Predictor support (#65)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Laughing-q <1185102784@qq.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

ultralytics/yolo/utils/ops.py

@@ -1,5 +1,6 @@
 import contextlib
 import math
+import re
 import time
 
 import cv2
@@ -374,3 +375,75 @@ def process_mask(protos, masks_in, bboxes, shape, upsample=False):
     if upsample:
         masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0]  # CHW
     return masks.gt_(0.5)
+
+
+def process_mask_native(protos, masks_in, bboxes, shape):
+    """
+    Crop after upsample.
+    protos: [mask_dim, mask_h, mask_w]
+    masks_in: [n, mask_dim], n is number of masks after nms
+    bboxes: [n, 4], n is number of masks after nms
+    shape: input_image_size, (h, w)
+    return: h, w, n
+    """
+    c, mh, mw = protos.shape  # CHW
+    masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
+    gain = min(mh / shape[0], mw / shape[1])  # gain  = old / new
+    pad = (mw - shape[1] * gain) / 2, (mh - shape[0] * gain) / 2  # wh padding
+    top, left = int(pad[1]), int(pad[0])  # y, x
+    bottom, right = int(mh - pad[1]), int(mw - pad[0])
+    masks = masks[:, top:bottom, left:right]
+
+    masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0]  # CHW
+    masks = crop_mask(masks, bboxes)  # CHW
+    return masks.gt_(0.5)
+
+
+def scale_segments(img1_shape, segments, img0_shape, ratio_pad=None, normalize=False):
+    # Rescale coords (xyxy) from img1_shape to img0_shape
+    if ratio_pad is None:  # calculate from img0_shape
+        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
+        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
+    else:
+        gain = ratio_pad[0][0]
+        pad = ratio_pad[1]
+
+    segments[:, 0] -= pad[0]  # x padding
+    segments[:, 1] -= pad[1]  # y padding
+    segments /= gain
+    clip_segments(segments, img0_shape)
+    if normalize:
+        segments[:, 0] /= img0_shape[1]  # width
+        segments[:, 1] /= img0_shape[0]  # height
+    return segments
+
+
+def masks2segments(masks, strategy='largest'):
+    # Convert masks(n,160,160) into segments(n,xy)
+    segments = []
+    for x in masks.int().cpu().numpy().astype('uint8'):
+        c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]
+        if c:
+            if strategy == 'concat':  # concatenate all segments
+                c = np.concatenate([x.reshape(-1, 2) for x in c])
+            elif strategy == 'largest':  # select largest segment
+                c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2)
+        else:
+            c = np.zeros((0, 2))  # no segments found
+        segments.append(c.astype('float32'))
+    return segments
+
+
+def clip_segments(segments, shape):
+    # Clip segments (xy1,xy2,...) to image shape (height, width)
+    if isinstance(segments, torch.Tensor):  # faster individually
+        segments[:, 0].clamp_(0, shape[1])  # x
+        segments[:, 1].clamp_(0, shape[0])  # y
+    else:  # np.array (faster grouped)
+        segments[:, 0] = segments[:, 0].clip(0, shape[1])  # x
+        segments[:, 1] = segments[:, 1].clip(0, shape[0])  # y
+
+
+def clean_str(s):
+    # Cleans a string by replacing special characters with underscore _
+    return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)