Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 7 additions & 8 deletions datumaro/plugins/imagenet_format.py
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,8 @@


class ImagenetPath:
IMAGES_EXT = '.jpg'
DEFAULT_IMAGE_EXT = '.jpg'
IMAGE_EXT_FORMAT = ['.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif']
IMAGES_DIR_NO_LABEL = 'no_label'


Expand All @@ -37,7 +38,7 @@ def _load_categories(self, path):
def _load_items(self, path):
items = {}
for image_path in glob(osp.join(path, '*', '*')):
if osp.splitext(image_path)[1] != ImagenetPath.IMAGES_EXT:
if osp.splitext(image_path)[1] not in ImagenetPath.IMAGE_EXT_FORMAT:
continue
label = osp.basename(osp.dirname(image_path))
image_name = osp.splitext(osp.basename(image_path))[0][len(label) + 1:]
Expand All @@ -62,7 +63,7 @@ def find_sources(cls, path):


class ImagenetConverter(Converter):
DEFAULT_IMAGE_EXT = ImagenetPath.IMAGES_EXT
DEFAULT_IMAGE_EXT = ImagenetPath.DEFAULT_IMAGE_EXT

def apply(self):
if 1 < len(self._extractor.subsets()):
Expand All @@ -79,12 +80,10 @@ def apply(self):
for label in labels[image_name]:
label_name = extractor.categories()[AnnotationType.label][label].name
self._save_image(item, osp.join(subset_dir, label_name,
'%s_%s%s' % \
(label_name, image_name, ImagenetPath.IMAGES_EXT)
))
'%s_%s' % (label_name, self._make_image_filename(item))))

if not labels[image_name]:
self._save_image(item, osp.join(subset_dir,
ImagenetPath.IMAGES_DIR_NO_LABEL,
ImagenetPath.IMAGES_DIR_NO_LABEL + '_' +
image_name + ImagenetPath.IMAGES_EXT))
ImagenetPath.IMAGES_DIR_NO_LABEL + '_'
+ self._make_image_filename(item)))
13 changes: 10 additions & 3 deletions datumaro/plugins/imagenet_txt_format.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,8 @@


class ImagenetTxtPath:
DEFAULT_IMAGE_EXT = '.jpg'
IMAGE_EXT_FORMAT = ['.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif']
LABELS_FILE = 'synsets.txt'
IMAGE_DIR = 'images'

Expand Down Expand Up @@ -56,9 +58,14 @@ def _load_items(self, path):
label < len(self._categories[AnnotationType.label]), \
"Image '%s': unknown label id '%s'" % (item_id, label)
anno.append(Label(label))
image_path = osp.join(self.image_dir, item_id +
ImagenetTxtPath.DEFAULT_IMAGE_EXT)
for path in glob(osp.join(self.image_dir, item_id + '*')):
if osp.splitext(path)[1] in ImagenetTxtPath.IMAGE_EXT_FORMAT:
image_path = path
break
items[item_id] = DatasetItem(id=item_id, subset=self._subset,
image=osp.join(self.image_dir, item_id + '.jpg'),
annotations=anno)
image=image_path, annotations=anno)
return items


Expand All @@ -75,7 +82,7 @@ def find_sources(cls, path):


class ImagenetTxtConverter(Converter):
DEFAULT_IMAGE_EXT = '.jpg'
DEFAULT_IMAGE_EXT = ImagenetTxtPath.DEFAULT_IMAGE_EXT

def apply(self):
subset_dir = self._save_dir
Expand Down