updates

test.py

@@ -101,7 +101,7 @@ def test(cfg,
                 # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
                 image_id = int(Path(paths[si]).stem.split('_')[-1])
                 box = pred[:, :4].clone()  # xyxy
-                scale_coords(imgs[si].shape[1:], box, shapes[si])  # to original shape
+                scale_coords(imgs[si].shape[1:], box, shapes[si][0], shapes[si][1])  # to original shape
                 box = xyxy2xywh(box)  # xywh
                 box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
                 for di, d in enumerate(pred):

utils/datasets.py

@@ -416,6 +416,7 @@ class LoadImagesAndLabels(Dataset):  # for training/testing
             # Load mosaic
             img, labels = load_mosaic(self, index)
             h, w = img.shape[:2]
+            ratio, pad = None, None
 
         else:
             # Load image
@@ -492,14 +493,14 @@ class LoadImagesAndLabels(Dataset):  # for training/testing
         img = np.ascontiguousarray(img, dtype=np.float32)  # uint8 to float32
         img /= 255.0  # 0 - 255 to 0.0 - 1.0
 
-        return torch.from_numpy(img), labels_out, img_path, (h, w)
+        return torch.from_numpy(img), labels_out, img_path, ((h, w), (ratio, pad))
 
     @staticmethod
     def collate_fn(batch):
-        img, label, path, hw = list(zip(*batch))  # transposed
+        img, label, path, shapes = list(zip(*batch))  # transposed
         for i, l in enumerate(label):
             l[:, 0] = i  # add target image index for build_targets()
-        return torch.stack(img, 0), torch.cat(label, 0), path, hw
+        return torch.stack(img, 0), torch.cat(label, 0), path, shapes
 
 
 def load_image(self, index):

utils/utils.py

@@ -126,7 +126,7 @@ def xywh2xyxy(x):
 
 def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
     # Rescale coords (xyxy) from img1_shape to img0_shape
-    if ratio_pad is None:  # not supplied, calculate
+    if ratio_pad is None:  # calculate from img0_shape
         gain = max(img1_shape) / max(img0_shape)  # gain  = old / new
         pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
     else: