vandanavk commented on a change in pull request #13325: [MXNET-1210 ] Gluon Audio - Example URL: https://github.com/apache/incubator-mxnet/pull/13325#discussion_r236766272
########## File path: example/gluon/urban_sounds/datasets.py ########## @@ -0,0 +1,173 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you 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. + +# coding: utf-8 +# pylint: disable= +""" Audio Dataset container.""" +__all__ = ['AudioFolderDataset'] + +import os +import warnings +from mxnet.gluon.data import Dataset +from mxnet import ndarray as nd +try: + import librosa +except ImportError as e: + warnings.warn("librosa dependency could not be resolved or \ + imported, could not load audio onto the numpy array. pip install librosa") + + +class AudioFolderDataset(Dataset): + """A dataset for loading Audio files stored in a folder structure like:: + + root/children_playing/0.wav + root/siren/23.wav + root/drilling/26.wav + root/dog_barking/42.wav + OR + Files(wav) and a csv file that has file name and associated label + + Parameters + ---------- + root : str + Path to root directory. + transform : callable, default None + A function that takes data and label and transforms them + train_csv: str, default None + train_csv should be populated by the training csv filename + file_format: str, default '.wav' + The format of the audio files(.wav) + skip_header: boolean, default False + While reading from csv file, whether to skip at the start of the file to avoid reading in header + + + Attributes + ---------- + synsets : list + List of class names. `synsets[i]` is the name for the integer label `i` + items : list of tuples + List of all audio in (filename, label) pairs. + + """ + def __init__(self, root, train_csv=None, file_format='.wav', skip_header=False): + if not librosa: + warnings.warn("pip install librosa to continue.") + return + self._root = os.path.expanduser(root) + self._exts = ['.wav'] + self._format = file_format + self._train_csv = train_csv + if file_format.lower() not in self._exts: + raise RuntimeError("format {} not supported currently.".format(file_format)) + if skip_header: + skip_rows = 1 + else: + skip_rows = 0 + self._list_audio_files(self._root, skip_rows=skip_rows) + + + def _list_audio_files(self, root, skip_rows=0): + """Populates synsets - a map of index to label for the data items. + Populates the data in the dataset, making tuples of (data, label) + """ + self.synsets = [] + self.items = [] + if self._train_csv is None: + for folder in sorted(os.listdir(root)): + path = os.path.join(root, folder) + if not os.path.isdir(path): + warnings.warn('Ignoring {}, which is not a directory.'.format(path)) + continue + label = len(self.synsets) + self.synsets.append(folder) + for filename in sorted(os.listdir(path)): + file_name = os.path.join(path, filename) + ext = os.path.splitext(file_name)[1] + if ext.lower() not in self._exts: + warnings.warn('Ignoring {} of type {}. Only support {}'\ + .format(filename, ext, ', '.join(self._exts))) + continue + self.items.append((file_name, label)) + else: + skipped_rows = 0 + with open(self._train_csv, "r") as traincsv: + for line in traincsv: + skipped_rows = skipped_rows + 1 + if skipped_rows <= skip_rows: + continue Review comment: for skipping multiple rows in csv, could you explore https://python-forum.io/Thread-How-to-Loop-CSV-File-Beginning-at-Specific-Row?pid=29676#pid29676 or https://stackoverflow.com/questions/40403971/skip-multiple-rows-in-python ? ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
