Upload folder using huggingface_hub

util/box_ops.py

@@ -0,0 +1,111 @@
+import numpy as np
+import cv2
+
+def compute_iou_matrix(boxes):
+    '''
+    Given a set of bboxes (in [x1, y1, x2, y2]), output an IOU matrix,
+    while ignoring pairs where one box fully contains the other.
+    '''
+    N = boxes.shape[0]
+    iou_matrix = np.zeros((N, N), dtype=np.float32)
+
+    def is_contained(box_a, box_b):
+        return (
+            box_a[0] <= box_b[0] and box_a[1] <= box_b[1] and
+            box_a[2] >= box_b[2] and box_a[3] >= box_b[3]
+        )
+
+    def is_almost_contained(inner, outer, epsilon=2):
+	    x1_i, y1_i, w_i, h_i = inner
+	    x1_o, y1_o, w_o, h_o = outer
+
+	    x2_i, y2_i = x1_i + w_i, y1_i + h_i
+	    x2_o, y2_o = x1_o + w_o, y1_o + h_o
+
+	    return (
+	        x1_i >= x1_o - epsilon and
+	        y1_i >= y1_o - epsilon and
+	        x2_i <= x2_o + epsilon and
+	        y2_i <= y2_o + epsilon
+	    )
+
+    for i in range(N):
+        x1_i, y1_i, x2_i, y2_i = boxes[i]
+        area_i = (x2_i - x1_i) * (y2_i - y1_i)
+        for j in range(i + 1, N):
+            x1_j, y1_j, x2_j, y2_j = boxes[j]
+            area_j = (x2_j - x1_j) * (y2_j - y1_j)
+
+            box_i = boxes[i]
+            box_j = boxes[j]
+
+            # Skip if one box fully contains the other
+            if is_almost_contained(box_i, box_j) or is_almost_contained(box_j, box_i):
+                iou = 0.0
+            else:
+                inter_x1 = max(x1_i, x1_j)
+                inter_y1 = max(y1_i, y1_j)
+                inter_x2 = min(x2_i, x2_j)
+                inter_y2 = min(y2_i, y2_j)
+
+                inter_w = max(0, inter_x2 - inter_x1)
+                inter_h = max(0, inter_y2 - inter_y1)
+                inter_area = inter_w * inter_h
+
+                union_area = area_i + area_j - inter_area
+                iou = inter_area / union_area if union_area > 0 else 0.0
+
+            iou_matrix[i, j] = iou
+            iou_matrix[j, i] = iou  # symmetric
+
+    return iou_matrix
+
+
+
+def draw_bboxes(image, bbox_xyxy, color=(0, 255, 0), thickness=2):
+    '''
+    given an image and set of bboxes, output a bbox annotated image
+    '''
+    image_copy = image.copy()
+    for box in bbox_xyxy:
+        x1, y1, x2, y2 = map(int, box)
+        cv2.rectangle(image_copy, (x1, y1), (x2, y2), color, thickness)
+    return image_copy
+
+
+def add_black_border(patch, border_width=1):
+    """
+    Set the outermost border of the patch to white.
+    
+    Args:
+        patch (np.ndarray): An image patch of shape (H, W, 3) for RGB.
+        border_width (int): Width of the white border (default: 1 pixel).
+    
+    Returns:
+        np.ndarray: The patch with a black border.
+    """
+    patch[:border_width, :, 0:3] = 255              # Top border
+    patch[-border_width:, :, 0:3] = 255             # Bottom border
+    patch[:, :border_width, 0:3] = 255              # Left border
+    patch[:, -border_width:, 0:3] = 255             # Right border
+    return patch
+
+def mask_to_bbox_xywh(mask):
+    """
+    Obtain bbox (xywh) from the mask.
+
+    Args:
+        mask (np.ndarray)
+
+    Returns:
+        np.ndarray: a bbox of shape (1, 4), in the format of [x, y, w, h]。
+                    if empty, return shape (0, 4)。
+    """
+    ys, xs = np.where(mask)
+    if len(xs) == 0 or len(ys) == 0:
+        return np.zeros((0, 4), dtype=np.int32)
+
+    x_min, x_max = xs.min(), xs.max()
+    y_min, y_max = ys.min(), ys.max()
+    bbox = [x_min, y_min, x_max - x_min, y_max - y_min]
+    return np.array(bbox, dtype=np.int32)

util/cityscapes_ops.py

@@ -0,0 +1,261 @@
+from collections import namedtuple
+from abc import ABCMeta, abstractmethod
+import os
+import json
+
+Label = namedtuple( 'Label' , [
+
+    'name'        , # The identifier of this label, e.g. 'car', 'person', ... .
+                    # We use them to uniquely name a class
+
+    'id'          , # An integer ID that is associated with this label.
+                    # The IDs are used to represent the label in ground truth images
+                    # An ID of -1 means that this label does not have an ID and thus
+                    # is ignored when creating ground truth images (e.g. license plate).
+                    # Do not modify these IDs, since exactly these IDs are expected by the
+                    # evaluation server.
+
+    'trainId'     , # Feel free to modify these IDs as suitable for your method. Then create
+                    # ground truth images with train IDs, using the tools provided in the
+                    # 'preparation' folder. However, make sure to validate or submit results
+                    # to our evaluation server using the regular IDs above!
+                    # For trainIds, multiple labels might have the same ID. Then, these labels
+                    # are mapped to the same class in the ground truth images. For the inverse
+                    # mapping, we use the label that is defined first in the list below.
+                    # For example, mapping all void-type classes to the same ID in training,
+                    # might make sense for some approaches.
+                    # Max value is 255!
+
+    'category'    , # The name of the category that this label belongs to
+
+    'categoryId'  , # The ID of this category. Used to create ground truth images
+                    # on category level.
+
+    'hasInstances', # Whether this label distinguishes between single instances or not
+
+    'ignoreInEval', # Whether pixels having this class as ground truth label are ignored
+                    # during evaluations or not
+
+    'color'       , # The color of this label
+    ] )
+
+labels = [
+    #       name                     id    trainId   category            catId     hasInstances   ignoreInEval   color
+    Label(  'unlabeled'            ,  0 ,      255 , 'void'            , 0       , False        , True         , (  0,  0,  0) ),
+    Label(  'ego vehicle'          ,  1 ,      255 , 'void'            , 0       , False        , True         , (  0,  0,  0) ),
+    Label(  'rectification border' ,  2 ,      255 , 'void'            , 0       , False        , True         , (  0,  0,  0) ),
+    Label(  'out of roi'           ,  3 ,      255 , 'void'            , 0       , False        , True         , (  0,  0,  0) ),
+    Label(  'static'               ,  4 ,      255 , 'void'            , 0       , False        , True         , (  0,  0,  0) ),
+    Label(  'dynamic'              ,  5 ,      255 , 'void'            , 0       , False        , True         , (111, 74,  0) ),
+    Label(  'ground'               ,  6 ,      255 , 'void'            , 0       , False        , True         , ( 81,  0, 81) ),
+    Label(  'road'                 ,  7 ,        0 , 'flat'            , 1       , False        , False        , (128, 64,128) ),
+    Label(  'sidewalk'             ,  8 ,        1 , 'flat'            , 1       , False        , False        , (244, 35,232) ),
+    Label(  'parking'              ,  9 ,      255 , 'flat'            , 1       , False        , True         , (250,170,160) ),
+    Label(  'rail track'           , 10 ,      255 , 'flat'            , 1       , False        , True         , (230,150,140) ),
+    Label(  'building'             , 11 ,        2 , 'construction'    , 2       , False        , False        , ( 70, 70, 70) ),
+    Label(  'wall'                 , 12 ,        3 , 'construction'    , 2       , False        , False        , (102,102,156) ),
+    Label(  'fence'                , 13 ,        4 , 'construction'    , 2       , False        , False        , (190,153,153) ),
+    Label(  'guard rail'           , 14 ,      255 , 'construction'    , 2       , False        , True         , (180,165,180) ),
+    Label(  'bridge'               , 15 ,      255 , 'construction'    , 2       , False        , True         , (150,100,100) ),
+    Label(  'tunnel'               , 16 ,      255 , 'construction'    , 2       , False        , True         , (150,120, 90) ),
+    Label(  'pole'                 , 17 ,        5 , 'object'          , 3       , False        , False        , (153,153,153) ),
+    Label(  'polegroup'            , 18 ,      255 , 'object'          , 3       , False        , True         , (153,153,153) ),
+    Label(  'traffic light'        , 19 ,        6 , 'object'          , 3       , False        , False        , (250,170, 30) ),
+    Label(  'traffic sign'         , 20 ,        7 , 'object'          , 3       , False        , False        , (220,220,  0) ),
+    Label(  'vegetation'           , 21 ,        8 , 'nature'          , 4       , False        , False        , (107,142, 35) ),
+    Label(  'terrain'              , 22 ,        9 , 'nature'          , 4       , False        , False        , (152,251,152) ),
+    Label(  'sky'                  , 23 ,       10 , 'sky'             , 5       , False        , False        , ( 70,130,180) ),
+    Label(  'person'               , 24 ,       11 , 'human'           , 6       , True         , False        , (220, 20, 60) ),
+    Label(  'rider'                , 25 ,       12 , 'human'           , 6       , True         , False        , (255,  0,  0) ),
+    Label(  'car'                  , 26 ,       13 , 'vehicle'         , 7       , True         , False        , (  0,  0,142) ),
+    Label(  'truck'                , 27 ,       14 , 'vehicle'         , 7       , True         , False        , (  0,  0, 70) ),
+    Label(  'bus'                  , 28 ,       15 , 'vehicle'         , 7       , True         , False        , (  0, 60,100) ),
+    Label(  'caravan'              , 29 ,      255 , 'vehicle'         , 7       , True         , True         , (  0,  0, 90) ),
+    Label(  'trailer'              , 30 ,      255 , 'vehicle'         , 7       , True         , True         , (  0,  0,110) ),
+    Label(  'train'                , 31 ,       16 , 'vehicle'         , 7       , True         , False        , (  0, 80,100) ),
+    Label(  'motorcycle'           , 32 ,       17 , 'vehicle'         , 7       , True         , False        , (  0,  0,230) ),
+    Label(  'bicycle'              , 33 ,       18 , 'vehicle'         , 7       , True         , False        , (119, 11, 32) ),
+    Label(  'license plate'        , -1 ,       -1 , 'vehicle'         , 7       , False        , True         , (  0,  0,142) ),
+]
+
+
+# name to label object
+name2label      = { label.name    : label for label in labels           }
+
+# A point in a polygon
+Point = namedtuple('Point', ['x', 'y'])
+
+class CsObjectType():
+    POLY = 1 # polygon
+    BBOX = 2 # bounding box
+
+
+# Abstract base class for annotation objects
+class CsObject:
+    __metaclass__ = ABCMeta
+
+    def __init__(self, objType):
+        self.objectType = objType
+        # the label
+        self.label    = ""
+
+        # If deleted or not
+        self.deleted  = 0
+        # If verified or not
+        self.verified = 0
+        # The date string
+        self.date     = ""
+        # The username
+        self.user     = ""
+        # Draw the object
+        # Not read from or written to JSON
+        # Set to False if deleted object
+        # Might be set to False by the application for other reasons
+        self.draw     = True
+
+    @abstractmethod
+    def __str__(self): pass
+
+    @abstractmethod
+    def fromJsonText(self, jsonText, objId=-1): pass
+
+    @abstractmethod
+    def toJsonText(self): pass
+
+    def updateDate( self ):
+        try:
+            locale.setlocale( locale.LC_ALL , 'en_US.utf8' )
+        except locale.Error:
+            locale.setlocale( locale.LC_ALL , 'en_US' )
+        except locale.Error:
+            locale.setlocale( locale.LC_ALL , 'us_us.utf8' )
+        except locale.Error:
+            locale.setlocale( locale.LC_ALL , 'us_us' )
+        except:
+            pass
+        self.date = datetime.datetime.now().strftime("%d-%b-%Y %H:%M:%S")
+
+    # Mark the object as deleted
+    def delete(self):
+        self.deleted = 1
+        self.draw    = False
+
+
+# Class that contains the information of a single annotated object as polygon
+class CsPoly(CsObject):
+    # Constructor
+    def __init__(self):
+        CsObject.__init__(self, CsObjectType.POLY)
+        # the polygon as list of points
+        self.polygon    = []
+        # the object ID
+        self.id         = -1
+
+    def __str__(self):
+        polyText = ""
+        if self.polygon:
+            if len(self.polygon) <= 4:
+                for p in self.polygon:
+                    polyText += '({},{}) '.format( p.x , p.y )
+            else:
+                polyText += '({},{}) ({},{}) ... ({},{}) ({},{})'.format(
+                    self.polygon[ 0].x , self.polygon[ 0].y ,
+                    self.polygon[ 1].x , self.polygon[ 1].y ,
+                    self.polygon[-2].x , self.polygon[-2].y ,
+                    self.polygon[-1].x , self.polygon[-1].y )
+        else:
+            polyText = "none"
+        text = "Object: {} - {}".format( self.label , polyText )
+        return text
+
+    def fromJsonText(self, jsonText, objId):
+        self.id = objId
+        self.label = str(jsonText['label'])
+        self.polygon = [ Point(p[0],p[1]) for p in jsonText['polygon'] ]
+        if 'deleted' in jsonText.keys():
+            self.deleted = jsonText['deleted']
+        else:
+            self.deleted = 0
+        if 'verified' in jsonText.keys():
+            self.verified = jsonText['verified']
+        else:
+            self.verified = 1
+        if 'user' in jsonText.keys():
+            self.user = jsonText['user']
+        else:
+            self.user = ''
+        if 'date' in jsonText.keys():
+            self.date = jsonText['date']
+        else:
+            self.date = ''
+        if self.deleted == 1:
+            self.draw = False
+        else:
+            self.draw = True
+
+    def toJsonText(self):
+        objDict = {}
+        objDict['label'] = self.label
+        objDict['id'] = self.id
+        objDict['deleted'] = self.deleted
+        objDict['verified'] = self.verified
+        objDict['user'] = self.user
+        objDict['date'] = self.date
+        objDict['polygon'] = []
+        for pt in self.polygon:
+            objDict['polygon'].append([pt.x, pt.y])
+
+        return objDict
+
+# The annotation of a whole image (doesn't support mixed annotations, i.e. combining CsPoly and CsBbox)
+class Annotation:
+    # Constructor
+    def __init__(self, objType=CsObjectType.POLY):
+        # the width of that image and thus of the label image
+        self.imgWidth  = 0
+        # the height of that image and thus of the label image
+        self.imgHeight = 0
+        # the list of objects
+        self.objects = []
+        assert objType in CsObjectType.__dict__.values()
+        self.objectType = objType
+
+    def toJson(self):
+        return json.dumps(self, default=lambda o: o.__dict__, sort_keys=True, indent=4)
+
+    def fromJsonText(self, jsonText):
+        jsonDict = json.loads(jsonText)
+        self.imgWidth  = int(jsonDict['imgWidth'])
+        self.imgHeight = int(jsonDict['imgHeight'])
+        self.objects   = []
+        for objId, objIn in enumerate(jsonDict[ 'objects' ]):
+            if self.objectType == CsObjectType.POLY:
+                obj = CsPoly()
+            elif self.objectType == CsObjectType.BBOX:
+                obj = CsBbox()
+            obj.fromJsonText(objIn, objId)
+            self.objects.append(obj)
+
+    def toJsonText(self):
+        jsonDict = {}
+        jsonDict['imgWidth'] = self.imgWidth
+        jsonDict['imgHeight'] = self.imgHeight
+        jsonDict['objects'] = []
+        for obj in self.objects:
+            objDict = obj.toJsonText()
+            jsonDict['objects'].append(objDict)
+
+        return jsonDict
+
+    # Read a json formatted polygon file and return the annotation
+    def fromJsonFile(self, jsonFile):
+        if not os.path.isfile(jsonFile):
+            # print('Given json file not found: {}'.format(jsonFile))
+            return
+        with open(jsonFile, 'r') as f:
+            jsonText = f.read()
+            self.fromJsonText(jsonText)
+
+    def toJsonFile(self, jsonFile):
+        with open(jsonFile, 'w') as f:
+            f.write(self.toJson())