ultralytics 8.0.237__py3-none-any.whl → 8.0.239__py3-none-any.whl

ultralytics/nn/__init__.py

@@ -1,9 +1,29 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-from .tasks import (BaseModel, ClassificationModel, DetectionModel, SegmentationModel, attempt_load_one_weight,
-                    attempt_load_weights, guess_model_scale, guess_model_task, parse_model, torch_safe_load,
-                    yaml_model_load)
+from .tasks import (
+    BaseModel,
+    ClassificationModel,
+    DetectionModel,
+    SegmentationModel,
+    attempt_load_one_weight,
+    attempt_load_weights,
+    guess_model_scale,
+    guess_model_task,
+    parse_model,
+    torch_safe_load,
+    yaml_model_load,
+)
 
-__all__ = ('attempt_load_one_weight', 'attempt_load_weights', 'parse_model', 'yaml_model_load', 'guess_model_task',
-           'guess_model_scale', 'torch_safe_load', 'DetectionModel', 'SegmentationModel', 'ClassificationModel',
-           'BaseModel')
+__all__ = (
+    "attempt_load_one_weight",
+    "attempt_load_weights",
+    "parse_model",
+    "yaml_model_load",
+    "guess_model_task",
+    "guess_model_scale",
+    "torch_safe_load",
+    "DetectionModel",
+    "SegmentationModel",
+    "ClassificationModel",
+    "BaseModel",
+)

ultralytics/nn/autobackend.py

@@ -32,10 +32,12 @@ def check_class_names(names):
         names = {int(k): str(v) for k, v in names.items()}
         n = len(names)
         if max(names.keys()) >= n:
-            raise KeyError(f'{n}-class dataset requires class indices 0-{n - 1}, but you have invalid class indices '
-                           f'{min(names.keys())}-{max(names.keys())} defined in your dataset YAML.')
-        if isinstance(names[0], str) and names[0].startswith('n0'):  # imagenet class codes, i.e. 'n01440764'
-            names_map = yaml_load(ROOT / 'cfg/datasets/ImageNet.yaml')['map']  # human-readable names
+            raise KeyError(
+                f"{n}-class dataset requires class indices 0-{n - 1}, but you have invalid class indices "
+                f"{min(names.keys())}-{max(names.keys())} defined in your dataset YAML."
+            )
+        if isinstance(names[0], str) and names[0].startswith("n0"):  # imagenet class codes, i.e. 'n01440764'
+            names_map = yaml_load(ROOT / "cfg/datasets/ImageNet.yaml")["map"]  # human-readable names
             names = {k: names_map[v] for k, v in names.items()}
     return names
 
@@ -44,8 +46,8 @@ def default_class_names(data=None):
     """Applies default class names to an input YAML file or returns numerical class names."""
     if data:
         with contextlib.suppress(Exception):
-            return yaml_load(check_yaml(data))['names']
-    return {i: f'class{i}' for i in range(999)}  # return default if above errors
+            return yaml_load(check_yaml(data))["names"]
+    return {i: f"class{i}" for i in range(999)}  # return default if above errors
 
 
 class AutoBackend(nn.Module):
@@ -77,14 +79,16 @@ class AutoBackend(nn.Module):
     """
 
     @torch.no_grad()
-    def __init__(self,
-                 weights='yolov8n.pt',
-                 device=torch.device('cpu'),
-                 dnn=False,
-                 data=None,
-                 fp16=False,
-                 fuse=True,
-                 verbose=True):
+    def __init__(
+        self,
+        weights="yolov8n.pt",
+        device=torch.device("cpu"),
+        dnn=False,
+        data=None,
+        fp16=False,
+        fuse=True,
+        verbose=True,
+    ):
         """
         Initialize the AutoBackend for inference.
 
@@ -100,17 +104,31 @@ class AutoBackend(nn.Module):
         super().__init__()
         w = str(weights[0] if isinstance(weights, list) else weights)
         nn_module = isinstance(weights, torch.nn.Module)
-        pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle, ncnn, triton = \
-            self._model_type(w)
+        (
+            pt,
+            jit,
+            onnx,
+            xml,
+            engine,
+            coreml,
+            saved_model,
+            pb,
+            tflite,
+            edgetpu,
+            tfjs,
+            paddle,
+            ncnn,
+            triton,
+        ) = self._model_type(w)
         fp16 &= pt or jit or onnx or xml or engine or nn_module or triton  # FP16
         nhwc = coreml or saved_model or pb or tflite or edgetpu  # BHWC formats (vs torch BCWH)
         stride = 32  # default stride
         model, metadata = None, None
 
         # Set device
-        cuda = torch.cuda.is_available() and device.type != 'cpu'  # use CUDA
+        cuda = torch.cuda.is_available() and device.type != "cpu"  # use CUDA
         if cuda and not any([nn_module, pt, jit, engine, onnx]):  # GPU dataloader formats
-            device = torch.device('cpu')
+            device = torch.device("cpu")
             cuda = False
 
         # Download if not local
@@ -121,77 +139,79 @@ class AutoBackend(nn.Module):
         if nn_module:  # in-memory PyTorch model
             model = weights.to(device)
             model = model.fuse(verbose=verbose) if fuse else model
-            if hasattr(model, 'kpt_shape'):
+            if hasattr(model, "kpt_shape"):
                 kpt_shape = model.kpt_shape  # pose-only
             stride = max(int(model.stride.max()), 32)  # model stride
-            names = model.module.names if hasattr(model, 'module') else model.names  # get class names
+            names = model.module.names if hasattr(model, "module") else model.names  # get class names
             model.half() if fp16 else model.float()
             self.model = model  # explicitly assign for to(), cpu(), cuda(), half()
             pt = True
         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,
-                                         fuse=fuse)
-            if hasattr(model, 'kpt_shape'):
+
+            model = attempt_load_weights(
+                weights if isinstance(weights, list) else w, device=device, inplace=True, fuse=fuse
+            )
+            if hasattr(model, "kpt_shape"):
                 kpt_shape = model.kpt_shape  # pose-only
             stride = max(int(model.stride.max()), 32)  # model stride
-            names = model.module.names if hasattr(model, 'module') else model.names  # get class names
+            names = model.module.names if hasattr(model, "module") else model.names  # get class names
             model.half() if fp16 else model.float()
             self.model = model  # explicitly assign for to(), cpu(), cuda(), half()
         elif jit:  # TorchScript
-            LOGGER.info(f'Loading {w} for TorchScript inference...')
-            extra_files = {'config.txt': ''}  # model metadata
+            LOGGER.info(f"Loading {w} for TorchScript inference...")
+            extra_files = {"config.txt": ""}  # model metadata
             model = torch.jit.load(w, _extra_files=extra_files, map_location=device)
             model.half() if fp16 else model.float()
-            if extra_files['config.txt']:  # load metadata dict
-                metadata = json.loads(extra_files['config.txt'], object_hook=lambda x: dict(x.items()))
+            if extra_files["config.txt"]:  # load metadata dict
+                metadata = json.loads(extra_files["config.txt"], object_hook=lambda x: dict(x.items()))
         elif dnn:  # ONNX OpenCV DNN
-            LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
-            check_requirements('opencv-python>=4.5.4')
+            LOGGER.info(f"Loading {w} for ONNX OpenCV DNN inference...")
+            check_requirements("opencv-python>=4.5.4")
             net = cv2.dnn.readNetFromONNX(w)
         elif onnx:  # ONNX Runtime
-            LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
-            check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
+            LOGGER.info(f"Loading {w} for ONNX Runtime inference...")
+            check_requirements(("onnx", "onnxruntime-gpu" if cuda else "onnxruntime"))
             import onnxruntime
-            providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
+
+            providers = ["CUDAExecutionProvider", "CPUExecutionProvider"] if cuda else ["CPUExecutionProvider"]
             session = onnxruntime.InferenceSession(w, providers=providers)
             output_names = [x.name for x in session.get_outputs()]
             metadata = session.get_modelmeta().custom_metadata_map  # metadata
         elif xml:  # OpenVINO
-            LOGGER.info(f'Loading {w} for OpenVINO inference...')
-            check_requirements('openvino>=2023.0')  # requires openvino-dev: https://pypi.org/project/openvino-dev/
+            LOGGER.info(f"Loading {w} for OpenVINO inference...")
+            check_requirements("openvino>=2023.0")  # requires openvino-dev: https://pypi.org/project/openvino-dev/
             from openvino.runtime import Core, Layout, get_batch  # noqa
+
             core = Core()
             w = Path(w)
             if not w.is_file():  # if not *.xml
-                w = next(w.glob('*.xml'))  # get *.xml file from *_openvino_model dir
-            ov_model = core.read_model(model=str(w), weights=w.with_suffix('.bin'))
+                w = next(w.glob("*.xml"))  # get *.xml file from *_openvino_model dir
+            ov_model = core.read_model(model=str(w), weights=w.with_suffix(".bin"))
             if ov_model.get_parameters()[0].get_layout().empty:
-                ov_model.get_parameters()[0].set_layout(Layout('NCHW'))
+                ov_model.get_parameters()[0].set_layout(Layout("NCHW"))
             batch_dim = get_batch(ov_model)
             if batch_dim.is_static:
                 batch_size = batch_dim.get_length()
-            ov_compiled_model = core.compile_model(ov_model, device_name='AUTO')  # AUTO selects best available device
-            metadata = w.parent / 'metadata.yaml'
+            ov_compiled_model = core.compile_model(ov_model, device_name="AUTO")  # AUTO selects best available device
+            metadata = w.parent / "metadata.yaml"
         elif engine:  # TensorRT
-            LOGGER.info(f'Loading {w} for TensorRT inference...')
+            LOGGER.info(f"Loading {w} for TensorRT inference...")
             try:
                 import tensorrt as trt  # noqa https://developer.nvidia.com/nvidia-tensorrt-download
             except ImportError:
                 if LINUX:
-                    check_requirements('nvidia-tensorrt', cmds='-U --index-url https://pypi.ngc.nvidia.com')
+                    check_requirements("nvidia-tensorrt", cmds="-U --index-url https://pypi.ngc.nvidia.com")
                 import tensorrt as trt  # noqa
-            check_version(trt.__version__, '7.0.0', hard=True)  # require tensorrt>=7.0.0
-            if device.type == 'cpu':
-                device = torch.device('cuda:0')
-            Binding = namedtuple('Binding', ('name', 'dtype', 'shape', 'data', 'ptr'))
+            check_version(trt.__version__, "7.0.0", hard=True)  # require tensorrt>=7.0.0
+            if device.type == "cpu":
+                device = torch.device("cuda:0")
+            Binding = namedtuple("Binding", ("name", "dtype", "shape", "data", "ptr"))
             logger = trt.Logger(trt.Logger.INFO)
             # Read file
-            with open(w, 'rb') as f, trt.Runtime(logger) as runtime:
-                meta_len = int.from_bytes(f.read(4), byteorder='little')  # read metadata length
-                metadata = json.loads(f.read(meta_len).decode('utf-8'))  # read metadata
+            with open(w, "rb") as f, trt.Runtime(logger) as runtime:
+                meta_len = int.from_bytes(f.read(4), byteorder="little")  # read metadata length
+                metadata = json.loads(f.read(meta_len).decode("utf-8"))  # read metadata
                 model = runtime.deserialize_cuda_engine(f.read())  # read engine
             context = model.create_execution_context()
             bindings = OrderedDict()
@@ -213,116 +233,124 @@ class AutoBackend(nn.Module):
                 im = torch.from_numpy(np.empty(shape, dtype=dtype)).to(device)
                 bindings[name] = Binding(name, dtype, shape, im, int(im.data_ptr()))
             binding_addrs = OrderedDict((n, d.ptr) for n, d in bindings.items())
-            batch_size = bindings['images'].shape[0]  # if dynamic, this is instead max batch size
+            batch_size = bindings["images"].shape[0]  # if dynamic, this is instead max batch size
         elif coreml:  # CoreML
-            LOGGER.info(f'Loading {w} for CoreML inference...')
+            LOGGER.info(f"Loading {w} for CoreML inference...")
             import coremltools as ct
+
             model = ct.models.MLModel(w)
             metadata = dict(model.user_defined_metadata)
         elif saved_model:  # TF SavedModel
-            LOGGER.info(f'Loading {w} for TensorFlow SavedModel inference...')
+            LOGGER.info(f"Loading {w} for TensorFlow SavedModel inference...")
             import tensorflow as tf
+
             keras = False  # assume TF1 saved_model
             model = tf.keras.models.load_model(w) if keras else tf.saved_model.load(w)
-            metadata = Path(w) / 'metadata.yaml'
+            metadata = Path(w) / "metadata.yaml"
         elif pb:  # GraphDef https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
-            LOGGER.info(f'Loading {w} for TensorFlow GraphDef inference...')
+            LOGGER.info(f"Loading {w} for TensorFlow GraphDef inference...")
             import tensorflow as tf
 
             from ultralytics.engine.exporter import gd_outputs
 
             def wrap_frozen_graph(gd, inputs, outputs):
                 """Wrap frozen graphs for deployment."""
-                x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=''), [])  # wrapped
+                x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), [])  # wrapped
                 ge = x.graph.as_graph_element
                 return x.prune(tf.nest.map_structure(ge, inputs), tf.nest.map_structure(ge, outputs))
 
             gd = tf.Graph().as_graph_def()  # TF GraphDef
-            with open(w, 'rb') as f:
+            with open(w, "rb") as f:
                 gd.ParseFromString(f.read())
-            frozen_func = wrap_frozen_graph(gd, inputs='x:0', outputs=gd_outputs(gd))
+            frozen_func = wrap_frozen_graph(gd, inputs="x:0", outputs=gd_outputs(gd))
         elif tflite or edgetpu:  # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
             try:  # https://coral.ai/docs/edgetpu/tflite-python/#update-existing-tf-lite-code-for-the-edge-tpu
                 from tflite_runtime.interpreter import Interpreter, load_delegate
             except ImportError:
                 import tensorflow as tf
+
                 Interpreter, load_delegate = tf.lite.Interpreter, tf.lite.experimental.load_delegate
             if edgetpu:  # TF Edge TPU https://coral.ai/software/#edgetpu-runtime
-                LOGGER.info(f'Loading {w} for TensorFlow Lite Edge TPU inference...')
-                delegate = {
-                    'Linux': 'libedgetpu.so.1',
-                    'Darwin': 'libedgetpu.1.dylib',
-                    'Windows': 'edgetpu.dll'}[platform.system()]
+                LOGGER.info(f"Loading {w} for TensorFlow Lite Edge TPU inference...")
+                delegate = {"Linux": "libedgetpu.so.1", "Darwin": "libedgetpu.1.dylib", "Windows": "edgetpu.dll"}[
+                    platform.system()
+                ]
                 interpreter = Interpreter(model_path=w, experimental_delegates=[load_delegate(delegate)])
             else:  # TFLite
-                LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
+                LOGGER.info(f"Loading {w} for TensorFlow Lite inference...")
                 interpreter = Interpreter(model_path=w)  # load TFLite model
             interpreter.allocate_tensors()  # allocate
             input_details = interpreter.get_input_details()  # inputs
             output_details = interpreter.get_output_details()  # outputs
             # Load metadata
             with contextlib.suppress(zipfile.BadZipFile):
-                with zipfile.ZipFile(w, 'r') as model:
+                with zipfile.ZipFile(w, "r") as model:
                     meta_file = model.namelist()[0]
-                    metadata = ast.literal_eval(model.read(meta_file).decode('utf-8'))
+                    metadata = ast.literal_eval(model.read(meta_file).decode("utf-8"))
         elif tfjs:  # TF.js
-            raise NotImplementedError('YOLOv8 TF.js inference is not currently supported.')
+            raise NotImplementedError("YOLOv8 TF.js inference is not currently supported.")
         elif paddle:  # PaddlePaddle
-            LOGGER.info(f'Loading {w} for PaddlePaddle inference...')
-            check_requirements('paddlepaddle-gpu' if cuda else 'paddlepaddle')
+            LOGGER.info(f"Loading {w} for PaddlePaddle inference...")
+            check_requirements("paddlepaddle-gpu" if cuda else "paddlepaddle")
             import paddle.inference as pdi  # noqa
+
             w = Path(w)
             if not w.is_file():  # if not *.pdmodel
-                w = next(w.rglob('*.pdmodel'))  # get *.pdmodel file from *_paddle_model dir
-            config = pdi.Config(str(w), str(w.with_suffix('.pdiparams')))
+                w = next(w.rglob("*.pdmodel"))  # get *.pdmodel file from *_paddle_model dir
+            config = pdi.Config(str(w), str(w.with_suffix(".pdiparams")))
             if cuda:
                 config.enable_use_gpu(memory_pool_init_size_mb=2048, device_id=0)
             predictor = pdi.create_predictor(config)
             input_handle = predictor.get_input_handle(predictor.get_input_names()[0])
             output_names = predictor.get_output_names()
-            metadata = w.parents[1] / 'metadata.yaml'
+            metadata = w.parents[1] / "metadata.yaml"
         elif ncnn:  # ncnn
-            LOGGER.info(f'Loading {w} for ncnn inference...')
-            check_requirements('git+https://github.com/Tencent/ncnn.git' if ARM64 else 'ncnn')  # requires ncnn
+            LOGGER.info(f"Loading {w} for ncnn inference...")
+            check_requirements("git+https://github.com/Tencent/ncnn.git" if ARM64 else "ncnn")  # requires ncnn
             import ncnn as pyncnn
+
             net = pyncnn.Net()
             net.opt.use_vulkan_compute = cuda
             w = Path(w)
             if not w.is_file():  # if not *.param
-                w = next(w.glob('*.param'))  # get *.param file from *_ncnn_model dir
+                w = next(w.glob("*.param"))  # get *.param file from *_ncnn_model dir
             net.load_param(str(w))
-            net.load_model(str(w.with_suffix('.bin')))
-            metadata = w.parent / 'metadata.yaml'
+            net.load_model(str(w.with_suffix(".bin")))
+            metadata = w.parent / "metadata.yaml"
         elif triton:  # NVIDIA Triton Inference Server
-            check_requirements('tritonclient[all]')
+            check_requirements("tritonclient[all]")
             from ultralytics.utils.triton import TritonRemoteModel
+
             model = TritonRemoteModel(w)
         else:
             from ultralytics.engine.exporter import export_formats
-            raise TypeError(f"model='{w}' is not a supported model format. "
-                            'See https://docs.ultralytics.com/modes/predict for help.'
-                            f'\n\n{export_formats()}')
+
+            raise TypeError(
+                f"model='{w}' is not a supported model format. "
+                "See https://docs.ultralytics.com/modes/predict for help."
+                f"\n\n{export_formats()}"
+            )
 
         # Load external metadata YAML
         if isinstance(metadata, (str, Path)) and Path(metadata).exists():
             metadata = yaml_load(metadata)
         if metadata:
             for k, v in metadata.items():
-                if k in ('stride', 'batch'):
+                if k in ("stride", "batch"):
                     metadata[k] = int(v)
-                elif k in ('imgsz', 'names', 'kpt_shape') and isinstance(v, str):
+                elif k in ("imgsz", "names", "kpt_shape") and isinstance(v, str):
                     metadata[k] = eval(v)
-            stride = metadata['stride']
-            task = metadata['task']
-            batch = metadata['batch']
-            imgsz = metadata['imgsz']
-            names = metadata['names']
-            kpt_shape = metadata.get('kpt_shape')
+            stride = metadata["stride"]
+            task = metadata["task"]
+            batch = metadata["batch"]
+            imgsz = metadata["imgsz"]
+            names = metadata["names"]
+            kpt_shape = metadata.get("kpt_shape")
         elif not (pt or triton or nn_module):
             LOGGER.warning(f"WARNING ⚠️ Metadata not found for 'model={weights}'")
 
         # Check names
-        if 'names' not in locals():  # names missing
+        if "names" not in locals():  # names missing
             names = default_class_names(data)
         names = check_class_names(names)
 
@@ -367,26 +395,28 @@ class AutoBackend(nn.Module):
             im = im.cpu().numpy()  # FP32
             y = list(self.ov_compiled_model(im).values())
         elif self.engine:  # TensorRT
-            if self.dynamic and im.shape != self.bindings['images'].shape:
-                i = self.model.get_binding_index('images')
+            if self.dynamic and im.shape != self.bindings["images"].shape:
+                i = self.model.get_binding_index("images")
                 self.context.set_binding_shape(i, im.shape)  # reshape if dynamic
-                self.bindings['images'] = self.bindings['images']._replace(shape=im.shape)
+                self.bindings["images"] = self.bindings["images"]._replace(shape=im.shape)
                 for name in self.output_names:
                     i = self.model.get_binding_index(name)
                     self.bindings[name].data.resize_(tuple(self.context.get_binding_shape(i)))
-            s = self.bindings['images'].shape
+            s = self.bindings["images"].shape
             assert im.shape == s, f"input size {im.shape} {'>' if self.dynamic else 'not equal to'} max model size {s}"
-            self.binding_addrs['images'] = int(im.data_ptr())
+            self.binding_addrs["images"] = int(im.data_ptr())
             self.context.execute_v2(list(self.binding_addrs.values()))
             y = [self.bindings[x].data for x in sorted(self.output_names)]
         elif self.coreml:  # CoreML
             im = im[0].cpu().numpy()
-            im_pil = Image.fromarray((im * 255).astype('uint8'))
+            im_pil = Image.fromarray((im * 255).astype("uint8"))
             # im = im.resize((192, 320), Image.BILINEAR)
-            y = self.model.predict({'image': im_pil})  # coordinates are xywh normalized
-            if 'confidence' in y:
-                raise TypeError('Ultralytics only supports inference of non-pipelined CoreML models exported with '
-                                f"'nms=False', but 'model={w}' has an NMS pipeline created by an 'nms=True' export.")
+            y = self.model.predict({"image": im_pil})  # coordinates are xywh normalized
+            if "confidence" in y:
+                raise TypeError(
+                    "Ultralytics only supports inference of non-pipelined CoreML models exported with "
+                    f"'nms=False', but 'model={w}' has an NMS pipeline created by an 'nms=True' export."
+                )
                 # TODO: CoreML NMS inference handling
                 # from ultralytics.utils.ops import xywh2xyxy
                 # box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]])  # xyxy pixels
@@ -425,20 +455,20 @@ class AutoBackend(nn.Module):
                 if len(y) == 2 and len(self.names) == 999:  # segments and names not defined
                     ip, ib = (0, 1) if len(y[0].shape) == 4 else (1, 0)  # index of protos, boxes
                     nc = y[ib].shape[1] - y[ip].shape[3] - 4  # y = (1, 160, 160, 32), (1, 116, 8400)
-                    self.names = {i: f'class{i}' for i in range(nc)}
+                    self.names = {i: f"class{i}" for i in range(nc)}
             else:  # Lite or Edge TPU
                 details = self.input_details[0]
-                integer = details['dtype'] in (np.int8, np.int16)  # is TFLite quantized int8 or int16 model
+                integer = details["dtype"] in (np.int8, np.int16)  # is TFLite quantized int8 or int16 model
                 if integer:
-                    scale, zero_point = details['quantization']
-                    im = (im / scale + zero_point).astype(details['dtype'])  # de-scale
-                self.interpreter.set_tensor(details['index'], im)
+                    scale, zero_point = details["quantization"]
+                    im = (im / scale + zero_point).astype(details["dtype"])  # de-scale
+                self.interpreter.set_tensor(details["index"], im)
                 self.interpreter.invoke()
                 y = []
                 for output in self.output_details:
-                    x = self.interpreter.get_tensor(output['index'])
+                    x = self.interpreter.get_tensor(output["index"])
                     if integer:
-                        scale, zero_point = output['quantization']
+                        scale, zero_point = output["quantization"]
                         x = (x.astype(np.float32) - zero_point) * scale  # re-scale
                     if x.ndim > 2:  # if task is not classification
                         # Denormalize xywh by image size. See https://github.com/ultralytics/ultralytics/pull/1695
@@ -483,13 +513,13 @@ class AutoBackend(nn.Module):
             (None): This method runs the forward pass and don't return any value
         """
         warmup_types = self.pt, self.jit, self.onnx, self.engine, self.saved_model, self.pb, self.triton, self.nn_module
-        if any(warmup_types) and (self.device.type != 'cpu' or self.triton):
+        if any(warmup_types) and (self.device.type != "cpu" or self.triton):
             im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
             for _ in range(2 if self.jit else 1):
                 self.forward(im)  # warmup
 
     @staticmethod
-    def _model_type(p='path/to/model.pt'):
+    def _model_type(p="path/to/model.pt"):
         """
         This function takes a path to a model file and returns the model type.
 
@@ -499,18 +529,20 @@ class AutoBackend(nn.Module):
         # Return model type from model path, i.e. path='path/to/model.onnx' -> type=onnx
         # types = [pt, jit, onnx, xml, engine, coreml, saved_model, pb, tflite, edgetpu, tfjs, paddle]
         from ultralytics.engine.exporter import export_formats
+
         sf = list(export_formats().Suffix)  # export suffixes
         if not is_url(p, check=False) and not isinstance(p, str):
             check_suffix(p, sf)  # checks
         name = Path(p).name
         types = [s in name for s in sf]
-        types[5] |= name.endswith('.mlmodel')  # retain support for older Apple CoreML *.mlmodel formats
+        types[5] |= name.endswith(".mlmodel")  # retain support for older Apple CoreML *.mlmodel formats
         types[8] &= not types[9]  # tflite &= not edgetpu
         if any(types):
             triton = False
         else:
             from urllib.parse import urlsplit
+
             url = urlsplit(p)
-            triton = url.netloc and url.path and url.scheme in {'http', 'grpc'}
+            triton = url.netloc and url.path and url.scheme in {"http", "grpc"}
 
         return types + [triton]

ultralytics/nn/modules/__init__.py

@@ -17,18 +17,101 @@ Example:
     ```
 """
 
-from .block import (C1, C2, C3, C3TR, DFL, SPP, SPPF, Bottleneck, BottleneckCSP, C2f, C3Ghost, C3x, GhostBottleneck,
-                    HGBlock, HGStem, Proto, RepC3, ResNetLayer)
-from .conv import (CBAM, ChannelAttention, Concat, Conv, Conv2, ConvTranspose, DWConv, DWConvTranspose2d, Focus,
-                   GhostConv, LightConv, RepConv, SpatialAttention)
+from .block import (
+    C1,
+    C2,
+    C3,
+    C3TR,
+    DFL,
+    SPP,
+    SPPF,
+    Bottleneck,
+    BottleneckCSP,
+    C2f,
+    C3Ghost,
+    C3x,
+    GhostBottleneck,
+    HGBlock,
+    HGStem,
+    Proto,
+    RepC3,
+    ResNetLayer,
+)
+from .conv import (
+    CBAM,
+    ChannelAttention,
+    Concat,
+    Conv,
+    Conv2,
+    ConvTranspose,
+    DWConv,
+    DWConvTranspose2d,
+    Focus,
+    GhostConv,
+    LightConv,
+    RepConv,
+    SpatialAttention,
+)
 from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment
-from .transformer import (AIFI, MLP, DeformableTransformerDecoder, DeformableTransformerDecoderLayer, LayerNorm2d,
-                          MLPBlock, MSDeformAttn, TransformerBlock, TransformerEncoderLayer, TransformerLayer)
+from .transformer import (
+    AIFI,
+    MLP,
+    DeformableTransformerDecoder,
+    DeformableTransformerDecoderLayer,
+    LayerNorm2d,
+    MLPBlock,
+    MSDeformAttn,
+    TransformerBlock,
+    TransformerEncoderLayer,
+    TransformerLayer,
+)
 
-__all__ = ('Conv', 'Conv2', 'LightConv', 'RepConv', 'DWConv', 'DWConvTranspose2d', 'ConvTranspose', 'Focus',
-           'GhostConv', 'ChannelAttention', 'SpatialAttention', 'CBAM', 'Concat', 'TransformerLayer',
-           'TransformerBlock', 'MLPBlock', 'LayerNorm2d', 'DFL', 'HGBlock', 'HGStem', 'SPP', 'SPPF', 'C1', 'C2', 'C3',
-           'C2f', 'C3x', 'C3TR', 'C3Ghost', 'GhostBottleneck', 'Bottleneck', 'BottleneckCSP', 'Proto', 'Detect',
-           'Segment', 'Pose', 'Classify', 'TransformerEncoderLayer', 'RepC3', 'RTDETRDecoder', 'AIFI',
-           'DeformableTransformerDecoder', 'DeformableTransformerDecoderLayer', 'MSDeformAttn', 'MLP', 'ResNetLayer',
-           'OBB')
+__all__ = (
+    "Conv",
+    "Conv2",
+    "LightConv",
+    "RepConv",
+    "DWConv",
+    "DWConvTranspose2d",
+    "ConvTranspose",
+    "Focus",
+    "GhostConv",
+    "ChannelAttention",
+    "SpatialAttention",
+    "CBAM",
+    "Concat",
+    "TransformerLayer",
+    "TransformerBlock",
+    "MLPBlock",
+    "LayerNorm2d",
+    "DFL",
+    "HGBlock",
+    "HGStem",
+    "SPP",
+    "SPPF",
+    "C1",
+    "C2",
+    "C3",
+    "C2f",
+    "C3x",
+    "C3TR",
+    "C3Ghost",
+    "GhostBottleneck",
+    "Bottleneck",
+    "BottleneckCSP",
+    "Proto",
+    "Detect",
+    "Segment",
+    "Pose",
+    "Classify",
+    "TransformerEncoderLayer",
+    "RepC3",
+    "RTDETRDecoder",
+    "AIFI",
+    "DeformableTransformerDecoder",
+    "DeformableTransformerDecoderLayer",
+    "MSDeformAttn",
+    "MLP",
+    "ResNetLayer",
+    "OBB",
+)