ultralytics 8.3.221__py3-none-any.whl → 8.3.223__py3-none-any.whl

tests/test_python.py

@@ -136,23 +136,23 @@ def test_predict_visualize(model):
     YOLO(WEIGHTS_DIR / model)(SOURCE, imgsz=32, visualize=True)
 
 
-def test_predict_grey_and_4ch(tmp_path):
-    """Test YOLO prediction on SOURCE converted to greyscale and 4-channel images with various filenames."""
+def test_predict_gray_and_4ch(tmp_path):
+    """Test YOLO prediction on SOURCE converted to grayscale and 4-channel images with various filenames."""
     im = Image.open(SOURCE)
 
-    source_greyscale = tmp_path / "greyscale.jpg"
+    source_grayscale = tmp_path / "grayscale.jpg"
     source_rgba = tmp_path / "4ch.png"
     source_non_utf = tmp_path / "non_UTF_测试文件_tést_image.jpg"
     source_spaces = tmp_path / "image with spaces.jpg"
 
-    im.convert("L").save(source_greyscale)  # greyscale
+    im.convert("L").save(source_grayscale)  # grayscale
     im.convert("RGBA").save(source_rgba)  # 4-ch PNG with alpha
     im.save(source_non_utf)  # non-UTF characters in filename
     im.save(source_spaces)  # spaces in filename
 
     # Inference
     model = YOLO(MODEL)
-    for f in source_rgba, source_greyscale, source_non_utf, source_spaces:
+    for f in source_rgba, source_grayscale, source_non_utf, source_spaces:
         for source in Image.open(f), cv2.imread(str(f)), f:
             results = model(source, save=True, verbose=True, imgsz=32)
             assert len(results) == 1  # verify that an image was run

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.221"
+__version__ = "8.3.223"
 
 import importlib
 import os

ultralytics/cfg/datasets/ImageNet.yaml

@@ -342,7 +342,7 @@ names:
   322: ringlet
   323: monarch butterfly
   324: small white
-  325: sulphur butterfly
+  325: sulfur butterfly
   326: gossamer-winged butterfly
   327: starfish
   328: sea urchin

ultralytics/cfg/datasets/lvis.yaml

@@ -35,7 +35,7 @@ names:
   17: armband
   18: armchair
   19: armoire
-  20: armor/armour
+  20: armor
   21: artichoke
   22: trash can/garbage can/wastebin/dustbin/trash barrel/trash bin
   23: ashtray
@@ -245,7 +245,7 @@ names:
   227: CD player
   228: celery
   229: cellular telephone/cellular phone/cellphone/mobile phone/smart phone
-  230: chain mail/ring mail/chain armor/chain armour/ring armor/ring armour
+  230: chain mail/ring mail/chain armor/ring armor
   231: chair
   232: chaise longue/chaise/daybed
   233: chalice
@@ -305,7 +305,7 @@ names:
   287: coin
   288: colander/cullender
   289: coleslaw/slaw
-  290: coloring material/colouring material
+  290: coloring material
   291: combination lock
   292: pacifier/teething ring
   293: comic book
@@ -401,7 +401,7 @@ names:
   383: domestic ass/donkey
   384: doorknob/doorhandle
   385: doormat/welcome mat
-  386: doughnut/donut
+  386: donut
   387: dove
   388: dragonfly
   389: drawer
@@ -1072,7 +1072,7 @@ names:
   1054: tag
   1055: taillight/rear light
   1056: tambourine
-  1057: army tank/armored combat vehicle/armoured combat vehicle
+  1057: army tank/armored combat vehicle
   1058: tank/tank storage vessel/storage tank
   1059: tank top/tank top clothing
   1060: tape/tape sticky cloth or paper

ultralytics/cfg/datasets/open-images-v7.yaml

@@ -182,7 +182,7 @@ names:
   163: Dolphin
   164: Door
   165: Door handle
-  166: Doughnut
+  166: Donut
   167: Dragonfly
   168: Drawer
   169: Dress

ultralytics/data/base.py

@@ -307,7 +307,7 @@ class BaseDataset(Dataset):
             b += im.nbytes
             if not os.access(Path(im_file).parent, os.W_OK):
                 self.cache = None
-                LOGGER.warning(f"{self.prefix}Skipping caching images to disk, directory not writeable")
+                LOGGER.warning(f"{self.prefix}Skipping caching images to disk, directory not writable")
                 return False
         disk_required = b * self.ni / n * (1 + safety_margin)  # bytes required to cache dataset to disk
         total, _used, free = shutil.disk_usage(Path(self.im_files[0]).parent)

ultralytics/data/utils.py

@@ -804,4 +804,4 @@ def save_dataset_cache_file(prefix: str, path: Path, x: dict, version: str):
             np.save(file, x)
         LOGGER.info(f"{prefix}New cache created: {path}")
     else:
-        LOGGER.warning(f"{prefix}Cache directory {path.parent} is not writeable, cache not saved.")
+        LOGGER.warning(f"{prefix}Cache directory {path.parent} is not writable, cache not saved.")

ultralytics/engine/exporter.py

@@ -107,9 +107,17 @@ from ultralytics.utils.checks import (
     is_intel,
     is_sudo_available,
 )
-from ultralytics.utils.downloads import attempt_download_asset, get_github_assets, safe_download
-from ultralytics.utils.export import onnx2engine, torch2imx, torch2onnx
-from ultralytics.utils.files import file_size, spaces_in_path
+from ultralytics.utils.downloads import get_github_assets, safe_download
+from ultralytics.utils.export import (
+    keras2pb,
+    onnx2engine,
+    onnx2saved_model,
+    pb2tfjs,
+    tflite2edgetpu,
+    torch2imx,
+    torch2onnx,
+)
+from ultralytics.utils.files import file_size
 from ultralytics.utils.metrics import batch_probiou
 from ultralytics.utils.nms import TorchNMS
 from ultralytics.utils.ops import Profile
@@ -206,15 +214,6 @@ def validate_args(format, passed_args, valid_args):
             assert arg in valid_args, f"ERROR ❌️ argument '{arg}' is not supported for format='{format}'"
 
 
-def gd_outputs(gd):
-    """Return TensorFlow GraphDef model output node names."""
-    name_list, input_list = [], []
-    for node in gd.node:  # tensorflow.core.framework.node_def_pb2.NodeDef
-        name_list.append(node.name)
-        input_list.extend(node.input)
-    return sorted(f"{x}:0" for x in list(set(name_list) - set(input_list)) if not x.startswith("NoOp"))
-
-
 def try_export(inner_func):
     """YOLO export decorator, i.e. @try_export."""
     inner_args = get_default_args(inner_func)
@@ -367,11 +366,11 @@ class Exporter:
             if not self.args.int8:
                 LOGGER.warning("IMX export requires int8=True, setting int8=True.")
                 self.args.int8 = True
-            if not self.args.nms:
+            if not self.args.nms and model.task in {"detect", "pose"}:
                 LOGGER.warning("IMX export requires nms=True, setting nms=True.")
                 self.args.nms = True
-            if model.task not in {"detect", "pose"}:
-                raise ValueError("IMX export only supported for detection and pose estimation models.")
+            if model.task not in {"detect", "pose", "classify"}:
+                raise ValueError("IMX export only supported for detection, pose estimation, and classification models.")
         if not hasattr(model, "names"):
             model.names = default_class_names()
         model.names = check_class_names(model.names)
@@ -396,8 +395,6 @@ class Exporter:
             assert self.args.name in RKNN_CHIPS, (
                 f"Invalid processor name '{self.args.name}' for Rockchip RKNN export. Valid names are {RKNN_CHIPS}."
             )
-        if self.args.int8 and tflite:
-            assert not getattr(model, "end2end", False), "TFLite INT8 export not supported for end2end models."
         if self.args.nms:
             assert not isinstance(model, ClassificationModel), "'nms=True' is not valid for classification models."
             assert not tflite or not ARM64 or not LINUX, "TFLite export with NMS unsupported on ARM64 Linux"
@@ -463,6 +460,10 @@ class Exporter:
             from ultralytics.utils.export.imx import FXModel
 
             model = FXModel(model, self.imgsz)
+        if tflite or edgetpu:
+            from ultralytics.utils.export.tensorflow import tf_wrapper
+
+            model = tf_wrapper(model)
         for m in model.modules():
             if isinstance(m, Classify):
                 m.export = True
@@ -644,7 +645,7 @@ class Exporter:
             assert TORCH_1_13, f"'nms=True' ONNX export requires torch>=1.13 (found torch=={TORCH_VERSION})"
 
         f = str(self.file.with_suffix(".onnx"))
-        output_names = ["output0", "output1"] if isinstance(self.model, SegmentationModel) else ["output0"]
+        output_names = ["output0", "output1"] if self.model.task == "segment" else ["output0"]
         dynamic = self.args.dynamic
         if dynamic:
             dynamic = {"images": {0: "batch", 2: "height", 3: "width"}}  # shape(1,3,640,640)
@@ -1055,75 +1056,43 @@ class Exporter:
         if f.is_dir():
             shutil.rmtree(f)  # delete output folder
 
-        # Pre-download calibration file to fix https://github.com/PINTO0309/onnx2tf/issues/545
-        onnx2tf_file = Path("calibration_image_sample_data_20x128x128x3_float32.npy")
-        if not onnx2tf_file.exists():
-            attempt_download_asset(f"{onnx2tf_file}.zip", unzip=True, delete=True)
+        # Export to TF
+        images = None
+        if self.args.int8 and self.args.data:
+            images = [batch["img"] for batch in self.get_int8_calibration_dataloader(prefix)]
+            images = (
+                torch.nn.functional.interpolate(torch.cat(images, 0).float(), size=self.imgsz)
+                .permute(0, 2, 3, 1)
+                .numpy()
+                .astype(np.float32)
+            )
 
         # Export to ONNX
         if isinstance(self.model.model[-1], RTDETRDecoder):
             self.args.opset = self.args.opset or 19
             assert 16 <= self.args.opset <= 19, "RTDETR export requires opset>=16;<=19"
         self.args.simplify = True
-        f_onnx = self.export_onnx()
-
-        # Export to TF
-        np_data = None
-        if self.args.int8:
-            tmp_file = f / "tmp_tflite_int8_calibration_images.npy"  # int8 calibration images file
-            if self.args.data:
-                f.mkdir()
-                images = [batch["img"] for batch in self.get_int8_calibration_dataloader(prefix)]
-                images = torch.nn.functional.interpolate(torch.cat(images, 0).float(), size=self.imgsz).permute(
-                    0, 2, 3, 1
-                )
-                np.save(str(tmp_file), images.numpy().astype(np.float32))  # BHWC
-                np_data = [["images", tmp_file, [[[[0, 0, 0]]]], [[[[255, 255, 255]]]]]]
-
-        import onnx2tf  # scoped for after ONNX export for reduced conflict during import
-
-        LOGGER.info(f"{prefix} starting TFLite export with onnx2tf {onnx2tf.__version__}...")
-        keras_model = onnx2tf.convert(
-            input_onnx_file_path=f_onnx,
-            output_folder_path=str(f),
-            not_use_onnxsim=True,
-            verbosity="error",  # note INT8-FP16 activation bug https://github.com/ultralytics/ultralytics/issues/15873
-            output_integer_quantized_tflite=self.args.int8,
-            custom_input_op_name_np_data_path=np_data,
-            enable_batchmatmul_unfold=True and not self.args.int8,  # fix lower no. of detected objects on GPU delegate
-            output_signaturedefs=True,  # fix error with Attention block group convolution
-            disable_group_convolution=self.args.format in {"tfjs", "edgetpu"},  # fix error with group convolution
+        f_onnx = self.export_onnx()  # ensure ONNX is available
+        keras_model = onnx2saved_model(
+            f_onnx,
+            f,
+            int8=self.args.int8,
+            images=images,
+            disable_group_convolution=self.args.format in {"tfjs", "edgetpu"},
+            prefix=prefix,
         )
         YAML.save(f / "metadata.yaml", self.metadata)  # add metadata.yaml
-
-        # Remove/rename TFLite models
-        if self.args.int8:
-            tmp_file.unlink(missing_ok=True)
-            for file in f.rglob("*_dynamic_range_quant.tflite"):
-                file.rename(file.with_name(file.stem.replace("_dynamic_range_quant", "_int8") + file.suffix))
-            for file in f.rglob("*_integer_quant_with_int16_act.tflite"):
-                file.unlink()  # delete extra fp16 activation TFLite files
-
         # Add TFLite metadata
         for file in f.rglob("*.tflite"):
-            f.unlink() if "quant_with_int16_act.tflite" in str(f) else self._add_tflite_metadata(file)
+            file.unlink() if "quant_with_int16_act.tflite" in str(file) else self._add_tflite_metadata(file)
 
         return str(f), keras_model  # or keras_model = tf.saved_model.load(f, tags=None, options=None)
 
     @try_export
     def export_pb(self, keras_model, prefix=colorstr("TensorFlow GraphDef:")):
         """Export YOLO model to TensorFlow GraphDef *.pb format https://github.com/leimao/Frozen-Graph-TensorFlow."""
-        import tensorflow as tf
-        from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2
-
-        LOGGER.info(f"\n{prefix} starting export with tensorflow {tf.__version__}...")
         f = self.file.with_suffix(".pb")
-
-        m = tf.function(lambda x: keras_model(x))  # full model
-        m = m.get_concrete_function(tf.TensorSpec(keras_model.inputs[0].shape, keras_model.inputs[0].dtype))
-        frozen_func = convert_variables_to_constants_v2(m)
-        frozen_func.graph.as_graph_def()
-        tf.io.write_graph(graph_or_graph_def=frozen_func.graph, logdir=str(f.parent), name=f.name, as_text=False)
+        keras2pb(keras_model, f, prefix)
         return f
 
     @try_export
@@ -1191,22 +1160,11 @@ class Exporter:
                 "sudo apt-get install edgetpu-compiler",
             ):
                 subprocess.run(c if is_sudo_available() else c.replace("sudo ", ""), shell=True, check=True)
-        ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().rsplit(maxsplit=1)[-1]
 
+        ver = subprocess.run(cmd, shell=True, capture_output=True, check=True).stdout.decode().rsplit(maxsplit=1)[-1]
         LOGGER.info(f"\n{prefix} starting export with Edge TPU compiler {ver}...")
+        tflite2edgetpu(tflite_file=tflite_model, output_dir=tflite_model.parent, prefix=prefix)
         f = str(tflite_model).replace(".tflite", "_edgetpu.tflite")  # Edge TPU model
-
-        cmd = (
-            "edgetpu_compiler "
-            f'--out_dir "{Path(f).parent}" '
-            "--show_operations "
-            "--search_delegate "
-            "--delegate_search_step 30 "
-            "--timeout_sec 180 "
-            f'"{tflite_model}"'
-        )
-        LOGGER.info(f"{prefix} running '{cmd}'")
-        subprocess.run(cmd, shell=True)
         self._add_tflite_metadata(f)
         return f
 
@@ -1214,31 +1172,10 @@ class Exporter:
     def export_tfjs(self, prefix=colorstr("TensorFlow.js:")):
         """Export YOLO model to TensorFlow.js format."""
         check_requirements("tensorflowjs")
-        import tensorflow as tf
-        import tensorflowjs as tfjs
 
-        LOGGER.info(f"\n{prefix} starting export with tensorflowjs {tfjs.__version__}...")
         f = str(self.file).replace(self.file.suffix, "_web_model")  # js dir
         f_pb = str(self.file.with_suffix(".pb"))  # *.pb path
-
-        gd = tf.Graph().as_graph_def()  # TF GraphDef
-        with open(f_pb, "rb") as file:
-            gd.ParseFromString(file.read())
-        outputs = ",".join(gd_outputs(gd))
-        LOGGER.info(f"\n{prefix} output node names: {outputs}")
-
-        quantization = "--quantize_float16" if self.args.half else "--quantize_uint8" if self.args.int8 else ""
-        with spaces_in_path(f_pb) as fpb_, spaces_in_path(f) as f_:  # exporter can not handle spaces in path
-            cmd = (
-                "tensorflowjs_converter "
-                f'--input_format=tf_frozen_model {quantization} --output_node_names={outputs} "{fpb_}" "{f_}"'
-            )
-            LOGGER.info(f"{prefix} running '{cmd}'")
-            subprocess.run(cmd, shell=True)
-
-        if " " in f:
-            LOGGER.warning(f"{prefix} your model may not work correctly with spaces in path '{f}'.")
-
+        pb2tfjs(pb_file=f_pb, output_dir=f, half=self.args.half, int8=self.args.int8, prefix=prefix)
         # Add metadata
         YAML.save(Path(f) / "metadata.yaml", self.metadata)  # add metadata.yaml
         return f
@@ -1510,17 +1447,16 @@ class NMSModel(torch.nn.Module):
             box, score, cls, extra = box[mask], score[mask], cls[mask], extra[mask]
             nmsbox = box.clone()
             # `8` is the minimum value experimented to get correct NMS results for obb
-            multiplier = 8 if self.obb else 1
+            multiplier = (8 if self.obb else 1) / max(len(self.model.names), 1)
             # Normalize boxes for NMS since large values for class offset causes issue with int8 quantization
             if self.args.format == "tflite":  # TFLite is already normalized
                 nmsbox *= multiplier
             else:
-                nmsbox = multiplier * nmsbox / torch.tensor(x.shape[2:], **kwargs).max()
-            if not self.args.agnostic_nms:  # class-specific NMS
+                nmsbox = multiplier * (nmsbox / torch.tensor(x.shape[2:], **kwargs).max())
+            if not self.args.agnostic_nms:  # class-wise NMS
                 end = 2 if self.obb else 4
                 # fully explicit expansion otherwise reshape error
-                # large max_wh causes issues when quantizing
-                cls_offset = cls.reshape(-1, 1).expand(nmsbox.shape[0], end)
+                cls_offset = cls.view(cls.shape[0], 1).expand(cls.shape[0], end)
                 offbox = nmsbox[:, :end] + cls_offset * multiplier
                 nmsbox = torch.cat((offbox, nmsbox[:, end:]), dim=-1)
             nms_fn = (

ultralytics/engine/model.py

@@ -877,7 +877,7 @@ class Model(torch.nn.Module):
             >>> model = model._apply(lambda t: t.cuda())  # Move model to GPU
         """
         self._check_is_pytorch_model()
-        self = super()._apply(fn)  # noqa
+        self = super()._apply(fn)
         self.predictor = None  # reset predictor as device may have changed
         self.overrides["device"] = self.device  # was str(self.device) i.e. device(type='cuda', index=0) -> 'cuda:0'
         return self

ultralytics/engine/trainer.py

@@ -727,7 +727,7 @@ class BaseTrainer:
 
     def label_loss_items(self, loss_items=None, prefix="train"):
         """
-        Return a loss dict with labelled training loss items tensor.
+        Return a loss dict with labeled training loss items tensor.
 
         Note:
             This is not needed for classification but necessary for segmentation & detection

ultralytics/models/rtdetr/val.py

@@ -89,7 +89,7 @@ class RTDETRDataset(YOLODataset):
             transforms = v8_transforms(self, self.imgsz, hyp, stretch=True)
         else:
             # transforms = Compose([LetterBox(new_shape=(self.imgsz, self.imgsz), auto=False, scale_fill=True)])
-            transforms = Compose([])
+            transforms = Compose([lambda x: {**x, **{"ratio_pad": [x["ratio_pad"], [0, 0]]}}])
         transforms.append(
             Format(
                 bbox_format="xywh",

ultralytics/models/yolo/classify/train.py

@@ -38,7 +38,7 @@ class ClassificationTrainer(BaseTrainer):
         preprocess_batch: Preprocess a batch of images and classes.
         progress_string: Return a formatted string showing training progress.
         get_validator: Return an instance of ClassificationValidator.
-        label_loss_items: Return a loss dict with labelled training loss items.
+        label_loss_items: Return a loss dict with labeled training loss items.
         final_eval: Evaluate trained model and save validation results.
         plot_training_samples: Plot training samples with their annotations.
 
@@ -178,7 +178,7 @@ class ClassificationTrainer(BaseTrainer):
 
     def label_loss_items(self, loss_items: torch.Tensor | None = None, prefix: str = "train"):
         """
-        Return a loss dict with labelled training loss items tensor.
+        Return a loss dict with labeled training loss items tensor.
 
         Args:
             loss_items (torch.Tensor, optional): Loss tensor items.

ultralytics/nn/autobackend.py

@@ -428,7 +428,7 @@ class AutoBackend(nn.Module):
             LOGGER.info(f"Loading {w} for TensorFlow GraphDef inference...")
             import tensorflow as tf
 
-            from ultralytics.engine.exporter import gd_outputs
+            from ultralytics.utils.export.tensorflow import gd_outputs
 
             def wrap_frozen_graph(gd, inputs, outputs):
                 """Wrap frozen graphs for deployment."""

ultralytics/nn/modules/head.py

@@ -166,22 +166,8 @@ class Detect(nn.Module):
             self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
             self.shape = shape
 
-        if self.export and self.format in {"saved_model", "pb", "tflite", "edgetpu", "tfjs"}:  # avoid TF FlexSplitV ops
-            box = x_cat[:, : self.reg_max * 4]
-            cls = x_cat[:, self.reg_max * 4 :]
-        else:
-            box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
-
-        if self.export and self.format in {"tflite", "edgetpu"}:
-            # Precompute normalization factor to increase numerical stability
-            # See https://github.com/ultralytics/ultralytics/issues/7371
-            grid_h = shape[2]
-            grid_w = shape[3]
-            grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=box.device).reshape(1, 4, 1)
-            norm = self.strides / (self.stride[0] * grid_size)
-            dbox = self.decode_bboxes(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2])
-        else:
-            dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides
+        box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
+        dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides
         return torch.cat((dbox, cls.sigmoid()), 1)
 
     def bias_init(self):
@@ -391,20 +377,9 @@ class Pose(Detect):
         """Decode keypoints from predictions."""
         ndim = self.kpt_shape[1]
         if self.export:
-            if self.format in {
-                "tflite",
-                "edgetpu",
-            }:  # required for TFLite export to avoid 'PLACEHOLDER_FOR_GREATER_OP_CODES' bug
-                # Precompute normalization factor to increase numerical stability
-                y = kpts.view(bs, *self.kpt_shape, -1)
-                grid_h, grid_w = self.shape[2], self.shape[3]
-                grid_size = torch.tensor([grid_w, grid_h], device=y.device).reshape(1, 2, 1)
-                norm = self.strides / (self.stride[0] * grid_size)
-                a = (y[:, :, :2] * 2.0 + (self.anchors - 0.5)) * norm
-            else:
-                # NCNN fix
-                y = kpts.view(bs, *self.kpt_shape, -1)
-                a = (y[:, :, :2] * 2.0 + (self.anchors - 0.5)) * self.strides
+            # NCNN fix
+            y = kpts.view(bs, *self.kpt_shape, -1)
+            a = (y[:, :, :2] * 2.0 + (self.anchors - 0.5)) * self.strides
             if ndim == 3:
                 a = torch.cat((a, y[:, :, 2:3].sigmoid()), 2)
             return a.view(bs, self.nk, -1)

ultralytics/utils/__init__.py

@@ -795,13 +795,13 @@ def is_pip_package(filepath: str = __name__) -> bool:
 
 def is_dir_writeable(dir_path: str | Path) -> bool:
     """
-    Check if a directory is writeable.
+    Check if a directory is writable.
 
     Args:
         dir_path (str | Path): The path to the directory.
 
     Returns:
-        (bool): True if the directory is writeable, False otherwise.
+        (bool): True if the directory is writable, False otherwise.
     """
     return os.access(str(dir_path), os.W_OK)
 
@@ -882,14 +882,14 @@ def get_user_config_dir(sub_dir="Ultralytics"):
         p.mkdir(parents=True, exist_ok=True)
         return p
 
-    # Fallbacks for Docker, GCP/AWS functions where only /tmp is writeable
+    # Fallbacks for Docker, GCP/AWS functions where only /tmp is writable
     for alt in [Path("/tmp") / sub_dir, Path.cwd() / sub_dir]:
         if alt.exists():
             return alt
         if is_dir_writeable(alt.parent):
             alt.mkdir(parents=True, exist_ok=True)
             LOGGER.warning(
-                f"user config directory '{p}' is not writeable, using '{alt}'. Set YOLO_CONFIG_DIR to override."
+                f"user config directory '{p}' is not writable, using '{alt}'. Set YOLO_CONFIG_DIR to override."
             )
             return alt
 

ultralytics/utils/benchmarks.py

@@ -144,7 +144,9 @@ def benchmark(
             if format == "imx":
                 assert not is_end2end
                 assert not isinstance(model, YOLOWorld), "YOLOWorldv2 IMX exports not supported"
-                assert model.task == "detect", "IMX only supported for detection task"
+                assert model.task in {"detect", "classify", "pose"}, (
+                    "IMX export is only supported for detection, classification and pose estimation tasks"
+                )
                 assert "C2f" in model.__str__(), "IMX only supported for YOLOv8n and YOLO11n"
             if format == "rknn":
                 assert not isinstance(model, YOLOWorld), "YOLOWorldv2 RKNN exports not supported yet"