ultralytics 8.3.186__tar.gz → 8.3.188__tar.gz

{ultralytics-8.3.186 → ultralytics-8.3.188}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.186
+Version: 8.3.188
 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: py-cpuinfo
-Requires-Dist: pandas>=1.1.4
+Requires-Dist: polars
 Requires-Dist: ultralytics-thop>=2.0.0
 Provides-Extra: dev
 Requires-Dist: ipython; extra == "dev"
@@ -54,11 +54,12 @@ Requires-Dist: coverage[toml]; extra == "dev"
 Requires-Dist: mkdocs>=1.6.0; extra == "dev"
 Requires-Dist: mkdocs-material>=9.5.9; extra == "dev"
 Requires-Dist: mkdocstrings[python]; extra == "dev"
-Requires-Dist: mkdocs-ultralytics-plugin>=0.1.28; extra == "dev"
+Requires-Dist: mkdocs-ultralytics-plugin>=0.1.29; extra == "dev"
 Requires-Dist: mkdocs-macros-plugin>=1.0.5; extra == "dev"
 Provides-Extra: export
 Requires-Dist: numpy<2.0.0; extra == "export"
-Requires-Dist: onnx<1.18.0,>=1.12.0; extra == "export"
+Requires-Dist: onnx>=1.12.0; platform_system != "Darwin" and extra == "export"
+Requires-Dist: onnx<1.18.0,>=1.12.0; platform_system == "Darwin" and extra == "export"
 Requires-Dist: coremltools>=8.0; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: scikit-learn>=1.3.2; (platform_system != "Windows" and python_version <= "3.13") and extra == "export"
 Requires-Dist: openvino>=2024.0.0; extra == "export"
@@ -80,7 +81,6 @@ Requires-Dist: ipython; extra == "extra"
 Requires-Dist: albumentations>=1.4.6; extra == "extra"
 Requires-Dist: faster-coco-eval>=1.6.7; extra == "extra"
 Provides-Extra: typing
-Requires-Dist: pandas-stubs; extra == "typing"
 Requires-Dist: scipy-stubs; extra == "typing"
 Requires-Dist: types-pillow; extra == "typing"
 Requires-Dist: types-psutil; extra == "typing"
@@ -91,7 +91,7 @@ Dynamic: license-file
 
 <div align="center">
   <p>
-    <a href="https://www.ultralytics.com/blog/ultralytics-yolo11-has-arrived-redefine-whats-possible-in-ai" target="_blank">
+    <a href="https://www.ultralytics.com/events/yolovision?utm_source=github&utm_medium=org&utm_campaign=yv25_event" target="_blank">
       <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png" alt="Ultralytics YOLO banner"></a>
   </p>
 

{ultralytics-8.3.186 → ultralytics-8.3.188}/README.md

@@ -1,6 +1,6 @@
 <div align="center">
   <p>
-    <a href="https://www.ultralytics.com/blog/ultralytics-yolo11-has-arrived-redefine-whats-possible-in-ai" target="_blank">
+    <a href="https://www.ultralytics.com/events/yolovision?utm_source=github&utm_medium=org&utm_campaign=yv25_event" target="_blank">
       <img width="100%" src="https://raw.githubusercontent.com/ultralytics/assets/main/yolov8/banner-yolov8.png" alt="Ultralytics YOLO banner"></a>
   </p>
 

{ultralytics-8.3.186 → ultralytics-8.3.188}/pyproject.toml

@@ -73,7 +73,7 @@ dependencies = [
     "torchvision>=0.9.0",
     "psutil", # system utilization
     "py-cpuinfo", # display CPU info
-    "pandas>=1.1.4",
+    "polars",
     "ultralytics-thop>=2.0.0", # FLOPs computation https://github.com/ultralytics/thop
 ]
 
@@ -87,12 +87,13 @@ dev = [
     "mkdocs>=1.6.0",
     "mkdocs-material>=9.5.9",
     "mkdocstrings[python]",
-    "mkdocs-ultralytics-plugin>=0.1.28", # for meta descriptions and images, dates and authors
+    "mkdocs-ultralytics-plugin>=0.1.29", # for meta descriptions and images, dates and authors
     "mkdocs-macros-plugin>=1.0.5", # duplicating content (i.e. export tables) in multiple places
 ]
 export = [
     "numpy<2.0.0", # TF 2.20 compatibility
-    "onnx>=1.12.0,<1.18.0", # ONNX export
+    "onnx>=1.12.0; platform_system != 'Darwin'", # ONNX export
+    "onnx>=1.12.0,<1.18.0; platform_system == 'Darwin'",  # TF inference hanging on MacOS
     "coremltools>=8.0; platform_system != 'Windows' and python_version <= '3.13'", # CoreML supported on macOS and Linux
     "scikit-learn>=1.3.2; platform_system != 'Windows' and python_version <= '3.13'", # CoreML k-means quantization
     "openvino>=2024.0.0",  # OpenVINO export
@@ -118,7 +119,6 @@ extra = [
     "faster-coco-eval>=1.6.7", # COCO mAP
 ]
 typing = [
-    "pandas-stubs",
     "scipy-stubs",
     "types-pillow",
     "types-psutil",

{ultralytics-8.3.186 → ultralytics-8.3.188}/tests/test_python.py

@@ -209,16 +209,11 @@ def test_val(task: str, weight: str, data: str) -> None:
         metrics = model.val(data=data, imgsz=32, plots=plots)
         metrics.to_df()
         metrics.to_csv()
-        metrics.to_xml()
-        metrics.to_html()
         metrics.to_json()
-        metrics.to_sql()
-        metrics.confusion_matrix.to_df()  # Tests for confusion matrix export
+        # Tests for confusion matrix export
+        metrics.confusion_matrix.to_df()
         metrics.confusion_matrix.to_csv()
-        metrics.confusion_matrix.to_xml()
-        metrics.confusion_matrix.to_html()
         metrics.confusion_matrix.to_json()
-        metrics.confusion_matrix.to_sql()
 
 
 def test_train_scratch():
@@ -304,10 +299,7 @@ def test_results(model: str):
         r.save_crop(save_dir=TMP / "runs/tests/crops/")
         r.to_df(decimals=3)  # Align to_ methods: https://docs.ultralytics.com/modes/predict/#working-with-results
         r.to_csv()
-        r.to_xml()
-        r.to_html()
         r.to_json(normalize=True)
-        r.to_sql()
         r.plot(pil=True, save=True, filename=TMP / "results_plot_save.jpg")
         r.plot(conf=True, boxes=True)
         print(r, len(r), r.path)  # print after methods

{ultralytics-8.3.186 → ultralytics-8.3.188}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.186"
+__version__ = "8.3.188"
 
 import os
 

{ultralytics-8.3.186 → ultralytics-8.3.188}/ultralytics/cfg/datasets/SKU-110K.yaml

@@ -24,7 +24,7 @@ download: |
   from pathlib import Path
 
   import numpy as np
-  import pandas as pd
+  import polars as pl
 
   from ultralytics.utils import TQDM
   from ultralytics.utils.downloads import download
@@ -45,7 +45,7 @@ download: |
   # Convert labels
   names = "image", "x1", "y1", "x2", "y2", "class", "image_width", "image_height"  # column names
   for d in "annotations_train.csv", "annotations_val.csv", "annotations_test.csv":
-      x = pd.read_csv(dir / "annotations" / d, names=names).values  # annotations
+      x = pl.read_csv(dir / "annotations" / d, names=names).to_numpy()  # annotations
       images, unique_images = x[:, 0], np.unique(x[:, 0])
       with open((dir / d).with_suffix(".txt").__str__().replace("annotations_", ""), "w", encoding="utf-8") as f:
           f.writelines(f"./images/{s}\n" for s in unique_images)

{ultralytics-8.3.186 → ultralytics-8.3.188}/ultralytics/engine/exporter.py

@@ -582,9 +582,9 @@ class Exporter:
     @try_export
     def export_onnx(self, prefix=colorstr("ONNX:")):
         """Export YOLO model to ONNX format."""
-        requirements = ["onnx>=1.12.0,<1.18.0"]
+        requirements = ["onnx>=1.12.0"]
         if self.args.simplify:
-            requirements += ["onnxslim>=0.1.59", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
+            requirements += ["onnxslim>=0.1.65", "onnxruntime" + ("-gpu" if torch.cuda.is_available() else "")]
         check_requirements(requirements)
         import onnx  # noqa
 
@@ -960,9 +960,9 @@ class Exporter:
                 "sng4onnx>=1.0.1",  # required by 'onnx2tf' package
                 "onnx_graphsurgeon>=0.3.26",  # required by 'onnx2tf' package
                 "ai-edge-litert>=1.2.0,<1.4.0",  # required by 'onnx2tf' package
-                "onnx>=1.12.0,<1.18.0",
+                "onnx>=1.12.0",
                 "onnx2tf>=1.26.3",
-                "onnxslim>=0.1.59",
+                "onnxslim>=0.1.65",
                 "onnxruntime-gpu" if cuda else "onnxruntime",
                 "protobuf>=5",
             ),

{ultralytics-8.3.186 → ultralytics-8.3.188}/ultralytics/engine/results.py

@@ -222,12 +222,9 @@ class Results(SimpleClass, DataExportMixin):
         save_txt: Save detection results to a text file.
         save_crop: Save cropped detection images to specified directory.
         summary: Convert inference results to a summarized dictionary.
-        to_df: Convert detection results to a Pandas Dataframe.
+        to_df: Convert detection results to a Polars Dataframe.
         to_json: Convert detection results to JSON format.
         to_csv: Convert detection results to a CSV format.
-        to_xml: Convert detection results to XML format.
-        to_html: Convert detection results to HTML format.
-        to_sql: Convert detection results to an SQL-compatible format.
 
     Examples:
         >>> results = model("path/to/image.jpg")

{ultralytics-8.3.186 → ultralytics-8.3.188}/ultralytics/engine/trainer.py

@@ -540,10 +540,10 @@ class BaseTrainer:
             torch.cuda.empty_cache()
 
     def read_results_csv(self):
-        """Read results.csv into a dictionary using pandas."""
-        import pandas as pd  # scope for faster 'import ultralytics'
+        """Read results.csv into a dictionary using polars."""
+        import polars as pl  # scope for faster 'import ultralytics'
 
-        return pd.read_csv(self.csv).to_dict(orient="list")
+        return pl.read_csv(self.csv).to_dict(as_series=False)
 
     def _model_train(self):
         """Set model in training mode."""

{ultralytics-8.3.186 → ultralytics-8.3.188}/ultralytics/models/rtdetr/val.py

@@ -196,7 +196,8 @@ class RTDETRValidator(DetectionValidator):
                 with bounding box coordinates, confidence scores, and class predictions.
             pbatch (Dict[str, Any]): Batch dictionary containing 'imgsz', 'ori_shape', 'ratio_pad', and 'im_file'.
         """
-        stem = Path(pbatch["im_file"]).stem
+        path = Path(pbatch["im_file"])
+        stem = path.stem
         image_id = int(stem) if stem.isnumeric() else stem
         box = predn["bboxes"].clone()
         box[..., [0, 2]] *= pbatch["ori_shape"][1] / self.args.imgsz  # native-space pred
@@ -207,6 +208,7 @@ class RTDETRValidator(DetectionValidator):
             self.jdict.append(
                 {
                     "image_id": image_id,
+                    "file_name": path.name,
                     "category_id": self.class_map[int(c)],
                     "bbox": [round(x, 3) for x in b],
                     "score": round(s, 5),

ultralytics-8.3.188/ultralytics/models/sam/__init__.py

@@ -0,0 +1,12 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+from .model import SAM
+from .predict import Predictor, SAM2DynamicInteractivePredictor, SAM2Predictor, SAM2VideoPredictor
+
+__all__ = (
+    "SAM",
+    "Predictor",
+    "SAM2Predictor",
+    "SAM2VideoPredictor",
+    "SAM2DynamicInteractivePredictor",
+)  # tuple or list of exportable items

{ultralytics-8.3.186 → ultralytics-8.3.188}/ultralytics/models/sam/modules/sam.py

@@ -574,7 +574,7 @@ class SAM2Model(torch.nn.Module):
             object_score_logits,
         )
 
-    def _use_mask_as_output(self, backbone_features, high_res_features, mask_inputs):
+    def _use_mask_as_output(self, mask_inputs, backbone_features=None, high_res_features=None):
         """Process mask inputs directly as output, bypassing SAM encoder/decoder."""
         # Use -10/+10 as logits for neg/pos pixels (very close to 0/1 in prob after sigmoid).
         out_scale, out_bias = 20.0, -10.0  # sigmoid(-10.0)=4.5398e-05
@@ -589,7 +589,7 @@ class SAM2Model(torch.nn.Module):
         )
         # a dummy IoU prediction of all 1's under mask input
         ious = mask_inputs.new_ones(mask_inputs.size(0), 1).float()
-        if not self.use_obj_ptrs_in_encoder:
+        if not self.use_obj_ptrs_in_encoder or backbone_features is None or high_res_features is None:
             # all zeros as a dummy object pointer (of shape [B, C])
             obj_ptr = torch.zeros(mask_inputs.size(0), self.hidden_dim, device=mask_inputs.device)
         else:
@@ -869,7 +869,6 @@ class SAM2Model(torch.nn.Module):
         prev_sam_mask_logits,
     ):
         """Perform a single tracking step, updating object masks and memory features based on current frame inputs."""
-        current_out = {"point_inputs": point_inputs, "mask_inputs": mask_inputs}
         # High-resolution feature maps for the SAM head, reshape (HW)BC => BCHW
         if len(current_vision_feats) > 1:
             high_res_features = [
@@ -883,7 +882,7 @@ class SAM2Model(torch.nn.Module):
             # (see it as a GT mask) without using a SAM prompt encoder + mask decoder.
             pix_feat = current_vision_feats[-1].permute(1, 2, 0)
             pix_feat = pix_feat.view(-1, self.hidden_dim, *feat_sizes[-1])
-            sam_outputs = self._use_mask_as_output(pix_feat, high_res_features, mask_inputs)
+            sam_outputs = self._use_mask_as_output(mask_inputs, pix_feat, high_res_features)
         else:
             # fused the visual feature with previous memory features in the memory bank
             pix_feat = self._prepare_memory_conditioned_features(
@@ -911,7 +910,7 @@ class SAM2Model(torch.nn.Module):
                 high_res_features=high_res_features,
                 multimask_output=multimask_output,
             )
-        return current_out, sam_outputs, high_res_features, pix_feat
+        return sam_outputs, high_res_features, pix_feat
 
     def _encode_memory_in_output(
         self,
@@ -960,7 +959,8 @@ class SAM2Model(torch.nn.Module):
         prev_sam_mask_logits=None,
     ):
         """Perform a single tracking step, updating object masks and memory features based on current frame inputs."""
-        current_out, sam_outputs, _, _ = self._track_step(
+        current_out = {}
+        sam_outputs, _, _ = self._track_step(
             frame_idx,
             is_init_cond_frame,
             current_vision_feats,