# Copyright 2019 Huawei Technologies Co., Ltd
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""
Cifar100 convert tool for MindRecord.
"""
from importlib import import_module
import os
import numpy as np
from mindspore import log as logger
from .cifar100 import Cifar100
from ..common.exceptions import PathNotExistsError
from ..filewriter import FileWriter
from ..shardutils import check_filename
try:
cv2 = import_module("cv2")
except ModuleNotFoundError:
cv2 = None
__all__ = ['Cifar100ToMR']
[docs]class Cifar100ToMR:
"""
Class is for transformation from cifar100 to MindRecord.
Args:
source (str): the cifar100 directory to be transformed.
destination (str): the MindRecord file path to transform into.
Raises:
ValueError: If source or destination is invalid.
"""
def __init__(self, source, destination):
check_filename(source)
self.source = source
files = os.listdir(self.source)
train_data_flag = False
test_data_flag = False
for file in files:
if file == "train":
train_data_flag = True
if file == "test":
test_data_flag = True
if not train_data_flag:
raise PathNotExistsError("train")
if not test_data_flag:
raise PathNotExistsError("test")
check_filename(destination)
self.destination = destination
self.writer = None
def _construct_raw_data(images, fine_labels, coarse_labels):
"""
Construct raw data from cifar100 data.
Args:
images (list): image list from cifar100.
fine_labels (list): fine label list from cifar100.
coarse_labels (list): coarse label list from cifar100.
Returns:
SUCCESS/FAILED, whether successfully written into MindRecord.
"""
if not cv2:
raise ModuleNotFoundError("opencv-python module not found, please use pip install it.")
raw_data = []
for i, img in enumerate(images):
fine_label = np.int(fine_labels[i][0])
coarse_label = np.int(coarse_labels[i][0])
_, img = cv2.imencode(".jpeg", img[..., [2, 1, 0]])
row_data = {"id": int(i),
"data": img.tobytes(),
"fine_label": int(fine_label),
"coarse_label": int(coarse_label)}
raw_data.append(row_data)
return raw_data
def _generate_mindrecord(file_name, raw_data, fields, schema_desc):
"""
Generate MindRecord file from raw data.
Args:
file_name (str): File name of MindRecord File.
fields (list[str]): Fields would be set as index which
could not belong to blob fields and type could not be 'array' or 'bytes'.
raw_data (dict): Dict of raw data.
schema_desc (str): String of schema description.
Returns:
SUCCESS/FAILED, whether successfully written into MindRecord.
"""
schema = {"id": {"type": "int64"}, "fine_label": {"type": "int64"},
"coarse_label": {"type": "int64"}, "data": {"type": "bytes"}}
logger.info("transformed MindRecord schema is: {}".format(schema))
writer = FileWriter(file_name, 1)
writer.add_schema(schema, schema_desc)
if fields and isinstance(fields, list):
writer.add_index(fields)
writer.write_raw_data(raw_data)
return writer.commit()