diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py
index 7eeb1e9..825e90c 100644
--- a/ultralytics/__init__.py
+++ b/ultralytics/__init__.py
@@ -1 +1,5 @@
 __version__ = "8.0.0.dev0"
+
+from ultralytics.yolo.engine.model import YOLO
+
+__all__ = ["__version__", "YOLO"]  # allow simpler import
diff --git a/ultralytics/nn/__init__.py b/ultralytics/nn/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/ultralytics/yolo/utils/modeling/autobackend.py b/ultralytics/nn/autobackend.py
similarity index 99%
rename from ultralytics/yolo/utils/modeling/autobackend.py
rename to ultralytics/nn/autobackend.py
index d5366a5..b635d00 100644
--- a/ultralytics/yolo/utils/modeling/autobackend.py
+++ b/ultralytics/nn/autobackend.py
@@ -13,6 +13,7 @@ from PIL import Image
 from ultralytics.yolo.utils import LOGGER, ROOT
 from ultralytics.yolo.utils.checks import check_requirements, check_suffix, check_version
 from ultralytics.yolo.utils.downloads import attempt_download, is_url
+from ultralytics.yolo.utils.files import yaml_load
 from ultralytics.yolo.utils.ops import xywh2xyxy
 
 
@@ -32,8 +33,6 @@ class AutoBackend(nn.Module):
         #   TensorFlow Lite:                *.tflite
         #   TensorFlow Edge TPU:            *_edgetpu.tflite
         #   PaddlePaddle:                   *_paddle_model
-        from ultralytics.yolo.utils.files import yaml_load
-        from ultralytics.yolo.utils.modeling import attempt_load_weights
 
         super().__init__()
         w = str(weights[0] if isinstance(weights, list) else weights)
@@ -54,6 +53,7 @@ class AutoBackend(nn.Module):
             model.half() if fp16 else model.float()
             self.model = model  # explicitly assign for to(), cpu(), cuda(), half()
         elif pt:  # PyTorch
+            from ultralytics.nn.tasks import attempt_load_weights
             model = attempt_load_weights(weights if isinstance(weights, list) else w,
                                          device=device,
                                          inplace=True,
@@ -89,7 +89,7 @@ class AutoBackend(nn.Module):
         elif xml:  # OpenVINO
             LOGGER.info(f'Loading {w} for OpenVINO inference...')
             check_requirements('openvino')  # requires openvino-dev: https://pypi.org/project/openvino-dev/
-            from openvino.runtime import Core, Layout, get_batch
+            from openvino.runtime import Core, Layout, get_batch  # noqa
             ie = Core()
             if not Path(w).is_file():  # if not *.xml
                 w = next(Path(w).glob('*.xml'))  # get *.xml file from *_openvino_model dir
diff --git a/ultralytics/yolo/utils/modeling/modules.py b/ultralytics/nn/modules.py
similarity index 99%
rename from ultralytics/yolo/utils/modeling/modules.py
rename to ultralytics/nn/modules.py
index 06270a6..c72f38b 100644
--- a/ultralytics/yolo/utils/modeling/modules.py
+++ b/ultralytics/nn/modules.py
@@ -17,6 +17,7 @@ import torch.nn as nn
 from PIL import Image, ImageOps
 from torch.cuda import amp
 
+from ultralytics.nn.autobackend import AutoBackend
 from ultralytics.yolo.data.augment import LetterBox
 from ultralytics.yolo.utils import LOGGER, colorstr
 from ultralytics.yolo.utils.files import increment_path
@@ -25,8 +26,6 @@ from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box
 from ultralytics.yolo.utils.tal import dist2bbox, make_anchors
 from ultralytics.yolo.utils.torch_utils import copy_attr, smart_inference_mode
 
-from .autobackend import AutoBackend
-
 # from utils.plots import feature_visualization TODO
 
 
diff --git a/ultralytics/yolo/utils/modeling/tasks.py b/ultralytics/nn/tasks.py
similarity index 62%
rename from ultralytics/yolo/utils/modeling/tasks.py
rename to ultralytics/nn/tasks.py
index 59e502c..0d259e6 100644
--- a/ultralytics/yolo/utils/modeling/tasks.py
+++ b/ultralytics/nn/tasks.py
@@ -1,11 +1,19 @@
+import contextlib
 from copy import deepcopy
+from pathlib import Path
 
 import thop
+import torch
+import torch.nn as nn
+import torchvision
+import yaml
 
-from ultralytics.yolo.utils.modeling import parse_model
-from ultralytics.yolo.utils.modeling.modules import *
-from ultralytics.yolo.utils.torch_utils import (fuse_conv_and_bn, initialize_weights, intersect_state_dicts, model_info,
-                                                scale_img, time_sync)
+from ultralytics.nn.modules import (C1, C2, C3, C3TR, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x, Classify,
+                                    Concat, Conv, ConvTranspose, Detect, DWConv, DWConvTranspose2d, Ensemble, Focus,
+                                    GhostBottleneck, GhostConv, Segment)
+from ultralytics.yolo.utils import LOGGER, colorstr
+from ultralytics.yolo.utils.torch_utils import (fuse_conv_and_bn, initialize_weights, intersect_state_dicts,
+                                                make_divisible, model_info, scale_img, time_sync)
 
 
 class BaseModel(nn.Module):
@@ -75,7 +83,6 @@ class DetectionModel(BaseModel):
         if isinstance(cfg, dict):
             self.yaml = cfg  # model dict
         else:  # is *.yaml
-            import yaml  # for torch hub
             self.yaml_file = Path(cfg).name
             with open(cfg, encoding='ascii', errors='ignore') as f:
                 self.yaml = yaml.safe_load(f)  # model dict
@@ -166,6 +173,7 @@ class ClassificationModel(BaseModel):
 
     def _from_detection_model(self, model, nc=1000, cutoff=10):
         # Create a YOLOv5 classification model from a YOLOv5 detection model
+        from ultralytics.nn.autobackend import AutoBackend
         if isinstance(model, AutoBackend):
             model = model.model  # unwrap DetectMultiBackend
         model.model = model.model[:cutoff]  # backbone
@@ -192,7 +200,6 @@ class ClassificationModel(BaseModel):
     @staticmethod
     def reshape_outputs(model, nc):
         # Update a TorchVision classification model to class count 'n' if required
-        from ultralytics.yolo.utils.modeling.modules import Classify
         name, m = list((model.model if hasattr(model, 'model') else model).named_children())[-1]  # last module
         if isinstance(m, Classify):  # YOLO Classify() head
             if m.linear.out_features != nc:
@@ -210,3 +217,110 @@ class ClassificationModel(BaseModel):
                 i = types.index(nn.Conv2d)  # nn.Conv2d index
                 if m[i].out_channels != nc:
                     m[i] = nn.Conv2d(m[i].in_channels, nc, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None)
+
+
+# Functions ------------------------------------------------------------------------------------------------------------
+
+
+def attempt_load_weights(weights, device=None, inplace=True, fuse=True):
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    from ultralytics.yolo.utils.downloads import attempt_download
+
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        ckpt = torch.load(attempt_download(w), map_location='cpu')  # load
+        ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float()  # FP32 model
+
+        # Model compatibility updates
+        if not hasattr(ckpt, 'stride'):
+            ckpt.stride = torch.tensor([32.])
+        if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)):
+            ckpt.names = dict(enumerate(ckpt.names))  # convert to dict
+
+        model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval())  # model in eval mode
+
+    # Module compatibility updates
+    for m in model.modules():
+        t = type(m)
+        if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Segment):
+            m.inplace = inplace  # torch 1.7.0 compatibility
+        elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
+            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
+
+    # Return model
+    if len(model) == 1:
+        return model[-1]
+
+    # Return detection ensemble
+    print(f'Ensemble created with {weights}\n')
+    for k in 'names', 'nc', 'yaml':
+        setattr(model, k, getattr(model[0], k))
+    model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
+    assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}'
+    return model
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    # Parse a YOLOv5 model.yaml dictionary
+    LOGGER.info(f"\n{'':>3}{'from':>20}{'n':>3}{'params':>10}  {'module':<45}{'arguments':<30}")
+    nc, gd, gw, act = d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
+    if act:
+        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
+        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
+    no = nc + 4  # number of outputs = classes + box
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            with contextlib.suppress(NameError):
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+
+        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in {
+                Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus, BottleneckCSP,
+                C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
+            c1, c2 = ch[f], args[0]
+            if c2 != no:  # if not output
+                c2 = make_divisible(c2 * gw, 8)
+
+            args = [c1, c2, *args[1:]]
+            if m in {BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, C3x}:
+                args.insert(2, n)  # number of repeats
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum(ch[x] for x in f)
+        # TODO: channel, gw, gd
+        elif m in {Detect, Segment}:
+            args.append([ch[x] for x in f])
+            if m is Segment:
+                args[3] = make_divisible(args[3] * gw, 8)
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        m.np = sum(x.numel() for x in m_.parameters())  # number params
+        m_.i, m_.f, m_.type = i, f, t  # attach index, 'from' index, type
+        LOGGER.info(f'{i:>3}{str(f):>20}{n_:>3}{m.np:10.0f}  {t:<45}{str(args):<30}')  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        if i == 0:
+            ch = []
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+def get_model(model='s.pt', pretrained=True):
+    # Load a YOLO model locally, from torchvision, or from Ultralytics assets
+    if model.endswith(".pt"):
+        model = model.split(".")[0]
+
+    if Path(f"{model}.pt").is_file():  # local file
+        return attempt_load_weights(f"{model}.pt", device='cpu')
+    elif model in torchvision.models.__dict__:  # TorchVision models i.e. resnet50, efficientnet_b0
+        return torchvision.models.__dict__[model](weights='IMAGENET1K_V1' if pretrained else None)
+    else:  # Ultralytics assets
+        return attempt_load_weights(f"{model}.pt", device='cpu')
diff --git a/ultralytics/tests/data/dataloader/yolodetection.py b/ultralytics/tests/data/dataloader/yolodetection.py
index 515633f..e30ea61 100644
--- a/ultralytics/tests/data/dataloader/yolodetection.py
+++ b/ultralytics/tests/data/dataloader/yolodetection.py
@@ -1,6 +1,5 @@
 import cv2
 import hydra
-import numpy as np
 
 from ultralytics.yolo.data import build_dataloader
 from ultralytics.yolo.utils import ROOT
diff --git a/ultralytics/tests/functional/test_loaders.py b/ultralytics/tests/functional/test_loaders.py
index 6a80e72..ea481c3 100644
--- a/ultralytics/tests/functional/test_loaders.py
+++ b/ultralytics/tests/functional/test_loaders.py
@@ -1,5 +1,5 @@
+from ultralytics.nn.tasks import DetectionModel
 from ultralytics.yolo.utils.checks import check_yaml
-from ultralytics.yolo.utils.modeling.tasks import DetectionModel
 
 
 def test_model_parser():
diff --git a/ultralytics/yolo/__init__.py b/ultralytics/yolo/__init__.py
index 37f36e0..e69de29 100644
--- a/ultralytics/yolo/__init__.py
+++ b/ultralytics/yolo/__init__.py
@@ -1,7 +0,0 @@
-from ultralytics.yolo import v8
-
-from .engine.model import YOLO
-from .engine.trainer import BaseTrainer
-from .engine.validator import BaseValidator
-
-__all__ = ["BaseTrainer", "BaseValidator", "YOLO"]  # allow simpler import
diff --git a/ultralytics/yolo/engine/model.py b/ultralytics/yolo/engine/model.py
index ba72812..1ecee36 100644
--- a/ultralytics/yolo/engine/model.py
+++ b/ultralytics/yolo/engine/model.py
@@ -2,14 +2,13 @@ import torch
 import yaml
 
 from ultralytics import yolo  # noqa required for python usage
+from ultralytics.nn.tasks import ClassificationModel, DetectionModel, SegmentationModel, attempt_load_weights
 # from ultralytics.yolo.data.utils import check_dataset, check_dataset_yaml
 from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG
 from ultralytics.yolo.utils import LOGGER
 from ultralytics.yolo.utils.checks import check_yaml
 from ultralytics.yolo.utils.configs import get_config
 from ultralytics.yolo.utils.files import yaml_load
-from ultralytics.yolo.utils.modeling import attempt_load_weights
-from ultralytics.yolo.utils.modeling.tasks import ClassificationModel, DetectionModel, SegmentationModel
 from ultralytics.yolo.utils.torch_utils import smart_inference_mode
 
 # map head: [model, trainer, validator, predictor]
diff --git a/ultralytics/yolo/engine/predictor.py b/ultralytics/yolo/engine/predictor.py
index 3e894e6..21c55d6 100644
--- a/ultralytics/yolo/engine/predictor.py
+++ b/ultralytics/yolo/engine/predictor.py
@@ -30,13 +30,13 @@ from pathlib import Path
 
 import cv2
 
+from ultralytics.nn.autobackend import AutoBackend
 from ultralytics.yolo.data.dataloaders.stream_loaders import LoadImages, LoadScreenshots, LoadStreams
 from ultralytics.yolo.data.utils import IMG_FORMATS, VID_FORMATS, check_dataset, check_dataset_yaml
 from ultralytics.yolo.utils import LOGGER, ROOT, colorstr, ops
 from ultralytics.yolo.utils.checks import check_file, check_imshow
 from ultralytics.yolo.utils.configs import get_config
 from ultralytics.yolo.utils.files import increment_path
-from ultralytics.yolo.utils.modeling.autobackend import AutoBackend
 from ultralytics.yolo.utils.torch_utils import check_imgsz, select_device, smart_inference_mode
 
 DEFAULT_CONFIG = ROOT / "yolo/utils/configs/default.yaml"
@@ -95,7 +95,7 @@ class BasePredictor:
         device = select_device(self.args.device)
         model = model or self.args.model
         self.args.half &= device.type != 'cpu'  # half precision only supported on CUDA
-        model = AutoBackend(model, device=device, dnn=self.args.dnn, fp16=self.args.half)  # NOTE: not passing data
+        model = AutoBackend(model, device=device, dnn=self.args.dnn, fp16=self.args.half)
         stride, pt = model.stride, model.pt
         imgsz = check_imgsz(self.args.imgsz, s=stride)  # check image size
 
diff --git a/ultralytics/yolo/engine/validator.py b/ultralytics/yolo/engine/validator.py
index 03bf951..4c1c09b 100644
--- a/ultralytics/yolo/engine/validator.py
+++ b/ultralytics/yolo/engine/validator.py
@@ -4,11 +4,11 @@ import torch
 from omegaconf import OmegaConf
 from tqdm import tqdm
 
+from ultralytics.nn.autobackend import AutoBackend
 from ultralytics.yolo.data.utils import check_dataset, check_dataset_yaml
 from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG
 from ultralytics.yolo.utils import LOGGER, TQDM_BAR_FORMAT
 from ultralytics.yolo.utils.files import increment_path
-from ultralytics.yolo.utils.modeling.autobackend import AutoBackend
 from ultralytics.yolo.utils.ops import Profile
 from ultralytics.yolo.utils.torch_utils import check_imgsz, de_parallel, select_device, smart_inference_mode
 
diff --git a/ultralytics/yolo/utils/modeling/__init__.py b/ultralytics/yolo/utils/modeling/__init__.py
deleted file mode 100644
index 9cedfa2..0000000
--- a/ultralytics/yolo/utils/modeling/__init__.py
+++ /dev/null
@@ -1,109 +0,0 @@
-import contextlib
-
-import torchvision
-
-from ultralytics.yolo.utils.downloads import attempt_download
-from ultralytics.yolo.utils.modeling.modules import *
-
-
-def attempt_load_weights(weights, device=None, inplace=True, fuse=True):
-    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
-
-    model = Ensemble()
-    for w in weights if isinstance(weights, list) else [weights]:
-        ckpt = torch.load(attempt_download(w), map_location='cpu')  # load
-        ckpt = (ckpt.get('ema') or ckpt['model']).to(device).float()  # FP32 model
-
-        # Model compatibility updates
-        if not hasattr(ckpt, 'stride'):
-            ckpt.stride = torch.tensor([32.])
-        if hasattr(ckpt, 'names') and isinstance(ckpt.names, (list, tuple)):
-            ckpt.names = dict(enumerate(ckpt.names))  # convert to dict
-
-        model.append(ckpt.fuse().eval() if fuse and hasattr(ckpt, 'fuse') else ckpt.eval())  # model in eval mode
-
-    # Module compatibility updates
-    for m in model.modules():
-        t = type(m)
-        if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Segment):
-            m.inplace = inplace  # torch 1.7.0 compatibility
-        elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
-            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
-
-    # Return model
-    if len(model) == 1:
-        return model[-1]
-
-    # Return detection ensemble
-    print(f'Ensemble created with {weights}\n')
-    for k in 'names', 'nc', 'yaml':
-        setattr(model, k, getattr(model[0], k))
-    model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride  # max stride
-    assert all(model[0].nc == m.nc for m in model), f'Models have different class counts: {[m.nc for m in model]}'
-    return model
-
-
-def parse_model(d, ch):  # model_dict, input_channels(3)
-    # Parse a YOLOv5 model.yaml dictionary
-    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<50}{'arguments':<30}")
-    nc, gd, gw, act = d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
-    if act:
-        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
-        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
-    no = nc + 4  # number of outputs = classes + box
-
-    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
-    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
-        m = eval(m) if isinstance(m, str) else m  # eval strings
-        for j, a in enumerate(args):
-            with contextlib.suppress(NameError):
-                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
-
-        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
-        if m in {
-                Conv, ConvTranspose, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, Focus, BottleneckCSP,
-                C1, C2, C2f, C3, C3TR, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
-            c1, c2 = ch[f], args[0]
-            if c2 != no:  # if not output
-                c2 = make_divisible(c2 * gw, 8)
-
-            args = [c1, c2, *args[1:]]
-            if m in {BottleneckCSP, C1, C2, C2f, C3, C3TR, C3Ghost, C3x}:
-                args.insert(2, n)  # number of repeats
-                n = 1
-        elif m is nn.BatchNorm2d:
-            args = [ch[f]]
-        elif m is Concat:
-            c2 = sum(ch[x] for x in f)
-        # TODO: channel, gw, gd
-        elif m in {Detect, Segment}:
-            args.append([ch[x] for x in f])
-            if m is Segment:
-                args[3] = make_divisible(args[3] * gw, 8)
-        else:
-            c2 = ch[f]
-
-        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
-        t = str(m)[8:-2].replace('__main__.', '')  # module type
-        m.np = sum(x.numel() for x in m_.parameters())  # number params
-        m_.i, m_.f, m_.type = i, f, t  # attach index, 'from' index, type
-        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{m.np:10.0f}  {t:<50}{str(args):<30}')  # print
-        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
-        layers.append(m_)
-        if i == 0:
-            ch = []
-        ch.append(c2)
-    return nn.Sequential(*layers), sorted(save)
-
-
-def get_model(model='s.pt', pretrained=True):
-    # Load a YOLO model locally, from torchvision, or from Ultralytics assets
-    if model.endswith(".pt"):
-        model = model.split(".")[0]
-
-    if Path(f"{model}.pt").is_file():  # local file
-        return attempt_load_weights(f"{model}.pt", device='cpu')
-    elif model in torchvision.models.__dict__:  # TorchVision models i.e. resnet50, efficientnet_b0
-        return torchvision.models.__dict__[model](weights='IMAGENET1K_V1' if pretrained else None)
-    else:  # Ultralytics assets
-        return attempt_load_weights(f"{model}.pt", device='cpu')
diff --git a/ultralytics/yolo/v8/__init__.py b/ultralytics/yolo/v8/__init__.py
index 97834a1..8efc544 100644
--- a/ultralytics/yolo/v8/__init__.py
+++ b/ultralytics/yolo/v8/__init__.py
@@ -6,5 +6,4 @@ ROOT = Path(__file__).parents[0]  # yolov8 ROOT
 
 __all__ = ["classify", "segment", "detect"]
 
-# Patch hydra cli
-from ultralytics.yolo.utils.configs import hydra_patch
+from ultralytics.yolo.utils.configs import hydra_patch  # noqa (patch hydra cli)
diff --git a/ultralytics/yolo/v8/classify/predict.py b/ultralytics/yolo/v8/classify/predict.py
index 9f07b5a..9b6e112 100644
--- a/ultralytics/yolo/v8/classify/predict.py
+++ b/ultralytics/yolo/v8/classify/predict.py
@@ -3,8 +3,7 @@ import torch
 
 from ultralytics.yolo.engine.predictor import BasePredictor
 from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG
-from ultralytics.yolo.utils import ops
-from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box
+from ultralytics.yolo.utils.plotting import Annotator
 
 
 class ClassificationPredictor(BasePredictor):
diff --git a/ultralytics/yolo/v8/classify/train.py b/ultralytics/yolo/v8/classify/train.py
index 2b98de6..d78007f 100644
--- a/ultralytics/yolo/v8/classify/train.py
+++ b/ultralytics/yolo/v8/classify/train.py
@@ -1,11 +1,10 @@
 import hydra
 import torch
 
+from ultralytics.nn.tasks import ClassificationModel, get_model
 from ultralytics.yolo import v8
 from ultralytics.yolo.data import build_classification_dataloader
 from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG, BaseTrainer
-from ultralytics.yolo.utils.modeling import get_model
-from ultralytics.yolo.utils.modeling.tasks import ClassificationModel
 
 
 class ClassificationTrainer(BaseTrainer):
diff --git a/ultralytics/yolo/v8/detect/train.py b/ultralytics/yolo/v8/detect/train.py
index d7fd5a7..5a86904 100644
--- a/ultralytics/yolo/v8/detect/train.py
+++ b/ultralytics/yolo/v8/detect/train.py
@@ -2,6 +2,7 @@ import hydra
 import torch
 import torch.nn as nn
 
+from ultralytics.nn.tasks import DetectionModel
 from ultralytics.yolo import v8
 from ultralytics.yolo.data import build_dataloader
 from ultralytics.yolo.data.dataloaders.v5loader import create_dataloader
@@ -9,7 +10,6 @@ from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG, BaseTrainer
 from ultralytics.yolo.utils import colorstr
 from ultralytics.yolo.utils.loss import BboxLoss
 from ultralytics.yolo.utils.metrics import smooth_BCE
-from ultralytics.yolo.utils.modeling.tasks import DetectionModel
 from ultralytics.yolo.utils.ops import xywh2xyxy
 from ultralytics.yolo.utils.plotting import plot_images, plot_results
 from ultralytics.yolo.utils.tal import TaskAlignedAssigner, dist2bbox, make_anchors
diff --git a/ultralytics/yolo/v8/segment/predict.py b/ultralytics/yolo/v8/segment/predict.py
index 4403635..bd0384f 100644
--- a/ultralytics/yolo/v8/segment/predict.py
+++ b/ultralytics/yolo/v8/segment/predict.py
@@ -1,11 +1,9 @@
-from pathlib import Path
-
 import hydra
 import torch
 
 from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG
-from ultralytics.yolo.utils import ROOT, ops
-from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box
+from ultralytics.yolo.utils import ops
+from ultralytics.yolo.utils.plotting import colors, save_one_box
 
 from ..detect.predict import DetectionPredictor
 
diff --git a/ultralytics/yolo/v8/segment/train.py b/ultralytics/yolo/v8/segment/train.py
index 40071d3..49e9f7f 100644
--- a/ultralytics/yolo/v8/segment/train.py
+++ b/ultralytics/yolo/v8/segment/train.py
@@ -3,10 +3,10 @@ import torch
 import torch.nn as nn
 import torch.nn.functional as F
 
+from ultralytics.nn.tasks import SegmentationModel
 from ultralytics.yolo import v8
-from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG, BaseTrainer
+from ultralytics.yolo.engine.trainer import DEFAULT_CONFIG
 from ultralytics.yolo.utils.metrics import FocalLoss, bbox_iou, smooth_BCE
-from ultralytics.yolo.utils.modeling.tasks import SegmentationModel
 from ultralytics.yolo.utils.ops import crop_mask, xywh2xyxy
 from ultralytics.yolo.utils.plotting import plot_images, plot_results
 from ultralytics.yolo.utils.torch_utils import de_parallel