ultralytics 8.3.222__tar.gz → 8.3.223__tar.gz

{ultralytics-8.3.222 → ultralytics-8.3.223}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.222
+Version: 8.3.223
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>
@@ -44,7 +44,7 @@ Requires-Dist: torch!=2.4.0,>=1.8.0; sys_platform == "win32"
 Requires-Dist: torchvision>=0.9.0
 Requires-Dist: psutil
 Requires-Dist: polars
-Requires-Dist: ultralytics-thop>=2.0.0
+Requires-Dist: ultralytics-thop>=2.0.18
 Provides-Extra: dev
 Requires-Dist: ipython; extra == "dev"
 Requires-Dist: pytest; extra == "dev"

{ultralytics-8.3.222 → ultralytics-8.3.223}/pyproject.toml

@@ -73,7 +73,7 @@ dependencies = [
     "torchvision>=0.9.0",
     "psutil", # system utilization
     "polars",
-    "ultralytics-thop>=2.0.0", # FLOPs computation https://github.com/ultralytics/thop
+    "ultralytics-thop>=2.0.18", # FLOPs computation https://github.com/ultralytics/thop
 ]
 
 # Optional dependencies ------------------------------------------------------------------------------------------------
@@ -190,4 +190,4 @@ in-place = true
 
 [tool.codespell]
 ignore-words-list = "grey,writeable,finalY,RepResNet,Idenfy,WIT,Smoot,EHR,ROUGE,ALS,iTerm,Carmel,FPR,Hach,Calle,ore,COO,MOT,crate,nd,ned,strack,dota,ane,segway,fo,gool,winn,commend,bloc,nam,afterall,skelton,goin"
-skip = "lvis.yaml,open-images-v7.yaml,ImageNet.yaml,*.pt,*.pth,*.torchscript,*.onnx,*.tflite,*.pb,*.bin,*.param,*.mlmodel,*.engine,*.npy,*.data*,*.csv,*pnnx*,*venv*,*translat*,*lock*,__pycache__*,*.ico,*.jpg,*.png,*.webp,*.avif,*.mp4,*.mov,/runs,/.git,./docs/??/*.md,./docs/mkdocs_??.yml"
+skip = "*.pt,*.pth,*.torchscript,*.onnx,*.tflite,*.pb,*.bin,*.param,*.mlmodel,*.engine,*.npy,*.data*,*.csv,*pnnx*,*venv*,*translat*,*lock*,__pycache__*,*.ico,*.jpg,*.png,*.webp,*.avif,*.mp4,*.mov,/runs,/.git,./docs/??/*.md,./docs/mkdocs_??.yml"

{ultralytics-8.3.222 → ultralytics-8.3.223}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.222"
+__version__ = "8.3.223"
 
 import importlib
 import os

{ultralytics-8.3.222 → ultralytics-8.3.223}/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-8.3.222 → ultralytics-8.3.223}/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-8.3.222 → ultralytics-8.3.223}/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-8.3.222 → ultralytics-8.3.223}/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)
@@ -371,7 +370,7 @@ class Exporter:
                 LOGGER.warning("IMX export requires nms=True, setting nms=True.")
                 self.args.nms = True
             if model.task not in {"detect", "pose", "classify"}:
-                raise ValueError("IMX export only supported for detection and pose estimation models.")
+                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)
@@ -461,6 +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
@@ -642,7 +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)
@@ -1053,75 +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
@@ -1189,22 +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
 
@@ -1212,31 +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

{ultralytics-8.3.222 → ultralytics-8.3.223}/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-8.3.222 → ultralytics-8.3.223}/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-8.3.222 → ultralytics-8.3.223}/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-8.3.223/ultralytics/utils/export/__init__.py

@@ -0,0 +1,7 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from .engine import onnx2engine, torch2onnx
+from .imx import torch2imx
+from .tensorflow import keras2pb, onnx2saved_model, pb2tfjs, tflite2edgetpu
+
+__all__ = ["keras2pb", "onnx2engine", "onnx2saved_model", "pb2tfjs", "tflite2edgetpu", "torch2imx", "torch2onnx"]

ultralytics-8.3.222/ultralytics/utils/export/__init__.py → ultralytics-8.3.223/ultralytics/utils/export/engine.py

@@ -10,8 +10,6 @@ import torch
 from ultralytics.utils import IS_JETSON, LOGGER
 from ultralytics.utils.torch_utils import TORCH_2_4
 
-from .imx import torch2imx  # noqa
-
 
 def torch2onnx(
     torch_model: torch.nn.Module,

ultralytics-8.3.223/ultralytics/utils/export/tensorflow.py

@@ -0,0 +1,221 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import numpy as np
+import torch
+
+from ultralytics.nn.modules import Detect, Pose
+from ultralytics.utils import LOGGER
+from ultralytics.utils.downloads import attempt_download_asset
+from ultralytics.utils.files import spaces_in_path
+from ultralytics.utils.tal import make_anchors
+
+
+def tf_wrapper(model: torch.nn.Module) -> torch.nn.Module:
+    """A wrapper to add TensorFlow compatible inference methods to Detect and Pose layers."""
+    for m in model.modules():
+        if not isinstance(m, Detect):
+            continue
+        import types
+
+        m._inference = types.MethodType(_tf_inference, m)
+        if type(m) is Pose:
+            m.kpts_decode = types.MethodType(tf_kpts_decode, m)
+    return model
+
+
+def _tf_inference(self, x: list[torch.Tensor]) -> tuple[torch.Tensor]:
+    """Decode boxes and cls scores for tf object detection."""
+    shape = x[0].shape  # BCHW
+    x_cat = torch.cat([xi.view(x[0].shape[0], self.no, -1) for xi in x], 2)
+    box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
+    if self.dynamic or self.shape != shape:
+        self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
+        self.shape = shape
+    grid_h, grid_w = shape[2], 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])
+    return torch.cat((dbox, cls.sigmoid()), 1)
+
+
+def tf_kpts_decode(self, bs: int, kpts: torch.Tensor) -> torch.Tensor:
+    """Decode keypoints for tf pose estimation."""
+    ndim = self.kpt_shape[1]
+    # 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
+    if ndim == 3:
+        a = torch.cat((a, y[:, :, 2:3].sigmoid()), 2)
+    return a.view(bs, self.nk, -1)
+
+
+def onnx2saved_model(
+    onnx_file: str,
+    output_dir: Path,
+    int8: bool = False,
+    images: np.ndarray = None,
+    disable_group_convolution: bool = False,
+    prefix="",
+):
+    """
+    Convert a ONNX model to TensorFlow SavedModel format via ONNX.
+
+    Args:
+        onnx_file (str): ONNX file path.
+        output_dir (Path): Output directory path for the SavedModel.
+        int8 (bool, optional): Enable INT8 quantization. Defaults to False.
+        images (np.ndarray, optional): Calibration images for INT8 quantization in BHWC format.
+        disable_group_convolution (bool, optional): Disable group convolution optimization. Defaults to False.
+        prefix (str, optional): Logging prefix. Defaults to "".
+
+    Returns:
+        (keras.Model): Converted Keras model.
+
+    Note:
+        Requires onnx2tf package. Downloads calibration data if INT8 quantization is enabled.
+        Removes temporary files and renames quantized models after conversion.
+    """
+    # 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)
+    np_data = None
+    if int8:
+        tmp_file = output_dir / "tmp_tflite_int8_calibration_images.npy"  # int8 calibration images file
+        if images is not None:
+            output_dir.mkdir()
+            np.save(str(tmp_file), images)  # 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=onnx_file,
+        output_folder_path=str(output_dir),
+        not_use_onnxsim=True,
+        verbosity="error",  # note INT8-FP16 activation bug https://github.com/ultralytics/ultralytics/issues/15873
+        output_integer_quantized_tflite=int8,
+        custom_input_op_name_np_data_path=np_data,
+        enable_batchmatmul_unfold=True and not int8,  # fix lower no. of detected objects on GPU delegate
+        output_signaturedefs=True,  # fix error with Attention block group convolution
+        disable_group_convolution=disable_group_convolution,  # fix error with group convolution
+    )
+
+    # Remove/rename TFLite models
+    if int8:
+        tmp_file.unlink(missing_ok=True)
+        for file in output_dir.rglob("*_dynamic_range_quant.tflite"):
+            file.rename(file.with_name(file.stem.replace("_dynamic_range_quant", "_int8") + file.suffix))
+        for file in output_dir.rglob("*_integer_quant_with_int16_act.tflite"):
+            file.unlink()  # delete extra fp16 activation TFLite files
+    return keras_model
+
+
+def keras2pb(keras_model, file: Path, prefix=""):
+    """
+    Convert a Keras model to TensorFlow GraphDef (.pb) format.
+
+    Args:
+        keras_model(tf_keras): Keras model to convert to frozen graph format.
+        file (Path): Output file path (suffix will be changed to .pb).
+        prefix (str, optional): Logging prefix. Defaults to "".
+
+    Note:
+        Creates a frozen graph by converting variables to constants for inference optimization.
+    """
+    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__}...")
+    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(file.parent), name=file.name, as_text=False)
+
+
+def tflite2edgetpu(tflite_file: str | Path, output_dir: str | Path, prefix: str = ""):
+    """
+    Convert a TensorFlow Lite model to Edge TPU format using the Edge TPU compiler.
+
+    Args:
+        tflite_file (str | Path): Path to the input TensorFlow Lite (.tflite) model file.
+        output_dir (str | Path): Output directory path for the compiled Edge TPU model.
+        prefix (str, optional): Logging prefix. Defaults to "".
+
+    Note:
+        Requires the Edge TPU compiler to be installed. The function compiles the TFLite model
+        for optimal performance on Google's Edge TPU hardware accelerator.
+    """
+    import subprocess
+
+    cmd = (
+        "edgetpu_compiler "
+        f'--out_dir "{output_dir}" '
+        "--show_operations "
+        "--search_delegate "
+        "--delegate_search_step 30 "
+        "--timeout_sec 180 "
+        f'"{tflite_file}"'
+    )
+    LOGGER.info(f"{prefix} running '{cmd}'")
+    subprocess.run(cmd, shell=True)
+
+
+def pb2tfjs(pb_file: str, output_dir: str, half: bool = False, int8: bool = False, prefix: str = ""):
+    """
+    Convert a TensorFlow GraphDef (.pb) model to TensorFlow.js format.
+
+    Args:
+        pb_file (str): Path to the input TensorFlow GraphDef (.pb) model file.
+        output_dir (str): Output directory path for the converted TensorFlow.js model.
+        half (bool, optional): Enable FP16 quantization. Defaults to False.
+        int8 (bool, optional): Enable INT8 quantization. Defaults to False.
+        prefix (str, optional): Logging prefix. Defaults to "".
+
+    Note:
+        Requires tensorflowjs package. Uses tensorflowjs_converter command-line tool for conversion.
+        Handles spaces in file paths and warns if output directory contains spaces.
+    """
+    import subprocess
+
+    import tensorflow as tf
+    import tensorflowjs as tfjs
+
+    LOGGER.info(f"\n{prefix} starting export with tensorflowjs {tfjs.__version__}...")
+
+    gd = tf.Graph().as_graph_def()  # TF GraphDef
+    with open(pb_file, "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 half else "--quantize_uint8" if int8 else ""
+    with spaces_in_path(pb_file) as fpb_, spaces_in_path(output_dir) 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 output_dir:
+        LOGGER.warning(f"{prefix} your model may not work correctly with spaces in path '{output_dir}'.")
+
+
+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"))

{ultralytics-8.3.222 → ultralytics-8.3.223}/ultralytics/utils/nms.py

@@ -231,9 +231,11 @@ class TorchNMS:
             upper_mask = row_idx < col_idx
             ious = ious * upper_mask
             # Zeroing these scores ensures the additional indices would not affect the final results
-            scores[~((ious >= iou_threshold).sum(0) <= 0)] = 0
+            scores_ = scores[sorted_idx]
+            scores_[~((ious >= iou_threshold).sum(0) <= 0)] = 0
+            scores[sorted_idx] = scores_  # update original tensor for NMSModel
             # NOTE: return indices with fixed length to avoid TFLite reshape error
-            pick = torch.topk(scores, scores.shape[0]).indices
+            pick = torch.topk(scores_, scores_.shape[0]).indices
         return sorted_idx[pick]
 
     @staticmethod