General ultralytics==8.0.6 updates (#351)

Co-authored-by: Dzmitry Plashchynski <plashchynski@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

ultralytics/yolo/v8/classify/train.py

@@ -113,11 +113,10 @@ class ClassificationTrainer(BaseTrainer):
         """
         # Not needed for classification but necessary for segmentation & detection
         keys = [f"{prefix}/{x}" for x in self.loss_names]
-        if loss_items is not None:
-            loss_items = [round(float(loss_items), 5)]
-            return dict(zip(keys, loss_items))
-        else:
+        if loss_items is None:
             return keys
+        loss_items = [round(float(loss_items), 5)]
+        return dict(zip(keys, loss_items))
 
     def resume_training(self, ckpt):
         pass

ultralytics/yolo/v8/detect/train.py

@@ -48,14 +48,14 @@ class DetectionTrainer(BaseTrainer):
         return batch
 
     def set_model_attributes(self):
-        nl = de_parallel(self.model).model[-1].nl  # number of detection layers (to scale hyps)
-        self.args.box *= 3 / nl  # scale to layers
+        # nl = de_parallel(self.model).model[-1].nl  # number of detection layers (to scale hyps)
+        # self.args.box *= 3 / nl  # scale to layers
         # self.args.cls *= self.data["nc"] / 80 * 3 / nl  # scale to classes and layers
-        self.args.cls *= (self.args.imgsz / 640) ** 2 * 3 / nl  # scale to image size and layers
+        # self.args.cls *= (self.args.imgsz / 640) ** 2 * 3 / nl  # scale to image size and layers
         self.model.nc = self.data["nc"]  # attach number of classes to model
+        self.model.names = self.data["names"]  # attach class names to model
         self.model.args = self.args  # attach hyperparameters to model
         # TODO: self.model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc
-        self.model.names = self.data["names"]
 
     def get_model(self, cfg=None, weights=None, verbose=True):
         model = DetectionModel(cfg, ch=3, nc=self.data["nc"], verbose=verbose)

ultralytics/yolo/v8/segment/predict.py

@@ -6,8 +6,7 @@ import torch
 from ultralytics.yolo.utils import DEFAULT_CONFIG, ROOT, ops
 from ultralytics.yolo.utils.checks import check_imgsz
 from ultralytics.yolo.utils.plotting import colors, save_one_box
-
-from ..detect.predict import DetectionPredictor
+from ultralytics.yolo.v8.detect.predict import DetectionPredictor
 
 
 class SegmentationPredictor(DetectionPredictor):

ultralytics/yolo/v8/segment/train.py

@@ -13,14 +13,15 @@ from ultralytics.yolo.utils.ops import crop_mask, xyxy2xywh
 from ultralytics.yolo.utils.plotting import plot_images, plot_results
 from ultralytics.yolo.utils.tal import make_anchors
 from ultralytics.yolo.utils.torch_utils import de_parallel
-
-from ..detect.train import Loss
+from ultralytics.yolo.v8.detect.train import Loss
 
 
 # BaseTrainer python usage
 class SegmentationTrainer(v8.detect.DetectionTrainer):
 
-    def __init__(self, config=DEFAULT_CONFIG, overrides={}):
+    def __init__(self, config=DEFAULT_CONFIG, overrides=None):
+        if overrides is None:
+            overrides = {}
         overrides["task"] = "segment"
         super().__init__(config, overrides)
 

ultralytics/yolo/v8/segment/val.py

@@ -13,8 +13,7 @@ from ultralytics.yolo.utils import DEFAULT_CONFIG, NUM_THREADS, ops
 from ultralytics.yolo.utils.checks import check_requirements
 from ultralytics.yolo.utils.metrics import ConfusionMatrix, SegmentMetrics, box_iou, mask_iou
 from ultralytics.yolo.utils.plotting import output_to_target, plot_images
-
-from ..detect import DetectionValidator
+from ultralytics.yolo.v8.detect import DetectionValidator
 
 
 class SegmentationValidator(DetectionValidator):