) # Create train_two with the newly defined feature train_two = train.copy() train_two["Family_size"] = 1 train_two["Family_size"] = train_two["SibSp"] + train_two["Parch"] + 1 train_two["Family_size"] = train_two["Family_size"].fillna(1) print(train_two) # Create a new feature set and add the new feature feature_list = ["Pclass", "Sex", "Age", "Fare", "SibSp", "Parch", "Family_size"] #Control overfitting by setting "max_depth" to 10 and "min_samples_split" to 5 : my_tree_two max_depth = 10 min_samples_split = 5 my_tree, features, target = u.train_model(train_two, feature_list, max_depth, min_samples_split) # Look at the importance and score of the included features print(my_tree.feature_importances_) print(my_tree.score(features, target)) u.plot_result(feature_list, my_tree, features, target)
# From:https://campus.datacamp.com
# Import the libraries
import matplotlib.pyplot as plt
from sklearn.ensemble import RandomForestClassifier
#import sklearn.ensemble.RandomForestClassifier as RandomForestClassifier
import utility as u
train, test = u.load_data()
train = u.prepare_data(train)
test = u.prepare_data(test)
# We want the Pclass, Age, Sex, Fare, SibSp, Parch, and Embarked variables
feature_list = ["Pclass", "Age", "Sex", "Fare", "SibSp", "Parch", "Embarked"]
features_forest = train[feature_list].values
target = train["Survived"].values
# Building and fitting my_forest
forest = RandomForestClassifier(max_depth=10,
min_samples_split=2,
n_estimators=100,
random_state=1)
my_forest = forest.fit(features_forest, target)
# Print the score of the fitted random forest
print(my_forest.score(features_forest, target))
# Compute predictions on our test set features then print the length of the prediction vector
test_features = test[feature_list].values
pred_forest = my_forest.predict(test_features)
print(len(pred_forest))
model.compile(optimizer=Adam(1e-2), loss="mse")
history = model.fit_generator(train_gen,
samples_per_epoch=TRAINS,
nb_epoch=EPOCHS,
validation_data=valid_gen,
nb_val_samples=VALIDS,
verbose=1)
# save model, weights
model.save_weights('model.h5')
with open('model.json', 'w') as f:
f.write(model.to_json())
if __name__ == '__main__':
#main()
train, valid = utility.prepare_data()
#utility.test_image_shear(train)
#utility.test_image_gamma(train)
#utility.test_image_flip(train)
#utility.test_augmented_image(train)
utility.test_left_center_right(train)