⚡️ [Update] using anchor if is given, or autoanchor

yolo/config/model/v9-c.yaml

@@ -1,5 +1,6 @@
 anchor:
   reg_max: 16
+  anchors: [8, 16, 32]
 
 model:
   backbone:

yolo/tools/solver.py

@@ -35,7 +35,7 @@ class ModelTrainer:
         self.num_epochs = cfg.task.epoch
 
         self.validation_dataloader = create_dataloader(cfg.task.validation.data, cfg.dataset, cfg.task.validation.task)
-        self.validator = ModelValidator(cfg.task.validation, model, vec2box, progress, device, self.progress)
+        self.validator = ModelValidator(cfg.task.validation, model, vec2box, progress, device)
 
         if getattr(train_cfg.ema, "enabled", False):
             self.ema = ExponentialMovingAverage(model, decay=train_cfg.ema.decay)

yolo/utils/bounding_box_utils.py

@@ -264,14 +264,17 @@ class BoxMatcher:
 
 
 class Vec2Box:
-    def __init__(self, model, image_size, device):
-        logger.info("🧸 Make a dummy test for auto-anchor size")
-        dummy_input = torch.zeros(1, 3, *image_size).to(device)
-        dummy_output = model(dummy_input)
-        anchors_num = []
-        for predict_head in dummy_output["Main"]:
-            _, _, *anchor_num = predict_head[2].shape
-            anchors_num.append(anchor_num)
+    def __init__(self, model, image_size, device, anchors: list = None):
+        if anchors is None:
+            logger.info("🧸 Found no anchor, Make a dummy test for auto-anchor size")
+            dummy_input = torch.zeros(1, 3, *image_size).to(device)
+            dummy_output = model(dummy_input)
+            anchors_num = []
+            for predict_head in dummy_output["Main"]:
+                _, _, *anchor_num = predict_head[2].shape
+                anchors_num.append(anchor_num)
+        else:
+            anchors_num = [[image_size[0] / anchor, image_size[0] / anchor] for anchor in anchors]
         anchor_grid, scaler = generate_anchors(image_size, anchors_num)
         self.anchor_grid, self.scaler = anchor_grid.to(device), scaler.to(device)
         self.anchor_norm = (anchor_grid / scaler[:, None])[None].to(device)