Update test.py for IoU in native image-space (#1439)

* Update test.py for IoU in native image-space

* remove redundant

* gn to device

* remove output scale_coords

* --img-size correction

* update

* native-space labels

* pred to predn

* remove clip_coords()

test.py

@@ -12,7 +12,7 @@ from tqdm import tqdm
 from models.experimental import attempt_load
 from utils.datasets import create_dataloader
 from utils.general import coco80_to_coco91_class, check_dataset, check_file, check_img_size, box_iou, \
-    non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, clip_coords, set_logging, increment_path
+    non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, set_logging, increment_path
 from utils.loss import compute_loss
 from utils.metrics import ap_per_class
 from utils.plots import plot_images, output_to_target
@@ -124,6 +124,7 @@ def test(data,
             labels = targets[targets[:, 0] == si, 1:]
             nl = len(labels)
             tcls = labels[:, 0].tolist() if nl else []  # target class
+            path = Path(paths[si])
             seen += 1
 
             if len(pred) == 0:
@@ -131,13 +132,14 @@ def test(data,
                     stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
                 continue
 
+            # Predictions
+            predn = pred.clone()
+            scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1])  # native-space pred
+
             # Append to text file
-            path = Path(paths[si])
             if save_txt:
                 gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]]  # normalization gain whwh
-                x = pred.clone()
-                x[:, :4] = scale_coords(img[si].shape[1:], x[:, :4], shapes[si][0], shapes[si][1])  # to original
-                for *xyxy, conf, cls in x:
+                for *xyxy, conf, cls in predn.tolist():
                     xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                     line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
                     with open(save_dir / 'labels' / (path.stem + '.txt'), 'a') as f:
@@ -150,19 +152,14 @@ def test(data,
                              "box_caption": "%s %.3f" % (names[cls], conf),
                              "scores": {"class_score": conf},
                              "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
-                boxes = {"predictions": {"box_data": box_data, "class_labels": names}}
+                boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space
                 wandb_images.append(wandb.Image(img[si], boxes=boxes, caption=path.name))
 
-            # Clip boxes to image bounds
-            clip_coords(pred, (height, width))
-
             # Append to pycocotools JSON dictionary
             if save_json:
                 # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
                 image_id = int(path.stem) if path.stem.isnumeric() else path.stem
-                box = pred[:, :4].clone()  # xyxy
-                scale_coords(img[si].shape[1:], box, shapes[si][0], shapes[si][1])  # to original shape
-                box = xyxy2xywh(box)  # xywh
+                box = xyxy2xywh(predn[:, :4])  # xywh
                 box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
                 for p, b in zip(pred.tolist(), box.tolist()):
                     jdict.append({'image_id': image_id,
@@ -178,6 +175,7 @@ def test(data,
 
                 # target boxes
                 tbox = xywh2xyxy(labels[:, 1:5]) * whwh
+                scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1])  # native-space labels
 
                 # Per target class
                 for cls in torch.unique(tcls_tensor):
@@ -187,7 +185,7 @@ def test(data,
                     # Search for detections
                     if pi.shape[0]:
                         # Prediction to target ious
-                        ious, i = box_iou(pred[pi, :4], tbox[ti]).max(1)  # best ious, indices
+                        ious, i = box_iou(predn[pi, :4], tbox[ti]).max(1)  # best ious, indices
 
                         # Append detections
                         detected_set = set()