def quickstart(client, train_dataset_path, val_dataset_path, gpus, hours,
query_paths):
'''
Conducts a full train-inference flow on the Fashion MNIST dataset with
models `SkDt` and `TfFeedForward` for the task `IMAGE_CLASSIFICATION`.
'''
task = 'IMAGE_CLASSIFICATION'
# Randomly generate app & model names to avoid naming conflicts
app_id = gen_id()
app = 'image_classification_app_{}'.format(app_id)
tf_model_name = 'TfFeedForward_{}'.format(app_id)
sk_model_name = 'SkDt_{}'.format(app_id)
print('Preprocessing datasets...')
load_fashion_mnist(train_dataset_path, val_dataset_path)
print('Creating & uploading datasets onto SINGA-Auto...')
train_dataset = client.create_dataset('{}_train'.format(app), task,
train_dataset_path)
pprint(train_dataset)
val_dataset = client.create_dataset('{}_val'.format(app), task,
val_dataset_path)
pprint(val_dataset)
print('Adding models "{}" and "{}" to SINGA-Auto...'.format(
tf_model_name, sk_model_name))
tf_model = client.create_model(
tf_model_name,
task,
'examples/models/image_classification/TfFeedForward.py',
'TfFeedForward',
dependencies={ModelDependency.TENSORFLOW: '1.12.0'})
pprint(tf_model)
sk_model = client.create_model(
sk_model_name,
task,
'examples/models/image_classification/SkDt.py',
'SkDt',
dependencies={ModelDependency.SCIKIT_LEARN: '0.20.0'})
pprint(sk_model)
model_ids = [tf_model['id'], sk_model['id']]
print('Creating train job for app "{}" on SINGA-Auto...'.format(app))
budget = {BudgetOption.TIME_HOURS: hours, BudgetOption.GPU_COUNT: gpus}
train_job = client.create_train_job(app,
task,
train_dataset['id'],
val_dataset['id'],
budget,
models=model_ids)
pprint(train_job)
print('Waiting for train job to complete...')
print('This might take a few minutes')
wait_until_train_job_has_stopped(client, app)
print('Train job has been stopped')
print('Listing best trials of latest train job for app "{}"...'.format(app))
pprint(client.get_best_trials_of_train_job(app))
print('Creating inference job for app "{}" on SINGA-Auto...'.format(app))
pprint(client.create_inference_job(app))
predictor_host = get_predictor_host(client, app)
if not predictor_host:
raise Exception('Inference job has errored')
print('Inference job is running!')
print('Making predictions for query images:')
print(query_paths)
queries = utils.dataset.load_images(query_paths).tolist()
predictions = make_predictions(client, predictor_host, queries)
print('Predictions are:')
print(predictions)
print('Stopping inference job...')
pprint(client.stop_inference_job(app))
def image_dataset_download_load_and_split(dataset_name, data_dir='data', min_image_size=None, max_image_size=None, mode=None, image_scale_size=None, dataset_types=['train','test']):
'''
:return: x_train, y_train, x_test, y_test.
x_train, x_test are lists of images in torch tensor format.
y_train, y_test are lists of labels, corresponding to the x_ sets.
:param dataset_name: list of str.
:param if_download: True/False. True means to download datasets to the nominated data_dir. False stands for loading the existing datasets.
:param data_dir: directory that datasets 'download to' or 'load from'.
'''
# if the dataset is not prepared in the directory yet
assert min_image_size<=max_image_size
if dataset_name == 'cifar10':
if os.path.exists(data_dir+'cifar10_train.zip') is False or os.path.exists(data_dir+'cifar10_test.zip') is False :
print ('Dataset Downloading ... ')
from examples.datasets.image_files.load_cifar10 import load_cifar10
# This will generate train, test, val datasets to 'data/' directory. When validation_split set to 0, means the val dataset is empty.
load_cifar10(limit=None, validation_split=0,
out_train_dataset_path=data_dir+'cifar10_train.zip',
out_val_dataset_path=data_dir+'cifar10_val.zip',
out_test_dataset_path=data_dir+'cifar10_test.zip',
out_meta_csv_path=data_dir+'cifar10_meta.csv')
elif dataset_name == 'fashion_mnist':
if os.path.exists(data_dir+'fashion_mnist_train.zip') is False or os.path.exists(data_dir+'fashion_mnist_test.zip') is False :
print ('Dataset Downloading ... ')
from examples.datasets.image_files.load_fashion_mnist import load_fashion_mnist
# This will generate train, test, val datasets to 'data/' directory. When validation_split set to 0, means the val dataset is empty.
load_fashion_mnist(limit=None, validation_split=0,
out_train_dataset_path=data_dir+'fashion_mnist_train.zip',
out_val_dataset_path=data_dir+'fashion_mnist_val.zip',
out_meta_csv_path=data_dir+'fashion_mnist_meta.csv',
out_test_dataset_path=data_dir+'fashion_mnist_test.zip')
elif dataset_name == 'xray' or dataset_name == 'chest-xray-pneumonia':
if os.path.exists(data_dir+'chest-xray-pneumonia.zip') is False:
print ('Dataset Downloading ... ')
import kaggle
kaggle.api.authenticate()
kaggle.api.dataset_download_files('paultimothymooney/chest-xray-pneumonia', path=data_dir, unzip=False)
# reading downloaded dataset zipfiles
if dataset_name == 'xray' or dataset_name == 'chest-xray-pneumonia':
datasets_loaded = processing_and_reading_downloaded_xray('chest-xray-pneumonia',
data_dir,
min_image_size=min_image_size,
max_image_size=max_image_size,
mode=mode,
image_scale_size=image_scale_size)
else:
datasets_loaded = dict()
for dataset_type in dataset_types:
(x, y) = processing_and_reading_existing_datasets(dataset_name,
data_dir=data_dir,
min_image_size=min_image_size,
max_image_size=max_image_size,
mode=mode,
image_scale_size=image_scale_size,
dataset_type=dataset_type)
datasets_loaded.update({f'x_{dataset_type}': x, f'y_{dataset_type}': y})
return datasets_loaded