clarifai 9.7.0__py3-none-any.whl → 9.7.2__py3-none-any.whl

clarifai_utils/data_upload/examples/image_detection/voc/annotations/2011_006412.xml

@@ -1,99 +0,0 @@
-<annotation>
-	<filename>2011_006412.jpg</filename>
-	<folder>VOC2011</folder>
-	<object>
-		<name>person</name>
-		<actions>
-			<jumping>0</jumping>
-			<other>0</other>
-			<phoning>0</phoning>
-			<playinginstrument>0</playinginstrument>
-			<reading>0</reading>
-			<ridingbike>0</ridingbike>
-			<ridinghorse>0</ridinghorse>
-			<running>0</running>
-			<takingphoto>0</takingphoto>
-			<usingcomputer>0</usingcomputer>
-			<walking>1</walking>
-		</actions>
-		<bndbox>
-			<xmax>58</xmax>
-			<xmin>1</xmin>
-			<ymax>375</ymax>
-			<ymin>173</ymin>
-		</bndbox>
-		<difficult>0</difficult>
-		<pose>Unspecified</pose>
-		<point>
-			<x>18</x>
-			<y>257</y>
-		</point>
-	</object>
-	<object>
-		<name>person</name>
-		<actions>
-			<jumping>0</jumping>
-			<other>0</other>
-			<phoning>0</phoning>
-			<playinginstrument>0</playinginstrument>
-			<reading>0</reading>
-			<ridingbike>0</ridingbike>
-			<ridinghorse>1</ridinghorse>
-			<running>0</running>
-			<takingphoto>0</takingphoto>
-			<usingcomputer>0</usingcomputer>
-			<walking>0</walking>
-		</actions>
-		<bndbox>
-			<xmax>223</xmax>
-			<xmin>123</xmin>
-			<ymax>330</ymax>
-			<ymin>106</ymin>
-		</bndbox>
-		<difficult>0</difficult>
-		<pose>Unspecified</pose>
-		<point>
-			<x>177</x>
-			<y>183</y>
-		</point>
-	</object>
-	<object>
-		<name>person</name>
-		<actions>
-			<jumping>0</jumping>
-			<other>0</other>
-			<phoning>0</phoning>
-			<playinginstrument>0</playinginstrument>
-			<reading>0</reading>
-			<ridingbike>0</ridingbike>
-			<ridinghorse>1</ridinghorse>
-			<running>0</running>
-			<takingphoto>0</takingphoto>
-			<usingcomputer>0</usingcomputer>
-			<walking>0</walking>
-		</actions>
-		<bndbox>
-			<xmax>397</xmax>
-			<xmin>293</xmin>
-			<ymax>303</ymax>
-			<ymin>111</ymin>
-		</bndbox>
-		<difficult>0</difficult>
-		<pose>Unspecified</pose>
-		<point>
-			<x>350</x>
-			<y>178</y>
-		</point>
-	</object>
-	<segmented>0</segmented>
-	<size>
-		<depth>3</depth>
-		<height>375</height>
-		<width>500</width>
-	</size>
-	<source>
-		<annotation>PASCAL VOC2011</annotation>
-		<database>The VOC2011 Database</database>
-		<image>flickr</image>
-	</source>
-</annotation>

clarifai_utils/data_upload/examples/image_detection/voc/annotations/2012_000690.xml

@@ -1,43 +0,0 @@
-<annotation>
-	<filename>2012_000690.jpg</filename>
-	<folder>VOC2012</folder>
-	<object>
-		<name>person</name>
-		<actions>
-			<jumping>0</jumping>
-			<other>0</other>
-			<phoning>0</phoning>
-			<playinginstrument>0</playinginstrument>
-			<reading>0</reading>
-			<ridingbike>0</ridingbike>
-			<ridinghorse>0</ridinghorse>
-			<running>0</running>
-			<takingphoto>1</takingphoto>
-			<usingcomputer>0</usingcomputer>
-			<walking>0</walking>
-		</actions>
-		<bndbox>
-			<xmax>142</xmax>
-			<xmin>63</xmin>
-			<ymax>375</ymax>
-			<ymin>137</ymin>
-		</bndbox>
-		<difficult>0</difficult>
-		<pose>Unspecified</pose>
-		<point>
-			<x>93</x>
-			<y>221</y>
-		</point>
-	</object>
-	<segmented>0</segmented>
-	<size>
-		<depth>3</depth>
-		<height>375</height>
-		<width>500</width>
-	</size>
-	<source>
-		<annotation>PASCAL VOC2012</annotation>
-		<database>The VOC2012 Database</database>
-		<image>flickr</image>
-	</source>
-</annotation>

clarifai_utils/data_upload/examples/image_detection/voc/dataset.py

@@ -1,76 +0,0 @@
-#! Pascal VOC Object Detection dataset.
-
-import os
-
-try:
-  import xml.etree.cElementTree as ET
-except ImportError:
-  import xml.etree.ElementTree as ET
-
-from clarifai.data_upload.datasets.features import VisualDetectionFeatures
-
-
-class VOCDetectionDataset:
-  """Pascal VOC Image Detection Dataset.
-  url: http://host.robots.ox.ac.uk/pascal/VOC/voc2012/index.html
-  """
-
-  voc_concepts = [
-      'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow',
-      'diningtable', 'dog', 'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa',
-      'train', 'tvmonitor'
-  ]
-
-  def __init__(self, split: str = "train") -> None:
-    """
-    Inititalize dataset params.
-    Args:
-      split: "train" or "test"
-    """
-
-    self.split = split
-    self.image_dir = {"train": os.path.join(os.path.dirname(__file__), "images")}
-    self.annotations_dir = {"train": os.path.join(os.path.dirname(__file__), "annotations")}
-
-  def dataloader(self):
-    """
-    Transform Pascal VOC detection dataset into clarifai proto compatible
-    format to uplaod
-    Returns:
-      VisualDetectionFeatures type generator.
-    """
-
-    all_imgs = os.listdir(self.image_dir[self.split])
-    img_ids = [img_filename.split('.')[0] for img_filename in all_imgs]
-
-    for _id in img_ids:
-      image_path = os.path.join(self.image_dir[self.split], _id + ".jpg")
-      annot_path = os.path.join(self.annotations_dir[self.split], _id + ".xml")
-
-      root = ET.parse(annot_path).getroot()
-      size = root.find('size')
-      width = float(size.find('width').text)
-      height = float(size.find('height').text)
-
-      annots = []
-      class_names = []
-      for obj in root.iter('object'):
-        concept = obj.find('name').text.strip().lower()
-        if concept not in self.voc_concepts:
-          continue
-        xml_box = obj.find('bndbox')
-        #Making bounding box to be 0-1
-        x_min = max(min((float(xml_box.find('xmin').text) - 1) / width, 1.0), 0.0)  #left_col
-        y_min = max(min((float(xml_box.find('ymin').text) - 1) / height, 1.0), 0.0)  #top_row
-        x_max = max(min((float(xml_box.find('xmax').text) - 1) / width, 1.0), 0.0)  #right_col
-        y_max = max(min((float(xml_box.find('ymax').text) - 1) / height, 1.0), 0.0)  #bottom_row
-
-        if (x_min >= x_max) or (y_min >= y_max):
-          continue
-        annots.append([x_min, y_min, x_max, y_max])
-        class_names.append(concept)
-
-      assert len(class_names) == len(annots), f"Num classes must match num bbox annotations\
-            for a single image. Found {len(class_names)} classes and {len(annots)} bboxes."
-
-      yield VisualDetectionFeatures(image_path, class_names, annots, id=_id)