dataset padding mode

test.py

@@ -56,8 +56,14 @@ def test(data,
 
     # Dataloader
     if dataloader is None:
+        fast |= conf_thres > 0.001  # enable fast mode
         path = data['test'] if opt.task == 'test' else data['val']  # path to val/test images
-        dataset = LoadImagesAndLabels(path, imgsz, batch_size, rect=True, single_cls=opt.single_cls)
+        dataset = LoadImagesAndLabels(path,
+                                      imgsz,
+                                      batch_size,
+                                      rect=True,  # rectangular inference
+                                      single_cls=opt.single_cls,  # single class mode
+                                      pad=0.0 if fast else 0.5)  # padding
         batch_size = min(batch_size, len(dataset))
         dataloader = DataLoader(dataset,
                                 batch_size=batch_size,

utils/datasets.py

@@ -257,7 +257,7 @@ class LoadStreams:  # multiple IP or RTSP cameras
 
 class LoadImagesAndLabels(Dataset):  # for training/testing
     def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
-                 cache_images=False, single_cls=False):
+                 cache_images=False, single_cls=False, pad=0.0):
         try:
             path = str(Path(path))  # os-agnostic
             parent = str(Path(path).parent) + os.sep
@@ -322,7 +322,7 @@ class LoadImagesAndLabels(Dataset):  # for training/testing
                 elif mini > 1:
                     shapes[i] = [1, 1 / mini]
 
-            self.batch_shapes = np.round(np.array(shapes) * img_size / 32. + 1.).astype(np.int) * 32
+            self.batch_shapes = np.ceil(np.array(shapes) * img_size / 32. + pad).astype(np.int) * 32
 
         # Cache labels
         self.imgs = [None] * n