Merge branch 'master' into advanced_logging

utils/datasets.py

@@ -48,7 +48,7 @@ def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=Fa
                                   rect=rect,  # rectangular training
                                   cache_images=cache,
                                   single_cls=opt.single_cls,
-                                  stride=stride,
+                                  stride=int(stride),
                                   pad=pad)
 
     batch_size = min(batch_size, len(dataset))
@@ -679,8 +679,8 @@ def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scale
         dw, dh = np.mod(dw, 64), np.mod(dh, 64)  # wh padding
     elif scaleFill:  # stretch
         dw, dh = 0.0, 0.0
-        new_unpad = new_shape
-        ratio = new_shape[0] / shape[1], new_shape[1] / shape[0]  # width, height ratios
+        new_unpad = (new_shape[1], new_shape[0])
+        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios
 
     dw /= 2  # divide padding into 2 sides
     dh /= 2

utils/utils.py

@@ -179,7 +179,7 @@ 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:  # calculate from img0_shape
-        gain = max(img1_shape) / max(img0_shape)  # gain  = old / new
+        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]