clarifai 9.1.0__py3-none-any.whl → 9.3.1__py3-none-any.whl

clarifai_utils/data_upload/datasets/text.py

@@ -0,0 +1,62 @@
+from typing import Iterator, List
+
+from clarifai_grpc.grpc.api import resources_pb2
+from google.protobuf.struct_pb2 import Struct
+from tqdm import tqdm
+
+from .base import ClarifaiDataset
+
+
+class TextClassificationDataset(ClarifaiDataset):
+  """
+  Upload text classification datasets to clarifai datasets
+  """
+
+  def __init__(self, datagen_object: Iterator, dataset_id: str, split: str) -> None:
+    super().__init__(datagen_object, dataset_id, split)
+
+  def create_input_protos(self, text_input: str, labels: List[str], input_id: str, dataset_id: str,
+                          metadata: Struct) -> resources_pb2.Input:
+    """
+    Create input protos for each text, label input pairs.
+    Args:
+    	`text_input`: text string.
+    	`labels`: text labels
+    	`input_id: unique input id
+    	`dataset_id`: Clarifai dataset id
+    	`metadata`:input metadata
+    Returns:
+    	An input proto representing a single row input
+    """
+    input_proto = resources_pb2.Input(
+        id=input_id,
+        dataset_ids=[dataset_id],
+        data=resources_pb2.Data(
+            text=resources_pb2.Text(raw=text_input),
+            concepts=[
+                resources_pb2.Concept(
+                    id=f"id-{''.join(_label.split(' '))}", name=_label, value=1.)
+                for _label in labels
+            ],
+            metadata=metadata))
+
+    return input_proto
+
+  def _get_input_protos(self) -> Iterator:
+    """
+    Creates input protos for each data generator item.
+    Returns:
+    	A list of input protos
+    """
+    for i, item in tqdm(enumerate(self.datagen_object), desc="Loading text data"):
+      metadata = Struct()
+      text = item.text
+      labels = item.labels if isinstance(item.labels, list) else [item.labels]  # clarifai concept
+      input_id = f"{self.dataset_id}-{self.split}-{i}" if item.id is None else f"{self.split}-{str(item.id)}"
+      metadata.update({"label": labels, "split": self.split})
+
+      input_proto = self.create_input_protos(text, labels, input_id, self.dataset_id, metadata)
+
+      self._all_input_protos.append(input_proto)
+
+    return iter(self._all_input_protos)

clarifai_utils/data_upload/datasets/zoo/coco_captions.py

@@ -0,0 +1,99 @@
+#! COCO 2017 image captioning dataset
+
+import os
+import zipfile
+from glob import glob
+
+import requests
+from pycocotools.coco import COCO
+from tqdm import tqdm
+
+from ..features import VisualClassificationFeatures
+
+
+class COCOCaptionsDataset:
+  """COCO 2017 Image Captioning Dataset."""
+
+  def __init__(self, split: str = "train"):
+    """
+    Initialize coco dataset.
+    Args:
+      filenames: the coco zip filenames: List[str] to be downloaded if download=True,
+      data_dir: the local coco dataset directory.
+      split: "train" or "val"
+    """
+    self.filenames = {
+        "train": "train2017.zip",
+        "val": "val2017.zip",
+        "annotations": "annotations_trainval2017.zip"
+    }
+    self.split = split
+    self.url = "http://images.cocodataset.org/zips/"  # coco base image-zip url
+    self.data_dir = os.path.join(os.curdir, ".data")  # data storage directory
+    self.extracted_coco_dirs = {"train": None, "val": None, "annotations": None}
+
+  def coco_download(self, save_dir):
+    """Download coco dataset."""
+    if not os.path.exists(save_dir):
+      os.mkdir(save_dir)
+
+    #check if train, val and annotation dirs exist
+    #so that the coco2017 data isn't downloaded
+    for key, filename in self.filenames.items():
+      if os.path.exists(glob(f"{save_dir}/{key}*")[0]):
+        print("Dataset already downloded and extracted")
+        continue
+
+      print("-" * 80)
+      print(f"Downloading {filename}")
+      print("-" * 80)
+
+      if "annotations" in filename:
+        self.url = "http://images.cocodataset.org/annotations/"
+
+      response = requests.get(self.url + filename, stream=True)
+      response.raise_for_status()
+      with open(os.path.join(save_dir, filename), "wb") as _file:
+        for chunk in tqdm(response.iter_content(chunk_size=5124000)):
+          if chunk:
+            _file.write(chunk)
+      print("Data download complete...")
+
+      #extract files
+      zf = zipfile.ZipFile(os.path.join(save_dir, filename))
+      print(f" Extracting {filename} file")
+      zf.extractall(path=save_dir)
+      # Delete coco zip
+      print(f" Deleting {filename}")
+      os.remove(path=os.path.join(save_dir, filename))
+
+  def dataloader(self):
+    """
+    Transform coco image captioning data into clarifai proto compatible
+    format for upload.
+    Returns:
+      VisualClassificationFeatures type generator.
+    """
+    if isinstance(self.filenames, list) and len(self.filenames) == 3:  #train, val, annotations
+      self.coco_download(self.data_dir)
+      self.extracted_coco_dirs["train"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "train" in i][0]
+      self.extracted_coco_dirs["val"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "val" in i][0]
+
+      self.extracted_coco_dirs["annotations"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "annotations" in i][0]
+    else:
+      raise Exception(f"`filenames` must be a list of atleast 3 coco zip file names; \
+      train, val and annotations. Found {len(self.filenames)} items instead.")
+
+    annot_file = glob(self.extracted_coco_dirs["annotations"] + "/" + f"captions_{self.split}*")[0]
+    coco = COCO(annot_file)
+    annot_ids = coco.getAnnIds()
+    annotations = coco.loadAnns(annot_ids)
+    for annot in annotations:
+      image_path = glob(self.extracted_coco_dirs[self.split]+"/"+\
+      f"{str(annot['image_id']).zfill(12)}*")[0]
+      # image_captioning and image classification datasets have the same
+      # image-label input feature formats
+      yield VisualClassificationFeatures(image_path, annot["caption"], annot["image_id"])

clarifai_utils/data_upload/datasets/zoo/coco_detection.py

@@ -0,0 +1,129 @@
+#! COCO 2017 detection dataset
+
+import os
+import zipfile
+from glob import glob
+
+import cv2
+import requests
+from pycocotools.coco import COCO
+from tqdm import tqdm
+
+from ..features import VisualDetectionFeatures
+
+
+class COCODetectionDataset:
+  """COCO 2017 Image Detection Dataset."""
+
+  def __init__(self, split: str = "train"):
+    """
+    Initialize coco dataset.
+    Args:
+      filenames: the coco zip filenames: List[str] to be downloaded if download=True,
+      data_dir: the local coco dataset directory.
+      split: "train" or "val"
+    """
+    self.filenames = {
+        "train": "train2017.zip",
+        "val": "val2017.zip",
+        "annotations": "annotations_trainval2017.zip"
+    }
+    self.split = split
+    self.url = "http://images.cocodataset.org/zips/"  # coco base image-zip url
+    self.data_dir = os.path.join(os.curdir, ".data")  # data storage directory
+    self.extracted_coco_dirs = {"train": None, "val": None, "annotations": None}
+
+  def coco_download(self, save_dir):
+    """Download coco dataset."""
+    if not os.path.exists(save_dir):
+      os.mkdir(save_dir)
+
+    #check if train*, val* and annotation* dirs exist
+    #so that the coco2017 data isn't downloaded
+    for key, filename in self.filenames.items():
+      if os.path.exists(glob(f"{save_dir}/{key}*")[0]):
+        print("dataset already downloded and extracted")
+        continue
+
+      print("-" * 80)
+      print(f"Downloading {filename}")
+      print("-" * 80)
+
+      if "annotations" in filename:
+        self.url = "http://images.cocodataset.org/annotations/"
+
+      response = requests.get(self.url + filename, stream=True)
+      response.raise_for_status()
+      with open(os.path.join(save_dir, filename), "wb") as _file:
+        for chunk in tqdm(response.iter_content(chunk_size=5124000)):
+          if chunk:
+            _file.write(chunk)
+      print("Coco data download complete...")
+
+      #extract files
+      zf = zipfile.ZipFile(os.path.join(save_dir, filename))
+      print(f" Extracting {filename} file")
+      zf.extractall(path=save_dir)
+      # Delete coco zip
+      print(f" Deleting {filename}")
+      os.remove(path=os.path.join(save_dir, filename))
+
+  def dataloader(self):
+    """
+    Transform coco object detection data into clarifai proto compatible
+    format for upload.
+    Returns:
+      VisualDetectionFeatures type generator.
+    """
+    if isinstance(self.filenames, list) and len(self.filenames) == 3:
+      self.coco_download(self.data_dir)
+      self.extracted_coco_dirs["train"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "train" in i][0]
+      self.extracted_coco_dirs["val"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "val" in i][0]
+
+      self.extracted_coco_dirs["annotations"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "annotations" in i][0]
+    else:
+      raise Exception(f"`filenames` must be a list of atleast 2 coco zip file names; \
+      train, val and annotations. Found {len(self.filenames)} items instead.")
+
+    annot_file = glob(self.extracted_coco_dirs["annotations"] + "/" +\
+     f"instances_{self.split}*")[0]
+    coco = COCO(annot_file)
+    categories = coco.loadCats(coco.getCatIds())
+    cat_id_map = {category["id"]: category["name"] for category in categories}
+    cat_img_ids = {}
+    for cat_id in list(cat_id_map.keys()):
+      cat_img_ids[cat_id] = coco.getImgIds(catIds=[cat_id])
+
+    img_ids = []
+    for i in list(cat_img_ids.values()):
+      img_ids.extend(i)
+
+    #get annotations for each image id
+    for _id in img_ids:
+      annots = []  # bboxes
+      class_names = []
+      labels = [i for i in list(filter(lambda x: _id in cat_img_ids[x], cat_img_ids))]
+      image_path = glob(self.extracted_coco_dirs[self.split]+"/"+\
+      f"{str(_id).zfill(12)}*")[0]
+
+      image_height, image_width = cv2.imread(image_path).shape[:2]
+      for cat_id in labels:
+        annot_ids = coco.getAnnIds(imgIds=_id, catIds=[cat_id])
+        if len(annot_ids) > 0:
+          img_annotations = coco.loadAnns(annot_ids)
+          for ann in img_annotations:
+            class_names.append(cat_id_map[cat_id])
+            x_min = ann['bbox'][0] / image_width  #left_col
+            y_min = ann['bbox'][1] / image_height  #top_row
+            x_max = (ann['bbox'][0] + ann['bbox'][2]) / image_width  #right_col
+            y_max = (ann['bbox'][1] + ann['bbox'][3]) / image_height  #bottom_row
+            annots.append([x_min, y_min, x_max, y_max])
+        else:  # if no annotations for given image_id-cat_id pair
+          continue
+      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)

clarifai_utils/data_upload/datasets/zoo/coco_segmentation.py

@@ -0,0 +1,158 @@
+#! COCO 2017 Image Segmentation dataset
+
+import gc
+import os
+import zipfile
+from functools import reduce
+from glob import glob
+
+import cv2
+import numpy as np
+import requests
+from pycocotools import mask as maskUtils
+from pycocotools.coco import COCO
+from tqdm import tqdm
+
+from ..features import VisualSegmentationFeatures
+
+
+class COCOSegmentationDataset:
+  """COCO 2017 Image Segmentation Dataset."""
+
+  def __init__(self, split: str = "train"):
+    """
+    Initialize coco dataset.
+    Args:
+      filenames: the coco zip filenames: List[str] to be downloaded if download=True,
+      data_dir: the local coco dataset directory
+      split: "train" or "val"
+    """
+    self.filenames = {
+        "train": "train2017.zip",
+        "val": "val2017.zip",
+        "annotations": "annotations_trainval2017.zip"
+    }
+    self.split = split
+    self.url = "http://images.cocodataset.org/zips/"  # coco base image-zip url
+    self.data_dir = os.path.join(os.curdir, ".data")  # data storage dir
+    self.extracted_coco_dirs = {"train": None, "val": None, "annotations": None}
+
+  def coco_download(self, save_dir):
+    """Download coco dataset."""
+    if not os.path.exists(save_dir):
+      os.mkdir(save_dir)
+
+    #check if train, val and annotation dirs exist
+    #so that the coco2017 data isn't downloaded
+    for key, filename in self.filenames.items():
+      if os.path.exists(glob(f"{save_dir}/{key}*")[0]):
+        print("dataset already downloded and extracted")
+        continue
+
+      print("-" * 80)
+      print(f"Downloading {filename}")
+      print("-" * 80)
+
+      if "annotations" in filename:
+        self.url = "http://images.cocodataset.org/annotations/"
+
+      response = requests.get(self.url + filename, stream=True)
+      response.raise_for_status()
+      with open(os.path.join(save_dir, filename), "wb") as _file:
+        for chunk in tqdm(response.iter_content(chunk_size=5124000)):
+          if chunk:
+            _file.write(chunk)
+      print("Coco data download complete...")
+
+      #extract files
+      zf = zipfile.ZipFile(os.path.join(save_dir, filename))
+      print(f" Extracting {filename} file")
+      zf.extractall(path=save_dir)
+      # Delete coco zip
+      print(f" Deleting {filename}")
+      os.remove(path=os.path.join(save_dir, filename))
+
+  def dataloader(self):
+    """
+    Transform coco data into clarifai proto compatible format for upload.
+    Returns:
+      VisualSegmentationFeatures type generator.
+    """
+    if isinstance(self.filenames, list) and len(self.filenames) == 3:
+      self.coco_download(self.data_dir)
+      self.extracted_coco_dirs["train"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "train" in i][0]
+      self.extracted_coco_dirs["val"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "val" in i][0]
+
+      self.extracted_coco_dirs["annotations"] = [os.path.join(self.data_dir, i) \
+      for i in os.listdir(self.data_dir) if "annotations" in i][0]
+    else:
+      raise Exception(f"`filenames` must be a list of atleast 3 coco zip file names; \
+      train, val and annotations. Found {len(self.filenames)} items instead.")
+
+    annot_file = glob(self.extracted_coco_dirs["annotations"] + "/" +\
+     f"instances_{self.split}*")[0]
+    coco = COCO(annot_file)
+    categories = coco.loadCats(coco.getCatIds())
+    cat_id_map = {category["id"]: category["name"] for category in categories}
+    cat_img_ids = {}
+    for cat_id in list(cat_id_map.keys()):
+      cat_img_ids[cat_id] = coco.getImgIds(catIds=[cat_id])
+
+    img_ids = []
+    for i in list(cat_img_ids.values()):
+      img_ids.extend(i)
+
+    #get annotations for each image id
+    for _id in img_ids:
+      annots = []  # polygons
+      class_names = []
+      labels = [i for i in list(filter(lambda x: _id in cat_img_ids[x], cat_img_ids))]
+      image_path = glob(self.extracted_coco_dirs[self.split]+"/"+\
+      f"{str(_id).zfill(12)}*")[0]
+
+      image_height, image_width = cv2.imread(image_path).shape[:2]
+      for cat_id in labels:
+        annot_ids = coco.getAnnIds(imgIds=_id, catIds=[cat_id])
+        if len(annot_ids) > 0:
+          img_annotations = coco.loadAnns(annot_ids)
+          for ann in img_annotations:
+            class_names.append(cat_id_map[cat_id])
+            # get polygons
+            if type(ann['segmentation']) == list:
+              for seg in ann['segmentation']:
+                poly = np.array(seg).reshape((int(len(seg) / 2), 2))
+                poly[:, 0], poly[:, 1] = poly[:, 0] / image_width, poly[:, 1] / image_height
+                annots.append(poly.tolist())  #[[x=col, y=row],...]
+            else:  # seg: {"counts":[...]}
+              if type(ann['segmentation']['counts']) == list:
+                rle = maskUtils.frPyObjects([ann['segmentation']], image_height, image_width)
+              else:
+                rle = ann['segmentation']
+              mask = maskUtils.decode(rle)  #binary mask
+              #convert mask to polygons and add to annots
+              contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
+              polygons = []
+              for cont in contours:
+                if cont.size >= 6:
+                  polygons.append(cont.astype(float).flatten().tolist())
+              # store polygons in (x,y) pairs
+              polygons_flattened = reduce(lambda x, y: x + y, polygons)
+              del polygons
+              del contours
+              del mask
+              gc.collect()
+
+              polygons = np.array(polygons_flattened).reshape((int(len(polygons_flattened) / 2),
+                                                               2))
+              polygons[:, 0] = polygons[:, 0] / image_width
+              polygons[:, 1] = polygons[:, 1] / image_height
+
+              annots.append(polygons.tolist())  #[[x=col, y=row],...,[x=col, y=row]]
+        else:  # if no annotations for given image_id-cat_id pair
+          continue
+      assert len(class_names) == len(annots), f"Num classes must match num annotations\
+      for a single image. Found {len(class_names)} classes and {len(annots)} polygons."
+
+      yield VisualSegmentationFeatures(image_path, class_names, annots, _id)

clarifai_utils/data_upload/examples.py

@@ -0,0 +1,19 @@
+#! Execute dataset upload using the `from_module` upload feature
+
+from clarifai.data_upload.upload import UploadConfig
+
+text_upload_obj = UploadConfig(
+    user_id="",
+    app_id="",
+    pat="",
+    dataset_id="",
+    task="visual_clf",
+    from_module="./examples/image_classification/cifar10",
+    split="train",
+    portal="clarifai"  #clarifai(prod), dev or staging
+)
+## change the task and from_module arguments in UploadConfig() to upload
+## example food-101 dataset
+
+if __name__ == "__main__":
+  text_upload_obj.upload_to_clarifai()