def test_load_openvino(self):
local_path = self.create_temp_dir()
model = InferenceModel(1)
model_url = data_url + "/analytics-zoo-models/openvino/2018_R5/resnet_v1_50.xml"
weight_url = data_url + "/analytics-zoo-models/openvino/2018_R5/resnet_v1_50.bin"
model_path = maybe_download("resnet_v1_50.xml",
local_path, model_url)
weight_path = maybe_download("resnet_v1_50.bin",
local_path, weight_url)
model.load_openvino(model_path, weight_path)
input_data = np.random.random([4, 1, 224, 224, 3])
model.predict(input_data)
def read_data_sets(train_dir, data_type="train"):
"""
Parse or download mnist data if train_dir is empty.
:param: train_dir: The directory storing the mnist data
:param: data_type: Reading training set or testing set.It can be either "train" or "test"
:return:
```
(ndarray, ndarray) representing (features, labels)
features is a 4D unit8 numpy array [index, y, x, depth]
representing each pixel valued from 0 to 255.
labels is 1D unit8 nunpy array representing the label valued from 0 to 9.
```
"""
TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
if data_type == "train":
local_file = base.maybe_download(TRAIN_IMAGES, train_dir,
SOURCE_URL + TRAIN_IMAGES)
with open(local_file, 'rb') as f:
train_images = extract_images(f)
local_file = base.maybe_download(TRAIN_LABELS, train_dir,
SOURCE_URL + TRAIN_LABELS)
with open(local_file, 'rb') as f:
train_labels = extract_labels(f)
return train_images, train_labels
else:
local_file = base.maybe_download(TEST_IMAGES, train_dir,
SOURCE_URL + TEST_IMAGES)
with open(local_file, 'rb') as f:
test_images = extract_images(f)
local_file = base.maybe_download(TEST_LABELS, train_dir,
SOURCE_URL + TEST_LABELS)
with open(local_file, 'rb') as f:
test_labels = extract_labels(f)
return test_images, test_labels
def download_news20(dest_dir):
file_name = "20news-18828.tar.gz"
file_abs_path = base.maybe_download(file_name, dest_dir, NEWS20_URL)
tar = tarfile.open(file_abs_path, "r:gz")
extracted_to = os.path.join(dest_dir, "20news-18828")
if not os.path.exists(extracted_to):
print("Extracting %s to %s" % (file_abs_path, extracted_to))
tar.extractall(dest_dir)
tar.close()
return extracted_to
def load_roberta(self):
os.makedirs(local_path, exist_ok=True)
model_url = data_url + "/analytics-zoo-data/roberta/roberta.tar"
model_path = maybe_download("roberta.tar",
local_path, model_url)
tar = tarfile.open(model_path)
tar.extractall(path=local_path)
tar.close()
model_path = os.path.join(local_path, "roberta/model.xml")
self.est = Estimator.from_openvino(model_path=model_path)
def download_glove_w2v(dest_dir):
file_name = "glove.6B.zip"
file_abs_path = base.maybe_download(file_name, dest_dir, GLOVE_URL)
import zipfile
zip_ref = zipfile.ZipFile(file_abs_path, 'r')
extracted_to = os.path.join(dest_dir, "glove.6B")
if not os.path.exists(extracted_to):
print("Extracting %s to %s" % (file_abs_path, extracted_to))
zip_ref.extractall(extracted_to)
zip_ref.close()
return extracted_to
def download_reuters(dest_dir):
"""Download pre-processed reuters newswire data
:argument
dest_dir: destination directory to store the data
:return
The absolute path of the stored data
"""
file_name = 'reuters.pkl'
file_abs_path = base.maybe_download(
file_name, dest_dir,
'https://s3.amazonaws.com/text-datasets/reuters.pkl')
return file_abs_path
def download_imdb(dest_dir):
"""Download pre-processed IMDB movie review data
:argument
dest_dir: destination directory to store the data
:return
The absolute path of the stored data
"""
file_name = "imdb_full.pkl"
file_abs_path = base.maybe_download(
file_name, dest_dir,
'https://s3.amazonaws.com/text-datasets/imdb_full.pkl')
return file_abs_path
def load_resnet(self):
input_file_path = os.path.join(resource_path, "orca/learn/resnet_input")
output_file_path = os.path.join(resource_path, "orca/learn/resnet_output")
self.input = read_file_and_cast(input_file_path)
self.output = read_file_and_cast(output_file_path)
self.input = np.array(self.input).reshape([3, 224, 224])
self.output = np.array(self.output).reshape([4, 1000])[:1]
os.makedirs(local_path, exist_ok=True)
model_url = data_url + "/analytics-zoo-data/openvino2020_resnet50.tar"
model_path = maybe_download("openvino2020_resnet50.tar",
local_path, model_url)
tar = tarfile.open(model_path)
tar.extractall(path=local_path)
tar.close()
model_path = os.path.join(local_path, "openvino2020_resnet50/resnet_v1_50.xml")
self.est = Estimator.from_openvino(model_path=model_path)
def get_word_index(dest_dir='/tmp/.zoo/dataset',
filename='reuters_word_index.pkl'):
"""Retrieves the dictionary mapping word indices back to words.
# Arguments
dest_dir: where to cache the data (relative to `~/.zoo/dataset`).
filename: dataset file name
# Returns
The word index dictionary.
"""
path = base.maybe_download(
filename, dest_dir,
'https://s3.amazonaws.com/text-datasets/reuters_word_index.pkl')
f = open(path, 'rb')
data = cPickle.load(f, encoding='latin1')
f.close()
return data
def read_data_sets(data_dir):
"""
Parse or download movielens 1m data if train_dir is empty.
:param data_dir: The directory storing the movielens data
:return: a 2D numpy array with user index and item index in each row
"""
WHOLE_DATA = 'ml-1m.zip'
local_file = base.maybe_download(WHOLE_DATA, data_dir,
SOURCE_URL + WHOLE_DATA)
zip_ref = zipfile.ZipFile(local_file, 'r')
extracted_to = os.path.join(data_dir, "ml-1m")
if not os.path.exists(extracted_to):
print("Extracting %s to %s" % (local_file, data_dir))
zip_ref.extractall(data_dir)
zip_ref.close()
rating_files = os.path.join(extracted_to, "ratings.dat")
rating_list = [
i.strip().split("::") for i in open(rating_files, "r").readlines()
]
movielens_data = np.array(rating_list).astype(int)
return movielens_data
def download_data(dest_dir):
TINYSHAKESPEARE_URL = 'https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt' # noqa
file_name = "input.txt"
file_abs_path = base.maybe_download(file_name, dest_dir, TINYSHAKESPEARE_URL)
return file_abs_path
