Lightweight YOLO-World tests (#10133)

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

tests/test_python.py

@@ -640,26 +640,31 @@ def test_yolo_world():
     model.set_classes(["tree", "window"])
     model(ASSETS / "bus.jpg", conf=0.01)
 
-    # Training from yaml
-    model = YOLO("yolov8s-worldv2.yaml")  # no YOLOv8n-world model yet
-    model.train(data="coco8.yaml", epochs=2, imgsz=32, cache="disk", batch=-1, close_mosaic=1, name="yolo-world")
-
     model = YOLO("yolov8s-worldv2.pt")  # no YOLOv8n-world model yet
-    # val
-    model.val(data="coco8.yaml", imgsz=32, save_txt=True, save_json=True)
-    # Training from pretrain
-    model.train(data="coco8.yaml", epochs=2, imgsz=32, cache="disk", batch=-1, close_mosaic=1, name="yolo-world")
+    # Training from pretrain, evaluation process is included at the final stage of training.
+    # Use dota8.yaml which has less categories to reduce the inference time of CLIP model
+    model.train(
+        data="dota8.yaml",
+        epochs=1,
+        imgsz=32,
+        cache="disk",
+        batch=4,
+        close_mosaic=1,
+        name="yolo-world",
+        save_txt=True,
+        save_json=True,
+    )
 
     # test WorWorldTrainerFromScratch
     from ultralytics.models.yolo.world.train_world import WorldTrainerFromScratch
 
     model = YOLO("yolov8s-worldv2.yaml")  # no YOLOv8n-world model yet
     model.train(
-        data={"train": {"yolo_data": ["coco8.yaml"]}, "val": {"yolo_data": ["coco8.yaml"]}},
-        epochs=2,
+        data={"train": {"yolo_data": ["dota8.yaml"]}, "val": {"yolo_data": ["dota8.yaml"]}},
+        epochs=1,
         imgsz=32,
         cache="disk",
-        batch=-1,
+        batch=4,
         close_mosaic=1,
         name="yolo-world",
         trainer=WorldTrainerFromScratch,