def skip_test_minddataset(add_and_remove_cv_file=True):
"""tutorial for cv minderdataset."""
columns_list = ["data", "file_name", "label"]
num_readers = 4
indices = [1, 2, 3, 5, 7]
sampler = ds.SubsetRandomSampler(indices)
data_set = ds.MindDataset(CV_FILE_NAME + "0",
columns_list,
num_readers,
sampler=sampler)
# Serializing into python dictionary
ds1_dict = ds.serialize(data_set)
# Serializing into json object
ds1_json = json.dumps(ds1_dict, sort_keys=True)
# Reconstruct dataset pipeline from its serialized form
data_set = ds.deserialize(input_dict=ds1_dict)
ds2_dict = ds.serialize(data_set)
# Serializing into json object
ds2_json = json.dumps(ds2_dict, sort_keys=True)
assert ds1_json == ds2_json
_ = get_data(CV_DIR_NAME)
assert data_set.get_dataset_size() == 5
num_iter = 0
for _ in data_set.create_dict_iterator(num_epochs=1, output_numpy=True):
num_iter += 1
assert num_iter == 5
def test_cv_minddataset_subset_random_sample_negative(add_and_remove_cv_file):
columns_list = ["data", "file_name", "label"]
num_readers = 4
indices = [1, 2, 4, -1, -2]
sampler = ds.SubsetRandomSampler(indices)
data_set = ds.MindDataset(CV_FILE_NAME + "0",
columns_list,
num_readers,
sampler=sampler)
assert data_set.get_dataset_size() == 5
num_iter = 0
for item in data_set.create_dict_iterator():
logger.info(
"-------------- cv reader basic: {} ------------------------".
format(num_iter))
logger.info(
"-------------- item[data]: {} -----------------------------".
format(item["data"]))
logger.info(
"-------------- item[file_name]: {} ------------------------".
format(item["file_name"]))
logger.info(
"-------------- item[label]: {} ----------------------------".
format(item["label"]))
num_iter += 1
assert num_iter == 5
def skip_test_chained_sampler_08():
logger.info("Test Case Chained Sampler - SubsetRandom and Distributed, 4 shards")
# Create chained sampler, subset random and distributed
indices = [0, 1, 2, 3, 4, 5, 12, 13, 14, 15, 16, 11]
sampler = ds.SubsetRandomSampler(indices, num_samples=12)
child_sampler = ds.DistributedSampler(num_shards=4, shard_id=1)
sampler.add_child(child_sampler)
# Create ImageFolderDataset with sampler
data1 = ds.ImageFolderDataset(DATA_DIR, sampler=sampler)
# Verify dataset size
data1_size = data1.get_dataset_size()
logger.info("dataset size is: {}".format(data1_size))
assert data1_size == 3
# Verify number of iterations
num_iter = 0
for item in data1.create_dict_iterator(num_epochs=1): # each data is a dictionary
# in this example, each dictionary has keys "image" and "label"
logger.info("image is {}".format(item["image"]))
logger.info("label is {}".format(item["label"]))
num_iter += 1
logger.info("Number of data in data1: {}".format(num_iter))
# Note: SubsetRandomSampler returns 12 samples
# Note: Each of 4 shards has 3 samples
assert num_iter == 3
def test_cv_minddataset_subset_random_sample_out_of_range(
add_and_remove_cv_file):
"""tutorial for cv minderdataset."""
columns_list = ["data", "file_name", "label"]
num_readers = 4
indices = [1, 2, 4, 11, 13]
sampler = ds.SubsetRandomSampler(indices)
data_set = ds.MindDataset(CV_FILE_NAME + "0",
columns_list,
num_readers,
sampler=sampler)
assert data_set.get_dataset_size() == 5
num_iter = 0
for item in data_set.create_dict_iterator(num_epochs=1, output_numpy=True):
logger.info(
"-------------- cv reader basic: {} ------------------------".
format(num_iter))
logger.info(
"-------------- item[data]: {} -----------------------------".
format(item["data"]))
logger.info(
"-------------- item[file_name]: {} ------------------------".
format(item["file_name"]))
logger.info(
"-------------- item[label]: {} ----------------------------".
format(item["label"]))
num_iter += 1
assert num_iter == 5
def test_cv_minddataset_subset_random_sample_empty(add_and_remove_cv_file):
"""tutorial for cv minderdataset."""
columns_list = ["data", "file_name", "label"]
num_readers = 4
indices = []
sampler = ds.SubsetRandomSampler(indices)
data_set = ds.MindDataset(CV_FILE_NAME + "0",
columns_list,
num_readers,
sampler=sampler)
data = get_data(CV_DIR_NAME)
assert data_set.get_dataset_size() == 10
num_iter = 0
for item in data_set.create_dict_iterator():
logger.info(
"-------------- cv reader basic: {} ------------------------".
format(num_iter))
logger.info(
"-------------- item[data]: {} -----------------------------".
format(item["data"]))
logger.info(
"-------------- item[file_name]: {} ------------------------".
format(item["file_name"]))
logger.info(
"-------------- item[label]: {} ----------------------------".
format(item["label"]))
num_iter += 1
assert num_iter == 0
def test_subset_random_sampler():
logger.info("Test Case SubsetRandomSampler")
# define parameters
repeat_count = 1
# apply dataset operations
indices = [0, 1, 2, 3, 4, 5, 12, 13, 14, 15, 16, 11]
sampler = ds.SubsetRandomSampler(indices)
data1 = ds.ImageFolderDatasetV2(DATA_DIR, sampler=sampler)
data1 = data1.repeat(repeat_count)
num_iter = 0
for item in data1.create_dict_iterator(): # each data is a dictionary
# in this example, each dictionary has keys "image" and "label"
logger.info("image is {}".format(item["image"]))
logger.info("label is {}".format(item["label"]))
num_iter += 1
logger.info("Number of data in data1: {}".format(num_iter))
assert num_iter == 12
