updates

models.py

@@ -253,7 +253,7 @@ def load_darknet_weights(self, weights, cutoff=-1):
     if not os.path.isfile(weights):
         try:
             url = 'https://pjreddie.com/media/files/' + weights_file
-            print('Downloading ' + url + ' to ' + weights)
+            print('Downloading ' + url)
             os.system('curl ' + url + ' -o ' + weights)
         except IOError:
             print(weights + ' not found.\nTry https://drive.google.com/drive/folders/1uxgUBemJVw9wZsdpboYbzUN4bcRhsuAI')

test.py

@@ -87,9 +87,6 @@ def test(cfg,
                     stats.append(([], torch.Tensor(), torch.Tensor(), tcls))
                 continue
 
-            # Clip boxes to image bounds
-            clip_coords(pred, (height, width))
-
             # Append to text file
             # with open('test.txt', 'a') as file:
             #    [file.write('%11.5g' * 7 % tuple(x) + '\n') for x in pred]
@@ -99,7 +96,7 @@ 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
-                box = scale_coords(imgs[si].shape[1:], box, shapes[si])  # to original shape
+                scale_coords(imgs[si].shape[1:], box, shapes[si])  # to original shape
                 box = xyxy2xywh(box)  # xywh
                 box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
                 for di, d in enumerate(pred):
@@ -108,6 +105,9 @@ def test(cfg,
                                   'bbox': [float3(x) for x in box[di]],
                                   'score': float(d[4])})
 
+            # Clip boxes to image bounds
+            clip_coords(pred, (height, width))
+
             # Assign all predictions as incorrect
             correct = [0] * len(pred)
             if nl:

utils/datasets.py

@@ -152,7 +152,7 @@ class LoadWebcam:  # for inference
 
 
 class LoadImagesAndLabels(Dataset):  # for training/testing
-    def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, rect=True, image_weights=False):
+    def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False):
         with open(path, 'r') as f:
             img_files = f.read().splitlines()
             self.img_files = [x for x in img_files if os.path.splitext(x)[-1].lower() in img_formats]
@@ -280,7 +280,7 @@ class LoadImagesAndLabels(Dataset):  # for training/testing
             img = cv2.imread(img_path)  # BGR
             assert img is not None, 'File Not Found ' + img_path
             r = self.img_size / max(img.shape)  # size ratio
-            if r < 1:  # downsize if target shape is smaller
+            if self.augment and r < 1:  # if training (NOT testing), downsize to inference shape
                 h, w, _ = img.shape
                 img = cv2.resize(img, (int(w * r), int(h * r)), interpolation=cv2.INTER_AREA)