def _prepare(self):
self.root = edu.get_root(self.NAME)
self._data_path = Path(self.root).joinpath("data.p")
if not edu.is_prepared(self.root):
# prep
self.logger.info("Preparing dataset {} in {}".format(
self.NAME, self.root))
root = Path(self.root)
urls = dict((v, urllib.parse.urljoin(self.URL, v))
for k, v in self.FILES.items())
local_files = edu.download_urls(urls, target_dir=root)
data = dict()
for k, v in local_files.items():
data[k] = read_mnist_file(v)
with open(self._data_path, "wb") as f:
pickle.dump(data, f)
edu.mark_prepared(self.root)
def _prepare(self):
self.root = edu.get_root(self.NAME)
self._data_path = Path(self.root).joinpath("data.p")
if not edu.is_prepared(self.root):
# prep
self.logger.info("Preparing dataset {} in {}".format(
self.NAME, self.root))
root = Path(self.root)
urls = dict((v, urllib.parse.urljoin(self.URL, v))
for k, v in self.FILES.items())
local_files = edu.download_urls(urls, target_dir=root)
edu.unpack(local_files["cifar-10-python.tar.gz"])
base = os.path.join(self.root, "cifar-10-batches-py")
labels = list()
filenames = list()
datas = list()
for batch_file in ["data_batch_{}".format(i) for i in range(1, 6)]:
with open(os.path.join(base, batch_file), "rb") as f:
batch_data = pickle.load(f, encoding="bytes")
labels += batch_data["labels".encode()]
filenames += [
fname.decode()
for fname in batch_data["filenames".encode()]
]
datas.append(batch_data["data".encode()])
with open(os.path.join(base, "test_batch"), "rb") as f:
test_data = pickle.load(f, encoding="bytes")
test_labels = test_data["labels".encode()]
test_filenames = [
fname.decode() for fname in test_data["filenames".encode()]
]
test_datas = test_data["data".encode()]
with open(os.path.join(base, "batches.meta"), "rb") as f:
_meta = pickle.load(f, encoding="bytes")
meta = {
"label_names":
[name.decode() for name in _meta["label_names".encode()]],
"num_vis":
_meta["num_vis".encode()],
"num_cases_per_batch":
_meta["num_cases_per_batch".encode()],
}
# convert to (32,32,3) RGB uint8
images = np.concatenate(datas, axis=0)
images = np.reshape(images, [-1, 3, 32, 32])
images = np.transpose(images, [0, 2, 3, 1])
test_images = test_datas
test_images = np.reshape(test_images, [-1, 3, 32, 32])
test_images = np.transpose(test_images, [0, 2, 3, 1])
filenames = np.array(filenames)
test_filenames = np.array(test_filenames)
labels = np.array(labels)
test_labels = np.array(test_labels)
data = {
"train":
dict(images=images, filenames=filenames, labels=labels),
"test":
dict(images=test_images,
filenames=test_filenames,
labels=test_labels),
"meta":
meta,
}
with open(self._data_path, "wb") as f:
pickle.dump(data, f)
edu.mark_prepared(self.root)
