def __init__(self, data_dir, class_file, n_support, n_query, cuda, args):
self.sample_rate = args['sample_rate']
self.clip_duration_ms = args['clip_duration']
self.window_size_ms = args['window_size']
self.window_stride_ms = args['window_stride']
self.feature_bin_count = args['num_features']
self.foreground_volume = args['foreground_volume']
self.time_shift_ms = args['time_shift']
self.use_background = args['include_background']
self.background_volume = args['bg_volume']
self.background_frequency = args['bg_frequency']
self.desired_samples = int(self.sample_rate * self.clip_duration_ms /
1000)
self.silence = args['include_silence']
self.silence_num_samples = args['num_silence']
self.unknown = args['include_unknown']
self.data_cache = {}
self.data_dir = data_dir
self.class_file = class_file
self.n_support = n_support
self.n_query = n_query
self.background_data = self.load_background_data()
self.mfcc = self.build_mfcc_extractor()
self.transforms = [
partial(convert_dict, 'class'), self.load_class_samples,
self.extract_episode
]
if cuda:
self.transforms.append(CudaTransform())
self.class_names = self.read()
transforms = compose(self.transforms)
super().__init__(ListDataset(self.class_names), transforms)
def load(opt, splits):
split_dir = os.path.join(MINI_IMGNET_DATA_DIR, 'splits', opt['data.split'])
ret = {}
for split in splits:
if split in ['val', 'test'] and opt['data.test_way'] != 0:
n_way = opt['data.test_way']
else:
n_way = opt['data.way']
if split in ['val', 'test'] and opt['data.test_shot'] != 0:
n_support = opt['data.test_shot']
else:
n_support = opt['data.shot']
if split in ['val', 'test'] and opt['data.test_query'] != 0:
n_query = opt['data.test_query']
else:
n_query = opt['data.query']
if split in ['val', 'test']:
n_episodes = opt['data.test_episodes']
else:
n_episodes = opt['data.train_episodes']
cache_path = get_cache_path(split)
if os.path.exists(cache_path):
with open(cache_path, "rb") as f:
try:
data = pkl.load(f, encoding='bytes')
img_data = data[b'image_data']
class_dict = data[b'class_dict']
except:
data = pkl.load(f)
img_data = data['image_data']
class_dict = data['class_dict']
transforms = [
partial(convert_dict, 'class'),
partial(load_class_images, img_data, class_dict),
partial(extract_episode, n_support, n_query)
]
if opt['data.cuda']:
transforms.append(CudaTransform())
class_names = [key for key in class_dict]
transforms = compose(transforms)
ds = TransformDataset(ListDataset(class_names), transforms)
if opt['data.sequential']:
sampler = SequentialBatchSampler(len(ds))
else:
sampler = EpisodicBatchSampler(len(ds), n_way, n_episodes)
# use num_workers=0, otherwise may receive duplicate episodes
ret[split] = torch.utils.data.DataLoader(ds,
batch_sampler=sampler,
num_workers=0)
return ret
def load(opt, splits):
split_dir = os.path.join(MINIIMAGENET_DATA_DIR, 'splits',
opt['data.split'])
ret = {}
for split in splits:
if split in ['val', 'test'] and opt['data.test_way'] != 0:
n_way = opt['data.test_way']
else:
n_way = opt['data.way']
if split in ['val', 'test'] and opt['data.test_shot'] != 0:
n_support = opt['data.test_shot']
else:
n_support = opt['data.shot']
if split in ['val', 'test'] and opt['data.test_query'] != 0:
n_query = opt['data.test_query']
else:
n_query = opt['data.query']
if split in ['val', 'test']:
n_episodes = opt['data.test_episodes']
else:
n_episodes = opt['data.train_episodes']
class_index = defaultdict(list)
with open(os.path.join(split_dir, "{:s}.csv".format(split)), 'r') as f:
f.readline()
for image_class in f.readlines():
image, class_name = image_class.split(',')
class_name = class_name.rstrip('\n')
class_index[class_name].append(image)
class_names = list(class_index.keys())
transforms = [
partial(convert_dict, 'class'),
partial(load_class_images, class_index),
partial(extract_episode, n_support, n_query)
]
if opt['data.cuda']:
transforms.append(CudaTransform())
transforms = compose(transforms)
ds = TransformDataset(ListDataset(class_names), transforms)
if opt['data.sequential']:
sampler = SequentialBatchSampler(len(ds))
else:
sampler = EpisodicBatchSampler(len(ds), n_way, n_episodes)
# use num_workers=0, otherwise may receive duplicate episodes
ret[split] = torch.utils.data.DataLoader(ds,
batch_sampler=sampler,
num_workers=0)
return ret
def load(opt, splits):
split_dir = os.path.join(OMNIGLOT_DATA_DIR, 'splits', opt['data.split'])
ret = { }
for split in splits:
# 获取n_way
if split in ['val', 'test'] and opt['data.test_way'] != 0:
n_way = opt['data.test_way']
else:
n_way = opt['data.way']
# 获取support的数量
if split in ['val', 'test'] and opt['data.test_shot'] != 0:
n_support = opt['data.test_shot']
else:
n_support = opt['data.shot']
# 获取query的数量
if split in ['val', 'test'] and opt['data.test_query'] != 0:
n_query = opt['data.test_query']
else:
n_query = opt['data.query']
# 获取episode
if split in ['val', 'test']:
n_episodes = opt['data.test_episodes']
else:
n_episodes = opt['data.train_episodes']
# 定义了三个函数：class字典，加载类的一张图片，取一个episode的数据
transforms = [partial(convert_dict, 'class'), # 取key是class的字典内容
load_class_images, # 取一个类中的一条数据
partial(extract_episode, n_support, n_query)] # 获取每个类的support和query
if opt['data.cuda']:
transforms.append(CudaTransform())
transforms = compose(transforms)
class_names = []
# 按照分割数据集的方式，获取相应的所有类名
with open(os.path.join(split_dir, "{:s}.txt".format(split)), 'r') as f:
for class_name in f.readlines():
class_names.append(class_name.rstrip('\n'))
# 对所有类划分support和query数据集
ds = TransformDataset(ListDataset(class_names), transforms)
if opt['data.sequential']:
sampler = SequentialBatchSampler(len(ds))
# 每个episode随机取n_way个类别
else:
sampler = EpisodicBatchSampler(len(ds), n_way, n_episodes)
# 封装数据，数据划分为多个episode
# use num_workers=0, otherwise may receive duplicate episodes
ret[split] = torch.utils.data.DataLoader(ds, batch_sampler=sampler, num_workers=0)
return ret
def load(opt, splits):
split_dir = os.path.join(OMNIGLOT_DATA_DIR, 'splits', opt['data.split'])
ret = {}
for split in splits:
if split in ['val', 'test'] and opt['data.test_way'] != 0:
n_way = opt['data.test_way']
else:
n_way = opt['data.way']
if split in ['val', 'test'] and opt['data.test_shot'] != 0:
n_support = opt['data.test_shot']
else:
n_support = opt['data.shot']
if split in ['val', 'test'] and opt['data.test_query'] != 0:
n_query = opt['data.test_query']
else:
n_query = opt['data.query']
if split in ['val', 'test']:
n_episodes = opt['data.test_episodes']
else:
n_episodes = opt['data.train_episodes']
transforms = [
partial(convert_dict, 'class'), load_class_images,
partial(extract_episode, n_support, n_query)
]
if opt['data.cuda']:
transforms.append(CudaTransform())
transforms = compose(transforms)
class_names = []
with open(os.path.join(split_dir, "{:s}.txt".format(split)), 'r') as f:
for class_name in f.readlines():
class_names.append(class_name.rstrip('\n'))
ds = TransformDataset(ListDataset(class_names), transforms)
if opt['data.sequential']:
sampler = SequentialBatchSampler(len(ds))
else:
sampler = EpisodicBatchSampler(len(ds), n_way, n_episodes)
# use num_workers=0, otherwise may receive duplicate episodes
ret[split] = torch.utils.data.DataLoader(ds,
batch_sampler=sampler,
num_workers=0)
print("Ret:", type(ret))
for key, value in ret.items():
print(key, type(value))
return ret
def load(opt, splits):
ret = {}
for split in splits:
if split in ['val', 'test'] and opt['data.test_way'] != 0:
n_way = opt['data.test_way']
else:
n_way = opt['data.way']
if split in ['val', 'test'] and opt['data.test_shot'] != 0:
n_support = opt['data.test_shot']
else:
n_support = opt['data.shot']
if split in ['val', 'test'] and opt['data.test_query'] != 0:
n_query = opt['data.test_query']
else:
n_query = opt['data.query']
if split in ['val', 'test']:
n_episodes = opt['data.test_episodes']
else:
n_episodes = opt['data.train_episodes']
speaker_ids = dataset[split]['class']
data_split = dataset[split]['data']
transforms = [
partial(convert_dict, 'class'),
partial(extract_episode, 'class', data_split, opt['data.min_len'],
opt['data.max_len'], n_support, n_query),
partial(convert_tensor,
['xq_padded', 'xs_padded', 'xq_len', 'xs_len'])
]
if opt['data.cuda']:
transforms.append(CudaTransform())
transforms = compose(transforms)
ds = TransformDataset(ListDataset(speaker_ids), transforms)
#sampler = SequencialEpisodicBatchSampler(len(ds), n_way)
if opt['data.sequential']:
sampler = SequentialBatchSampler(len(ds))
else:
sampler = EpisodicBatchSampler(len(ds), n_way, n_episodes)
ret[split] = torch.utils.data.DataLoader(ds,
batch_sampler=sampler,
num_workers=0)
return ret
def __iter__(self):
if self.dataset is None:
self.dataset = self.load_dataset(from_disk=True)[self.split]
transforms = [partial(batch_from_index, self.dataset['data']), partial(convert_tensor, 'data')]
if self.if_cuda:
transforms.append(CudaTransform())
self.transforms = compose(transforms)
index_batches = self.shuffle_dataset()
batches = TransformDataset(ListDataset(index_batches), self.transforms)
print(f"\nSize of batches: {len(batches)}")
for batch in batches:
batch['n_way'] = self.n_way
batch['n_support'] = self.n_support
batch['n_query'] = self.n_query
yield batch
def load_kws(opt, splits):
#split_dir = os.path.join(KWS_DATA_DIR, 'splits', opt['data.split'])
dataset_self = {}
if splits[0] == 'test':
files = sorted(os.listdir(KWS_DATA_DIR_TEST))
class_names = []
for file in files:
class_name = file.split('_')[0]
if not class_names.__contains__(class_name):
class_names.append(class_name)
dataset_self['test'] = class_names
data_dir = KWS_DATA_DIR_TEST
else:
data_dir = KWS_DATA_DIR
files = sorted(os.listdir(KWS_DATA_DIR))
val_class_names = [
'label01', 'label13', 'label03', 'label13', 'label03', 'label13',
'label03', 'label03'
]
class_names = []
for file in files:
class_name = file.split('_')[0]
if not class_names.__contains__(
class_name) and not val_class_names.__contains__(
class_name):
class_names.append(class_name)
train_data = {}
for name in class_names:
name_files = []
for file in files:
if file.__contains__(name):
name_files.append(file)
train_data[name] = name_files
val_data = {}
for name in val_class_names:
name_files = []
for file in files:
if file.__contains__(name):
name_files.append(file)
val_data[name] = name_files
dataset_self['train'] = class_names
dataset_self['val'] = val_class_names
ret = {}
for split in splits:
if split in ['val', 'test'] and opt['data.test_way'] != 0:
n_way = opt['data.test_way']
else:
n_way = opt['data.way']
if split in ['val', 'test'] and opt['data.test_shot'] != 0:
n_support = opt['data.test_shot']
else:
n_support = opt['data.shot']
if split in ['val', 'test'] and opt['data.test_query'] != 0:
n_query = opt['data.test_query']
else:
n_query = opt['data.query']
if split in ['val', 'test']:
n_episodes = opt['data.test_episodes']
else:
n_episodes = opt['data.train_episodes']
transforms = [
partial(convert_dict, 'class'),
partial(load_class_features, data_dir),
partial(extract_episode, n_support, n_query)
]
if opt['data.cuda']:
transforms.append(CudaTransform())
transforms = compose(transforms)
ds = TransformDataset(ListDataset(dataset_self[split]), transforms)
if opt['data.sequential']:
sampler = SequentialBatchSampler(len(ds))
else:
sampler = EpisodicBatchSampler(len(ds), n_way, n_episodes)
# use num_workers=0, otherwise may receive duplicate episodes
ret[split] = torch.utils.data.DataLoader(ds,
batch_sampler=sampler,
num_workers=0)
return ret
def load(opt, splits):
split_dir = os.path.join(MINIIMAGENET_DATA_DIR, 'splits',
opt['data.split'])
ret = {}
for split in splits:
if split in ['val', 'test'] and opt['data.test_way'] != 0:
n_way = opt['data.test_way']
else:
n_way = opt['data.way']
if split in ['val', 'test'] and opt['data.test_shot'] != 0:
n_support = opt['data.test_shot']
else:
n_support = opt['data.shot']
if split in ['val', 'test'] and opt['data.test_query'] != 0:
n_query = opt['data.test_query']
else:
n_query = opt['data.query']
if split in ['val', 'test']:
n_episodes = opt['data.test_episodes']
else:
n_episodes = opt['data.train_episodes']
transforms = [
partial(convert_dict, 'class'), load_class_images,
partial(extract_episode, n_support, n_query)
]
if opt['data.cuda']:
transforms.append(CudaTransform())
transforms = compose(transforms)
class_names = []
with open(os.path.join(split_dir, "{:s}.csv".format(split)), 'r') as f:
for class_name in f.readlines():
name = class_name.split(',')[1].rstrip('\n')
if name == 'label':
continue
if opt['data.augmented']:
class_names.extend([
name + '/rot000', name + '/rot090', name + '/rot180',
name + '/rot270'
])
else:
class_names.append(name)
ds = TransformDataset(ListDataset(class_names), transforms)
if opt['data.sequential']:
sampler = SequentialBatchSampler(len(ds))
else:
sampler = EpisodicBatchSampler(len(ds), n_way, n_episodes)
# use num_workers=0, otherwise may receive duplicate episodes
ret[split] = torch.utils.data.DataLoader(ds,
batch_sampler=sampler,
num_workers=0)
return ret