simba-uw-tf-dev 5.3.2__tar.gz → 5.3.4__tar.gz

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: simba_uw_tf_dev
-Version: 5.3.2
+Version: 5.3.4
 Summary: Toolkit for computer classification and analysis of behaviors in experimental animals
 Home-page: https://github.com/sgoldenlab/simba
 Author: Simon Nilsson, Jia Jie Choong, Sophia Hwang

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/setup.py

@@ -29,7 +29,7 @@ with open(GPU_REQUIREMENTS_PATH, "r") as f:
 # Setup configuration
 setuptools.setup(
     name="simba_uw_tf_dev",
-    version="5.3.2",
+    version="5.3.4",
     author="Simon Nilsson, Jia Jie Choong, Sophia Hwang",
     author_email="sronilsson@gmail.com",
     description="Toolkit for computer classification and analysis of behaviors in experimental animals",

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/simba/SimBA.py

@@ -57,9 +57,10 @@ from simba.ui.import_pose_frame import ImportPoseFrame
 from simba.ui.import_videos_frame import ImportVideosFrame
 from simba.ui.machine_model_settings_ui import MachineModelSettingsPopUp
 from simba.ui.pop_ups.about_simba_pop_up import AboutSimBAPopUp
-from simba.ui.pop_ups.animal_directing_other_animals_pop_up import AnimalDirectingAnimalPopUp
-from simba.ui.pop_ups.roi_directing_visualizer_pop_up import DirectingROIVisualizerPopUp
-from simba.ui.pop_ups.animal_directing_roi_pop_up import AnimalDirectingROIPopUp
+from simba.ui.pop_ups.animal_directing_other_animals_pop_up import \
+    AnimalDirectingAnimalPopUp
+from simba.ui.pop_ups.animal_directing_roi_pop_up import \
+    AnimalDirectingROIPopUp
 from simba.ui.pop_ups.annotated_bouts_videos_pop_up import \
     AnnotatedBoutsVideoPopUp
 from simba.ui.pop_ups.append_roi_features_animals_pop_up import \
@@ -146,6 +147,8 @@ from simba.ui.pop_ups.roi_aggregate_stats_popup import \
     ROIAggregateDataAnalyzerPopUp
 from simba.ui.pop_ups.roi_analysis_time_bins_pop_up import \
     ROIAnalysisTimeBinsPopUp
+from simba.ui.pop_ups.roi_directing_visualizer_pop_up import \
+    DirectingROIVisualizerPopUp
 from simba.ui.pop_ups.roi_features_plot_pop_up import VisualizeROIFeaturesPopUp
 from simba.ui.pop_ups.roi_tracking_plot_pop_up import VisualizeROITrackingPopUp
 from simba.ui.pop_ups.roi_video_table_pop_up import ROIVideoTable

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/simba/assets/.recent_projects.txt

@@ -1,3 +1,4 @@
+G:/projects/edmayelle/superanimal_multianimal_project/project_folder/project_config.ini
 D:/troubleshooting/open_field_rearing/project_folder/project_config.ini
 F:/troubleshooting/varsha/project_folder/project_config.ini
 E:/troubleshooting/mitra/project_folder/project_config.ini

simba_uw_tf_dev-5.3.4/simba/assets/ppyoloe_plus_crn_s_80e_coco.yml

@@ -0,0 +1,15 @@
+_BASE_: [
+  '../datasets/coco_detection.yml',
+  '../runtime.yml',
+  './_base_/optimizer_80e.yml',
+  './_base_/ppyoloe_plus_crn.yml',
+  './_base_/ppyoloe_plus_reader.yml',
+]
+
+log_iter: 100
+snapshot_epoch: 5
+weights: output/ppyoloe_plus_crn_s_80e_coco/model_final
+
+pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/pretrained/ppyoloe_crn_s_obj365_pretrained.pdparams
+depth_mult: 0.33
+width_mult: 0.50

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/simba/mixins/plotting_mixin.py

@@ -586,8 +586,10 @@ class PlottingMixin(object):
                                    legend_lbl: str = "location (seconds)",
                                    heatmap_opacity: Optional[float] = 0.99,
                                    color_legend: bool = True,
-                                   leg_width: Optional[int] = None) -> Union[np.ndarray, None]:
+                                   leg_width: Optional[int] = None,
+                                   hh_mm_ss: bool = False) -> Union[np.ndarray, None]:
 
+        check_valid_boolean(value=hh_mm_ss, source=f'{PlottingMixin.make_location_heatmap_plot.__name__} hh_mm_ss', raise_error=True)
         cum_df = pd.DataFrame(frm_data).reset_index()
         cum_df = cum_df.melt(id_vars="index", value_vars=None, var_name=None, value_name="seconds", col_level=None).rename(columns={"index": "vertical_idx", "variable": "horizontal_idx"})
         below_min = cum_df["seconds"] < min_seconds if min_seconds is not None else pd.Series(False, index=cum_df.index)
@@ -653,6 +655,13 @@ class PlottingMixin(object):
             cb.ax.yaxis.set_major_locator(MaxNLocator(integer=True))
 
             def _legend_formatter(x, pos):
+                if hh_mm_ss:
+                    from simba.utils.read_write import seconds_to_timestamp
+                    if x >= max_scale - 1e-9:
+                        return f">{seconds_to_timestamp(max_scale)}"
+                    if min_seconds is not None and x <= vmin_plot + 1e-9:
+                        return f"<{seconds_to_timestamp(min_seconds)}"
+                    return seconds_to_timestamp(float(x))
                 if x >= max_scale - 1e-9:
                     return f">{int(round(max_scale))}"
                 if min_seconds is not None and x <= vmin_plot + 1e-9:
@@ -1251,6 +1260,7 @@ class PlottingMixin(object):
                   grid: bool = True,
                   bg_clr: str = 'white',
                   line_width: float = 1.5,
+                  line_opacity: float = 1.0,
                   save_path: Optional[Union[str, os.PathLike]] = None,
                   dpi: Optional[int] = None,
                   tight_layout: bool = True,
@@ -1264,7 +1274,9 @@ class PlottingMixin(object):
                   markersize: Optional[float] = None,
                   linestyle: Optional[Union[str, List[str]]] = None,
                   save_kwargs: Optional[Dict[str, Any]] = None,
-                  svg: bool = False):
+                  svg: bool = False,
+                  x_tick_lbl_rotation: Optional[int] = None,
+                  x_tick_interval: Optional[int] = None):
         """
         Line plot from DataFrame with optional error bands.
 
@@ -1287,6 +1299,7 @@ class PlottingMixin(object):
         check_str(name=f"{PlottingMixin.line_plot.__name__} x", value=x, options=tuple(df.columns))
         check_instance(source=f"{PlottingMixin.line_plot.__name__} y", instance=y, accepted_types=(str, list))
         check_float(name=f"{PlottingMixin.line_plot.__name__} line_width", value=line_width, allow_zero=False, allow_negative=False, raise_error=True)
+        check_float(name=f"{PlottingMixin.line_plot.__name__} line_opacity", value=line_opacity, min_value=0.0, max_value=1.0)
         check_valid_boolean(value=grid, source=f"{PlottingMixin.line_plot.__name__} grid", raise_error=True)
         check_str(name=f"{PlottingMixin.line_plot.__name__} bg_clr", value=bg_clr.lower(), options=tuple(get_named_colors()))
         bg_clr = bg_clr.lower()
@@ -1311,6 +1324,10 @@ class PlottingMixin(object):
             if len(linestyle) != len(y):
                 raise ValueError(f"{PlottingMixin.line_plot.__name__} linestyle list length must match number of y series ({len(y)}).")
         check_valid_boolean(value=svg, source=f"{PlottingMixin.line_plot.__name__} svg", raise_error=True)
+        if x_tick_lbl_rotation is not None:
+            check_int(name=f"{PlottingMixin.line_plot.__name__} x_tick_lbl_rotation", value=x_tick_lbl_rotation, min_value=0, max_value=360)
+        if x_tick_interval is not None:
+            check_int(name=f"{PlottingMixin.line_plot.__name__} x_tick_interval", value=x_tick_interval, min_value=1)
         if grid:
             sns.set_style(style="whitegrid", rc={"grid.linestyle": "--"})
         else:
@@ -1341,7 +1358,7 @@ class PlottingMixin(object):
         colors = sns.color_palette(palette, n_colors=len(y))
         for i in range(len(y)):
             ls = linestyle[i] if isinstance(linestyle, list) else linestyle
-            plot_kw = dict(data=df, x=x, y=y[i], label=y[i], color=colors[i], linewidth=line_width)
+            plot_kw = dict(data=df, x=x, y=y[i], label=y[i], color=colors[i], linewidth=line_width, alpha=line_opacity)
             if marker is not None:
                 plot_kw['marker'] = marker
             if ls is not None:
@@ -1373,6 +1390,12 @@ class PlottingMixin(object):
         elif legend_loc is not None and ax.legend_ is not None:
             ax.legend(loc=legend_loc, fontsize=font_size)
         ax.grid(grid)
+        if x_tick_interval is not None:
+            x_vals = df[x].values
+            ax.set_xticks(range(0, len(x_vals), x_tick_interval))
+            ax.set_xticklabels(x_vals[::x_tick_interval])
+        if x_tick_lbl_rotation is not None:
+            plt.setp(ax.get_xticklabels(), rotation=x_tick_lbl_rotation, ha='right')
         if tight_layout:
             fig.tight_layout()
         if save_path is not None:

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/simba/mixins/pose_importer_mixin.py

@@ -35,9 +35,28 @@ class PoseImporterMixin(object):
                                    animal_bp_dict: dict,
                                    video_info: dict,
                                    data_df: pd.DataFrame,
-                                   video_path: Union[str, os.PathLike]):
+                                   video_path: Union[str, os.PathLike],
+                                   initial_frame_no: Optional[int] = None):
+        """
+        :param Optional[int] initial_frame_no: Frame index to start the assignment UI on.
+            Useful for jumping directly to a frame where all animals are simultaneously
+            detected, so the user doesn't have to press "x" repeatedly to find one.
+            If ``None`` (default) the UI starts at frame 0, preserving previous behaviour.
+            Clamped to the valid range ``[0, len(data_df) - 1]``; out-of-range values
+            emit a :class:`FrameRangeWarning` and fall back to 0.
+        """
 
-        self.video_info, self.data_df, self.frame_no, self.add_spacer = (video_info, data_df, 0, 2)
+        start_frame = 0
+        if initial_frame_no is not None:
+            if not isinstance(initial_frame_no, int) or initial_frame_no < 0 or initial_frame_no >= len(data_df):
+                FrameRangeWarning(
+                    msg=(f"initial_frame_no={initial_frame_no} is outside the valid range "
+                         f"[0, {len(data_df) - 1}] for this video; starting at frame 0 instead."),
+                    source=self.__class__.__name__,
+                )
+            else:
+                start_frame = initial_frame_no
+        self.video_info, self.data_df, self.frame_no, self.add_spacer = (video_info, data_df, start_frame, 2)
         self.animal_bp_dict, self.cap = animal_bp_dict, cv2.VideoCapture(video_path)
         _, self.video_name, _ = get_fn_ext(video_path)
         self.get_video_scalers(video_info=video_info)
@@ -152,7 +171,7 @@ class PoseImporterMixin(object):
         for animal_cnt, (animal_name, animal_bps) in enumerate(self.animal_bp_dict.items()):
             self.img_bp_cords[animal_name] = []
             for x_name, y_name in zip(animal_bps["X_bps"], animal_bps["Y_bps"]):
-                self.img_bp_cords[animal_name].append(tuple(self.data_df.loc[self.frame_no, [x_name, y_name]].values.astype(int)))
+                self.img_bp_cords[animal_name].append(tuple(self.data_df.loc[self.frame_no, [x_name, y_name]].values.astype(np.int32)))
         self.insert_all_bodyparts_into_img(img=self.img_overlay, body_parts=self.img_bp_cords)
         side_img = np.ones((int(self.video_info["height"] / 2), self.video_info["width"], 3))
         cv2.putText(side_img, f"Current video: {self.video_name}", (10, self.scalers["space"]), cv2.FONT_HERSHEY_SIMPLEX, self.scalers["font"], (255, 255, 255), 2)
@@ -237,20 +256,25 @@ class PoseImporterMixin(object):
         self.animal_order = {}
         for animal_number, animal_click_data in self.id_cords.items():
             animal_name, animal_cord = (animal_click_data["name"], animal_click_data["cord"])
-            closest_animal = {}
-            closest_animal["animal_name"] = None
-            closest_animal["body_part_name"] = None
-            closest_animal["distance"] = np.inf
+            closest_animal = {"animal_name": None, "body_part_name": None, "distance": np.inf}
             for other_animal_name, animal_bps in self.animal_bp_dict.items():
                 animal_bp_names_x = self.animal_bp_dict[other_animal_name]["X_bps"]
                 animal_bp_names_y = self.animal_bp_dict[other_animal_name]["Y_bps"]
                 for x_col, y_col in zip(animal_bp_names_x, animal_bp_names_y):
-                    bp_location = (int(self.all_frame_data[x_col]), int(self.all_frame_data[y_col]))
-                    distance = np.sqrt((animal_cord[0] - bp_location[0]) ** 2 + (animal_cord[1] - bp_location[1]) ** 2)
+                    bp_x, bp_y = self.all_frame_data[x_col], self.all_frame_data[y_col]
+                    distance = np.sqrt((animal_cord[0] - bp_x) ** 2 + (animal_cord[1] - bp_y) ** 2)
                     if distance < closest_animal["distance"]:
                         closest_animal["animal_name"] = other_animal_name
                         closest_animal["body_part_name"] = (x_col, y_col)
                         closest_animal["distance"] = distance
+            if closest_animal["animal_name"] is None:
+                raise InvalidInputError(
+                    msg=(f'No tracked body-parts found on frame {self.frame_no} for click number '
+                         f'{animal_number} ({animal_name}): every body-part of every animal is NaN at '
+                         f'this frame. Press "x" to step to a frame where at least one body-part per '
+                         f'animal is tracked, then assign identities.'),
+                    source=self.__class__.__name__,
+                )
             self.animal_order[animal_number] = closest_animal
         self.check_intergity_of_chosen_animal_order()
         self.organize_results()

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/simba/model/yolo_fit.py

@@ -33,7 +33,6 @@ from simba.utils.yolo import load_yolo_model
 YOLO_M_PATH = "https://huggingface.co/Ultralytics/YOLO11/resolve/main/yolo11m-pose.pt"
 
 
-
 class FitYolo():
 
     """
@@ -44,12 +43,6 @@ class FitYolo():
        - Download starter weights from `HuggingFace <https://huggingface.co/Ultralytics>`__.
        - Example dataset YAMLs: `bbox <https://github.com/sgoldenlab/simba/blob/master/misc/ex_yolo_model.yaml>`__, `pose <https://github.com/sgoldenlab/simba/blob/master/misc/ex_yolo_model_keypoints.yaml>`__.
 
-    .. important::
-       When fitting a **segmentation** model, the ``imgsz`` parameter is critical for mask quality. Segmentation
-       requires pixel-level precision along object boundaries, so spatial detail lost to downscaling hurts
-       segmentation far more than detection or pose tasks. Set ``imgsz`` as large as your GPU memory allows.
-       The default ``640`` may be too coarse for high-quality segmentation masks.
-
     .. seealso::
        :func:`simba.bounding_box_tools.yolo.utils.fit_yolo` for the functional API.
        :func:`simba.bounding_box_tools.yolo.utils.load_yolo_model` to load trained weights.
@@ -98,11 +91,20 @@ class FitYolo():
                  device:  Union[Literal['cpu'], int] = 0,
                  verbose: bool = True,
                  workers: int = 8,
-                 patience: int = 300):
+                 patience: int = 500,
+                 device_id: Optional[int] = None):
 
         os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
-        if not _is_cuda_available()[0]:
+        gpu_available, gpus = _is_cuda_available()
+        if not gpu_available:
             raise SimBAGPUError(msg='No GPU detected.', source=self.__class__.__name__)
+        if device_id is not None:
+            check_int(name=f'{self.__class__.__name__} device_id', value=device_id, min_value=0)
+            gpu_ids = list(gpus.keys())
+            if device_id not in gpu_ids:
+                raise SimBAGPUError(msg=f'GPU device_id {device_id} not found. Available GPU id(s): {gpu_ids}', source=self.__class__.__name__)
+            os.environ["CUDA_VISIBLE_DEVICES"] = str(device_id)
+            device = 0
         if YOLO is None:
             raise SimBAPAckageVersionError(msg='Ultralytics package not detected.', source=self.__class__.__name__)
         if weights_path is not None:
@@ -155,77 +157,72 @@ class FitYolo():
                         patience=self.patience)
 
 
-if __name__ == "__main__" and not hasattr(sys, 'ps1'):
-    parser = argparse.ArgumentParser(description="Fit YOLO model using ultralytics package.")
-    parser.add_argument('--weights_path', type=str, default=None, help='Path to the trained YOLO model weights (e.g., yolo11n-pose.pt). Omit to download default starter weights.')
-    parser.add_argument('--model_yaml', type=str, required=True, help='Path to map.yaml (model structure and label definitions)')
-    parser.add_argument('--save_path', type=str, required=True, help='Directory where trained model and logs will be saved')
-    parser.add_argument('--epochs', type=int, default=25, help='Number of epochs to train the model. Default is 25')
-    parser.add_argument('--batch', type=int, default=16, help='Batch size for training. Default is 16')
-    parser.add_argument('--plots', type=lambda x: str(x).lower() == 'true', default=True, help='Whether to plot training results. Use "True" or "False". Default is True')
-    parser.add_argument('--imgsz', type=int, default=640, help='Image size for training. Default is 640')
-    parser.add_argument('--format', type=str, default=None,  help=f'Format of the YOLO model. Must be one of: {", ".join(Options.VALID_YOLO_FORMATS.value)}')
-    parser.add_argument('--device', type=str, default='0', help='Device to train on. Use "cpu" or GPU index (e.g., "0"). Default is "0"')
-    parser.add_argument('--verbose', type=lambda x: str(x).lower() == 'true', default=True, help='Print verbose messages. Use "True" or "False". Default is True')
-    parser.add_argument('--workers', type=int, default=8, help='Number of data loader workers. Default is 8. Use -1 for max cores')
-    parser.add_argument('--patience', type=int, default=100, help='Number of epochs to wait without improvement in validation metrics before early stopping the training. Default is 100')
-
-    args = parser.parse_args()
-
-    yolo_fitter = FitYolo(weights_path=args.weights_path,
-                          model_yaml=args.model_yaml,
-                          save_path=args.save_path,
-                          epochs=args.epochs,
-                          batch=args.batch,
-                          plots=args.plots,
-                          imgsz=args.imgsz,
-                          format=args.format,
-                          device=int(args.device) if args.device != 'cpu' else 'cpu',
-                          verbose=args.verbose,
-                          workers=args.workers,
-                          patience=args.patience)
-    yolo_fitter.run()
-
-
-#
-# fitter = FitYolo(weights_path=r"C:\Users\sroni\Downloads\yolo26n-seg.pt",
-#                  model_yaml=r"E:\open_video\open_field_2\yolo_seg_project\map.yaml",
-#                  save_path=r'E:\open_video\open_field_2\yolo_seg_project\mdl',
-#                  epochs=1500,
-#                  batch=2,
-#                  workers=1,
-#                  format=None,
-#                  device=0,
-#                  imgsz=1248)
-# fitter.run()
+# if __name__ == "__main__" and not hasattr(sys, 'ps1'):
+#     parser = argparse.ArgumentParser(description="Fit YOLO model using ultralytics package.")
+#     parser.add_argument('--weights_path', type=str, default=None, help='Path to the trained YOLO model weights (e.g., yolo11n-pose.pt). Omit to download default starter weights.')
+#     parser.add_argument('--model_yaml', type=str, required=True, help='Path to map.yaml (model structure and label definitions)')
+#     parser.add_argument('--save_path', type=str, required=True, help='Directory where trained model and logs will be saved')
+#     parser.add_argument('--epochs', type=int, default=25, help='Number of epochs to train the model. Default is 25')
+#     parser.add_argument('--batch', type=int, default=16, help='Batch size for training. Default is 16')
+#     parser.add_argument('--plots', type=lambda x: str(x).lower() == 'true', default=True, help='Whether to plot training results. Use "True" or "False". Default is True')
+#     parser.add_argument('--imgsz', type=int, default=640, help='Image size for training. Default is 640')
+#     parser.add_argument('--format', type=str, default=None,  help=f'Format of the YOLO model. Must be one of: {", ".join(Options.VALID_YOLO_FORMATS.value)}')
+#     parser.add_argument('--device', type=str, default='0', help='Device to train on. Use "cpu" or GPU index (e.g., "0"). Default is "0"')
+#     parser.add_argument('--verbose', type=lambda x: str(x).lower() == 'true', default=True, help='Print verbose messages. Use "True" or "False". Default is True')
+#     parser.add_argument('--workers', type=int, default=8, help='Number of data loader workers. Default is 8. Use -1 for max cores')
+#     parser.add_argument('--patience', type=int, default=100, help='Number of epochs to wait without improvement in validation metrics before early stopping the training. Default is 100')
 #
-
+#     args = parser.parse_args()
 #
-# fitter = FitYolo(weights_path=r"F:\yolo_weights\yolo26n.pt",
-#                  model_yaml=r"F:\irondog\data\yolo\map.yaml",
-#                  save_path=r"F:\irondog\data\yolo\mdl",
-#                  epochs=1500,
-#                  batch=16,
-#                  workers=3,
-#                  format=None,
-#                  device=0,
-#                  imgsz=256)
+#     yolo_fitter = FitYolo(weights_path=args.weights_path,
+#                           model_yaml=args.model_yaml,
+#                           save_path=args.save_path,
+#                           epochs=args.epochs,
+#                           batch=args.batch,
+#                           plots=args.plots,
+#                           imgsz=args.imgsz,
+#                           format=args.format,
+#                           device=int(args.device) if args.device != 'cpu' else 'cpu',
+#                           verbose=args.verbose,
+#                           workers=args.workers,
+#                           patience=args.patience)
+#     yolo_fitter.run()
+
+
+
+# fitter = FitYolo(weights_path=r"/home/cat/simon/yolo_0413/yolo26s.pt",
+#                   model_yaml=r"/home/cat/simon/yolo_0413/map.yaml",
+#                   save_path=r'/home/cat/simon/yolo_0413/mdl',
+#                   epochs=5000,
+#                   batch=2000,
+#                   format=None,
+#                   device_id=0,
+#                   imgsz=256)
 # fitter.run()
-#
 
 
-
-# fitter = FitYolo(weights_path=r"C:\Users\sroni\Downloads\yolo26n.pt",
-#                  model_yaml=r"E:\litpose_yolo\bbox\map.yaml",
-#                  save_path=r'E:\litpose_yolo\bbox\mdl',
-#                  epochs=1500,
-#                  batch=16,
-#                  format=None,
-#                  device=0,
-#                  imgsz=196)
-# fitter.run()
+# if __name__ == "__main__":
+#     parser = argparse.ArgumentParser(description="Fit YOLO model")
+#     parser.add_argument('--weights_path', type=str, default=r"/home/cat/simon/yolo_0413/yolo26s.pt")
+#     parser.add_argument('--model_yaml', type=str, default=r"/home/cat/simon/yolo_0413/map.yaml")
+#     parser.add_argument('--save_path', type=str, default=r'/home/cat/simon/yolo_0413/mdl')
+#     parser.add_argument('--epochs', type=int, default=3000)
+#     parser.add_argument('--batch', type=int, default=2000)
+#     parser.add_argument('--imgsz', type=int, default=256)
+#     parser.add_argument('--device_id', type=int, default=0)
+#     parser.add_argument('--patience', type=int, default=500)
+#     args = parser.parse_args()
 #
-
+#     fitter = FitYolo(weights_path=args.weights_path,
+#                       model_yaml=args.model_yaml,
+#                       save_path=args.save_path,
+#                       epochs=args.epochs,
+#                       batch=args.batch,
+#                       format=None,
+#                       imgsz=args.imgsz,
+#                       patience=args.patience,
+#                       device_id=args.device_id)
+#     fitter.run()
 
 
 # fitter = FitYolo(weights_path=r"D:\maplight_tg2576_yolo\yolo_mdl\original_weight_oct\best.pt",
@@ -296,4 +293,4 @@ if __name__ == "__main__" and not hasattr(sys, 'ps1'):
 #                  format=None,
 #                  device=0,
 #                  imgsz=640)
-# fitter.run()
+# fitter.run()

{simba_uw_tf_dev-5.3.2 → simba_uw_tf_dev-5.3.4}/simba/plotting/directing_animals_visualizer.py

@@ -3,7 +3,6 @@ __author__ = "Simon Nilsson; sronilsson@gmail.com"
 import os
 from typing import Any, Dict, Optional, Union
 
-
 import cv2
 import numpy as np