remove Mosaic & RandomPerspective (#4450)

ppdet/data/transform/operators.py

@@ -253,8 +253,8 @@ class SniperDecodeCrop(BaseOperator):
 
         chip = sample['chip']
         x1, y1, x2, y2 = [int(xi) for xi in chip]
-        im = im[max(y1, 0):min(y2, im.shape[0]),
-                max(x1, 0):min(x2, im.shape[1]), :]
+        im = im[max(y1, 0):min(y2, im.shape[0]), max(x1, 0):min(x2, im.shape[
+            1]), :]
 
         sample['image'] = im
         h = im.shape[0]
@@ -2471,184 +2471,6 @@ class RandomResizeCrop(BaseOperator):
         return sample
 
 
-class RandomPerspective(BaseOperator):
-    """
-    Rotate, tranlate, scale, shear and perspect image and bboxes randomly,
-    refer to https://github.com/ultralytics/yolov5/blob/develop/utils/datasets.py
-
-    Args:
-        degree (int): rotation degree, uniformly sampled in [-degree, degree]
-        translate (float): translate fraction, translate_x and translate_y are uniformly sampled
-            in [0.5 - translate, 0.5 + translate]
-        scale (float): scale factor, uniformly sampled in [1 - scale, 1 + scale]
-        shear (int): shear degree, shear_x and shear_y are uniformly sampled in [-shear, shear]
-        perspective (float): perspective_x and perspective_y are uniformly sampled in [-perspective, perspective]
-        area_thr (float): the area threshold of bbox to be kept after transformation, default 0.25
-        fill_value (tuple): value used in case of a constant border, default (114, 114, 114)
-    """
-
-    def __init__(self,
-                 degree=10,
-                 translate=0.1,
-                 scale=0.1,
-                 shear=10,
-                 perspective=0.0,
-                 border=[0, 0],
-                 area_thr=0.25,
-                 fill_value=(114, 114, 114)):
-        super(RandomPerspective, self).__init__()
-        self.degree = degree
-        self.translate = translate
-        self.scale = scale
-        self.shear = shear
-        self.perspective = perspective
-        self.border = border
-        self.area_thr = area_thr
-        self.fill_value = fill_value
-
-    def apply(self, sample, context=None):
-        im = sample['image']
-        height = im.shape[0] + self.border[0] * 2
-        width = im.shape[1] + self.border[1] * 2
-
-        # center
-        C = np.eye(3)
-        C[0, 2] = -im.shape[1] / 2
-        C[1, 2] = -im.shape[0] / 2
-
-        # perspective
-        P = np.eye(3)
-        P[2, 0] = random.uniform(-self.perspective, self.perspective)
-        P[2, 1] = random.uniform(-self.perspective, self.perspective)
-
-        # Rotation and scale
-        R = np.eye(3)
-        a = random.uniform(-self.degree, self.degree)
-        s = random.uniform(1 - self.scale, 1 + self.scale)
-        R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
-
-        # Shear
-        S = np.eye(3)
-        # shear x (deg)
-        S[0, 1] = math.tan(
-            random.uniform(-self.shear, self.shear) * math.pi / 180)
-        # shear y (deg)
-        S[1, 0] = math.tan(
-            random.uniform(-self.shear, self.shear) * math.pi / 180)
-
-        # Translation
-        T = np.eye(3)
-        T[0, 2] = random.uniform(0.5 - self.translate,
-                                 0.5 + self.translate) * width
-        T[1, 2] = random.uniform(0.5 - self.translate,
-                                 0.5 + self.translate) * height
-
-        # matmul
-        # M = T @ S @ R @ P @ C
-        M = np.eye(3)
-        for cM in [T, S, R, P, C]:
-            M = np.matmul(M, cM)
-
-        if (self.border[0] != 0) or (self.border[1] != 0) or (
-                M != np.eye(3)).any():
-            if self.perspective:
-                im = cv2.warpPerspective(
-                    im, M, dsize=(width, height), borderValue=self.fill_value)
-            else:
-                im = cv2.warpAffine(
-                    im,
-                    M[:2],
-                    dsize=(width, height),
-                    borderValue=self.fill_value)
-
-        sample['image'] = im
-        if sample['gt_bbox'].shape[0] > 0:
-            sample = transform_bbox(
-                sample,
-                M,
-                width,
-                height,
-                area_thr=self.area_thr,
-                perspective=self.perspective)
-
-        return sample
-
-
-@register_op
-class Mosaic(BaseOperator):
-    """
-    Mosaic Data Augmentation, refer to https://github.com/ultralytics/yolov5/blob/develop/utils/datasets.py
-
-    """
-
-    def __init__(self,
-                 target_size,
-                 mosaic_border=None,
-                 fill_value=(114, 114, 114)):
-        super(Mosaic, self).__init__()
-        self.target_size = target_size
-        if mosaic_border is None:
-            mosaic_border = (-target_size // 2, -target_size // 2)
-        self.mosaic_border = mosaic_border
-        self.fill_value = fill_value
-
-    def __call__(self, sample, context=None):
-        if not isinstance(sample, Sequence):
-            return sample
-
-        s = self.target_size
-        yc, xc = [
-            int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border
-        ]
-        boxes = [x['gt_bbox'] for x in sample]
-        labels = [x['gt_class'] for x in sample]
-        for i in range(len(sample)):
-            im = sample[i]['image']
-            h, w, c = im.shape
-
-            if i == 0:  # top left
-                image = np.ones(
-                    (s * 2, s * 2, c), dtype=np.uint8) * self.fill_value
-                # xmin, ymin, xmax, ymax (dst image)
-                x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc
-                # xmin, ymin, xmax, ymax (src image)
-                x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h
-            elif i == 1:  # top right
-                x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
-                x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
-            elif i == 2:  # bottom left
-                x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
-                x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, max(xc, w), min(
-                    y2a - y1a, h)
-            elif i == 3:  # bottom right
-                x1a, y1a, x2a, y2a = xc, yc, min(xc + w,
-                                                 s * 2), min(s * 2, yc + h)
-                x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
-
-            image[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b]
-            padw = x1a - x1b
-            padh = y1a - y1b
-            boxes[i] = boxes[i] + (padw, padh, padw, padh)
-
-        boxes = np.concatenate(boxes, axis=0)
-        boxes = np.clip(boxes, 0, s * 2)
-        labels = np.concatenate(labels, axis=0)
-        if 'is_crowd' in sample[0]:
-            is_crowd = np.concatenate([x['is_crowd'] for x in sample], axis=0)
-        if 'difficult' in sample[0]:
-            difficult = np.concatenate([x['difficult'] for x in sample], axis=0)
-        sample = sample[0]
-        sample['image'] = image.astype(np.uint8)
-        sample['gt_bbox'] = boxes
-        sample['gt_class'] = labels
-        if 'is_crowd' in sample:
-            sample['is_crowd'] = is_crowd
-        if 'difficult' in sample:
-            sample['difficult'] = difficult
-
-        return sample
-
-
 @register_op
 class RandomSelect(BaseOperator):
     """