ultralytics 8.1.43 40% faster ultralytics imports (#9547)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>

ultralytics/models/fastsam/prompt.py

@@ -4,7 +4,6 @@ import os
 from pathlib import Path
 
 import cv2
-import matplotlib.pyplot as plt
 import numpy as np
 import torch
 from PIL import Image
@@ -118,6 +117,8 @@ class FastSAMPrompt:
             retina (bool, optional): Whether to use retina mask. Defaults to False.
             with_contours (bool, optional): Whether to plot contours. Defaults to True.
         """
+        import matplotlib.pyplot as plt
+
         pbar = TQDM(annotations, total=len(annotations))
         for ann in pbar:
             result_name = os.path.basename(ann.path)
@@ -202,6 +203,8 @@ class FastSAMPrompt:
             target_height (int, optional): Target height for resizing. Defaults to 960.
             target_width (int, optional): Target width for resizing. Defaults to 960.
         """
+        import matplotlib.pyplot as plt
+
         n, h, w = annotation.shape  # batch, height, width
 
         areas = np.sum(annotation, axis=(1, 2))

ultralytics/models/sam/predict.py

@@ -11,7 +11,6 @@ segmentation tasks.
 import numpy as np
 import torch
 import torch.nn.functional as F
-import torchvision
 
 from ultralytics.data.augment import LetterBox
 from ultralytics.engine.predictor import BasePredictor
@@ -246,6 +245,8 @@ class Predictor(BasePredictor):
         Returns:
             (tuple): A tuple containing segmented masks, confidence scores, and bounding boxes.
         """
+        import torchvision  # scope for faster 'import ultralytics'
+
         self.segment_all = True
         ih, iw = im.shape[2:]
         crop_regions, layer_idxs = generate_crop_boxes((ih, iw), crop_n_layers, crop_overlap_ratio)
@@ -449,6 +450,8 @@ class Predictor(BasePredictor):
                 - new_masks (torch.Tensor): The processed masks with small regions removed. Shape is (N, H, W).
                 - keep (List[int]): The indices of the remaining masks post-NMS, which can be used to filter the boxes.
         """
+        import torchvision  # scope for faster 'import ultralytics'
+
         if len(masks) == 0:
             return masks
 

ultralytics/models/yolo/classify/train.py

@@ -1,7 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
 import torch
-import torchvision
 
 from ultralytics.data import ClassificationDataset, build_dataloader
 from ultralytics.engine.trainer import BaseTrainer
@@ -59,6 +58,8 @@ class ClassificationTrainer(BaseTrainer):
 
     def setup_model(self):
         """Load, create or download model for any task."""
+        import torchvision  # scope for faster 'import ultralytics'
+
         if isinstance(self.model, torch.nn.Module):  # if model is loaded beforehand. No setup needed
             return