def task_dog_breed_identification(data_path, dataset):
images_path = os.path.join(data_path, dataset, 'images_all')
label_path = os.path.join(data_path, dataset, 'labels.csv')
test_path = os.path.join(data_path, dataset, 'test')
load_dataset = task.Dataset(images_path, label_file=label_path)
@ag.obj(learning_rate=ag.space.Real(0.3, 0.5),
momentum=ag.space.Real(0.90, 0.95),
wd=ag.space.Real(1e-6, 1e-4, log=True),
multi_precision=False)
class NAG(optim.NAG):
pass
classifier = task.fit(dataset=load_dataset,
net=ag.Categorical('standford_dog_resnext101_64x4d',
'standford_dog_resnet152_v1'),
optimizer=NAG(),
epochs=20,
final_fit_epochs=180,
num_trials=40,
ngpus_per_trial=8,
batch_size=48,
verbose=False,
ensemble=1)
test_dataset = task.Dataset(test_path, train=False, crop_ratio=0.65)
inds, probs, probs_all = classifier.predict(test_dataset,
set_prob_thresh=0.001)
ag.utils.generate_prob_csv(test_dataset,
probs_all,
custom='./submission.csv')
def test_tricks(test_trials):
dataset = 'shopee-iet'
data_dir = './'
download_shopee(data_dir, dataset)
for i in range(test_trials):
print('Test:{}\n'.format(i))
target = config_choice(dataset, data_dir, tricks_combination[i])
classifier = task.fit(dataset=task.Dataset(target['dataset']),
net=target['net'],
optimizer=target['optimizer'],
epochs=target['epochs'],
ngpus_per_trial=target['ngpus_per_trial'],
num_trials=target['num_trials'],
batch_size=target['batch_size'],
verbose=True,
search_strategy='skopt',
tricks=target['tricks'],
lr_config=target['lr_config'],
plot_results=True)
# test_dataset = task.Dataset(target['dataset'].replace('images', 'test'))
# inds, probs, probals_all= classifier.predict(test_dataset)
# print(inds[0], probs[0], probals_all[0])
print('Top-1 val acc: %.3f' % classifier.results['best_reward'])
def test_tricks(test_trials):
dataset = 'shopee-iet'
data_dir = './'
download_shopee(data_dir, dataset)
for i in range(test_trials):
print('Test:{}\n'.format(i))
target = config_choice(dataset, data_dir, tricks_combination[i])
classifier = task.fit(dataset=task.Dataset(target['dataset']),
net=target['net'],
optimizer=target['optimizer'],
epochs=target['epochs'],
ngpus_per_trial=target['ngpus_per_trial'],
num_trials=target['num_trials'],
batch_size=target['batch_size'],
verbose=True,
search_strategy='random',
tricks=target['tricks'],
lr_config=target['lr_config'],
plot_results=True)
test_dataset = task.Dataset(target['dataset'].replace(
'train', 'test/BabyPants'),
train=False,
scale_ratio_choice=[0.7, 0.8, 0.875])
inds, probs, probs_all = classifier.predict(test_dataset,
set_prob_thresh=0.001)
print(inds[0], probs[0], probs_all[0])
print('Top-1 val acc: %.3f' % classifier.results['best_reward'])
def test_classifier_save_load():
dataset = task.Dataset(name='FashionMNIST')
test_dataset = task.Dataset(name='FashionMNIST', train=False)
classifier = task.fit(dataset, epochs=1, ngpus_per_trial=1, verbose=False)
classifier.save('classifier.ag')
classifier2 = task.Classifier.load('classifier.ag')
test_acc = classifier2.evaluate(test_dataset)
def test_ensemble():
dataset = task.Dataset(name='FashionMNIST')
test_dataset = task.Dataset(name='FashionMNIST', train=False)
classifier = task.fit(dataset,
epochs=10,
ngpus_per_trial=1,
verbose=False,
ensemble=2)
test_acc = classifier.evaluate(test_dataset)
def predict_details(data_path, classifier, load_dataset):
test_dataset = os.path.join(data_path, 'test')
inds, probs, probs_all = classifier.predict(task.Dataset(test_dataset))
value = []
target_dataset = load_dataset.init()
for i in inds:
value.append(target_dataset.classes[i])
return inds, probs, probs_all, value
def main():
opt = parse_args()
if not os.path.exists(opt.dataset):
os.mkdir(opt.dataset)
dataset_path = os.path.join(opt.data_dir, opt.dataset)
local_path = os.path.dirname(__file__)
output_directory = os.path.join(opt.dataset, 'checkpoint/')
filehandler = logging.FileHandler(os.path.join(opt.dataset, 'summary.log'))
streamhandler = logging.StreamHandler()
logger = logging.getLogger('')
logger.setLevel(logging.INFO)
logger.addHandler(filehandler)
logger.addHandler(streamhandler)
logging.info(opt)
target = config_choice(opt.data_dir, opt.dataset)
load_dataset = task.Dataset(target['dataset'])
classifier = task.fit(dataset=load_dataset,
output_directory=output_directory,
net=target['net'],
optimizer=target['optimizer'],
tricks=target['tricks'],
lr_config=target['lr_config'],
resume=opt.resume,
epochs=opt.num_epochs,
ngpus_per_trial=opt.ngpus_per_trial,
num_trials=opt.num_trials,
batch_size=opt.batch_size,
verbose=True,
plot_results=True)
summary = classifier.fit_summary(output_directory=opt.dataset, verbosity=4)
logging.info('Top-1 val acc: %.3f' % classifier.results['best_reward'])
logger.info(summary)
if opt.submission:
test_dataset = task.Dataset(os.path.join(opt.data_dir, opt.dataset,
'test'),
train=False)
inds, probs, probs_all, value = predict_details(
test_dataset, classifier, load_dataset)
ag.utils.generate_csv_submission(dataset_path, opt.dataset, local_path,
inds, probs_all, value, opt.custom)
def train(args):
print("args {}".format(args))
is_distributed = len(args.hosts) > 1
dist_ip_addrs = []
if is_distributed:
host_rank = args.hosts.index(args.current_host)
ag.sagemaker_setup()
if host_rank > 0:
print('Host rank {} exit.'.format(host_rank))
return
dist_ip_addrs = args.hosts
dist_ip_addrs.pop(host_rank)
dataset = task.Dataset(os.path.join(args.data_dir, 'train'))
ngpus_per_trial = 1 if args.num_gpus > 0 else 0
classifier = task.fit(dataset,
epochs=args.epochs,
num_trials=args.num_trials,
ngpus_per_trial=ngpus_per_trial,
verbose=True,
dist_ip_addrs=dist_ip_addrs,
output_directory=args.model_dir)
import autogluon as ag
from autogluon import ImageClassification as task
dataset = task.Dataset('train')
test_dataset = task.Dataset('va', train=False)
print(ag.get_gpu_count())
time_limits = 8 * 60 * 60
epochs = 150
output = 'checkpoint/'
resume = True
classifier = task.fit(dataset,
search_strategy='skopt',
search_options={
'base_estimator': 'RF',
'acq_func': 'EI'
},
time_limits=time_limits,
epochs=epochs,
ngpus_per_trial=1,
num_trials=1,
output_directory=output,
verbose=True,
resume=resume,
plot_results=True)
print('Top-1 val acc: %.3f' %
classifier.results[classifier.results['reward_attr']])
classifier.save('checkpoint/model.pth')
# Import Libraries
"""
pip install --upgrade mxnet-cu100
pip install autogluon
import autogluon as ag
from autogluon import ImageClassification as task
"""# Create AutoGluon Dataset"""
!unzip shop.zip
dataset = task.Dataset('data/train')
test_dataset = task.Dataset('data/test', train=False)
if ag.get_gpu_count() == 0:
dataset = task.Dataset(name='FashionMNIST')
test_dataset = task.Dataset(name='FashionMNIST', train=False)
"""# Use AutoGluon to Fit Models"""
classifier = task.fit(dataset,
epochs=5,
ngpus_per_trial=1,
verbose=False)
print('Top-1 val acc: %.3f' % classifier.results['best_reward'])
import math
import autogluon as ag
from autogluon import ImageClassification as task
@ag.obj(
width_coefficient=ag.space.Categorical(1.1, 1.2),
depth_coefficient=ag.space.Categorical(1.1, 1.2),
)
class EfficientNetB1(ag.nas.EfficientNet):
def __init__(self, width_coefficient, depth_coefficient):
input_factor = math.sqrt(2.0 / (width_coefficient**2) /
depth_coefficient)
input_size = math.ceil((224 * input_factor) / 32) * 32
super().__init__(width_coefficient=width_coefficient,
depth_coefficient=depth_coefficient,
input_size=input_size)
results = task.fit('imagenet',
net=EfficientNetB1(),
search_strategy='grid',
optimizer=ag.optimizer.SGD(learning_rate=1e-1,
momentum=0.9,
wd=1e-4),
batch_size=32)
print(results)
ag.done()
y_pred = np.rint(model.predict(X_test))
print(accuracy_score(y_test, y_pred))
# %%
"""
# Experiment with AutoGluon: AutoML Toolkit for Deep Learning
"""
# %%
import autogluon as ag
from autogluon import ImageClassification as task
# %%
dataset = task.Dataset('./data')
# %%
#time_limits = 10 * 60 # 10mins
#classifier = task.fit(dataset, time_limits=time_limits, ngpus_per_trial=1)
classifier = task.fit(dataset,
epochs=10,
ngpus_per_trial=1,
verbose=True)
# %%
print('Top-1 val acc: %.3f' % classifier.results['best_reward'])
# %%
