diff --git a/deeplabcut/pose_estimation_pytorch/apis/evaluation.py b/deeplabcut/pose_estimation_pytorch/apis/evaluation.py
index f9b02e2c78..f4f0ec91c5 100755
--- a/deeplabcut/pose_estimation_pytorch/apis/evaluation.py
+++ b/deeplabcut/pose_estimation_pytorch/apis/evaluation.py
@@ -114,6 +114,7 @@ def evaluate(
     comparison_bodyparts: str | list[str] | None = None,
     per_keypoint_evaluation: bool = False,
     pcutoff: float | list[float] = 0.6,
+    force_multi_animal: bool = False,
 ) -> tuple[dict[str, float], dict[str, dict[str, np.ndarray]]]:
     """
     Args:
@@ -134,6 +135,9 @@ def evaluate(
         pcutoff: Confidence threshold for RMSE computation. If a list is provided,
             there should be one value for each bodypart and one value for each unique
             bodypart (if there are any).
+        force_multi_animal: If False - the scenario (single- or multi-animal) is inferred from the loader.
+            If True - the multi-animal is used during evaluation, even if the loader contains only a single animal.
+
 
     Returns:
         A dict containing the evaluation results
@@ -201,7 +205,7 @@ def evaluate(
     results = metrics.compute_metrics(
         gt_pose,
         pred_pose,
-        single_animal=parameters.max_num_animals == 1,
+        single_animal=False if force_multi_animal else parameters.max_num_animals == 1,
         pcutoff=pcutoff,
         unique_bodypart_poses=pred_unique,
         unique_bodypart_gt=gt_unique,
diff --git a/deeplabcut/pose_estimation_pytorch/data/cocoloader.py b/deeplabcut/pose_estimation_pytorch/data/cocoloader.py
index f086cfd4ee..1fc6ed6f05 100644
--- a/deeplabcut/pose_estimation_pytorch/data/cocoloader.py
+++ b/deeplabcut/pose_estimation_pytorch/data/cocoloader.py
@@ -29,6 +29,7 @@ class COCOLoader(Loader):
     """
     Attributes:
         project_root: root directory path of the COCO project.
+        model_config_path: path to the pytorch_config.yaml file
         train_json_filename: the name of the json file containing the train annotations
         test_json_filename: the name of the json file containing the train annotations.
             None if there is no test set.
@@ -79,7 +80,9 @@ def get_dataset_parameters(self) -> PoseDatasetParameters:
                 bodyparts=bodyparts,
                 unique_bpts=[],
                 individuals=[f"individual{i}" for i in range(num_individuals)],
-                with_center_keypoints=self.model_cfg.get("with_center_keypoints", False),
+                with_center_keypoints=self.model_cfg.get(
+                    "with_center_keypoints", False
+                ),
                 color_mode=self.model_cfg.get("color_mode", "RGB"),
                 top_down_crop_size=(crop_w, crop_h),
                 top_down_crop_margin=crop_margin,
@@ -262,15 +265,15 @@ def load_data(self, mode: str = "train") -> dict:
             annotations_per_image[image_id] = individual_idx + 1
 
         filter_annotations = []
-        for annotation in data['annotations']:
-            keypoints = annotation['keypoints']
-            bbox = annotation['bbox']
+        for annotation in data["annotations"]:
+            keypoints = annotation["keypoints"]
+            bbox = annotation["bbox"]
             if np.all(keypoints <= 0) or len(bbox) == 0:
                 continue
             filter_annotations.append(annotation)
 
-        data["annotations"] = filter_annotations        
-        
+        data["annotations"] = filter_annotations
+
         # FIXME: why estimating bbox when there are already bbox?
         annotations_with_bbox = self._compute_bboxes(
             data["images"],
diff --git a/deeplabcut/pose_estimation_pytorch/data/dlcloader.py b/deeplabcut/pose_estimation_pytorch/data/dlcloader.py
index c8f43d007e..bd61c59f31 100644
--- a/deeplabcut/pose_estimation_pytorch/data/dlcloader.py
+++ b/deeplabcut/pose_estimation_pytorch/data/dlcloader.py
@@ -25,6 +25,7 @@
 from deeplabcut.pose_estimation_pytorch.data.base import Loader
 from deeplabcut.pose_estimation_pytorch.data.dataset import PoseDatasetParameters
 from deeplabcut.pose_estimation_pytorch.data.snapshots import Snapshot
+from deeplabcut.pose_estimation_pytorch.data.utils import bbox_from_keypoints
 from deeplabcut.pose_estimation_pytorch.data.utils import read_image_shape_fast
 
 
@@ -481,7 +482,42 @@ def to_coco(
                         }
                     )
 
-        return {"annotations": anns, "categories": categories, "images": images}
+        coco_dict = {"annotations": anns, "categories": categories, "images": images}
+        coco_dict = DLCLoader._add_bbox_annotations(coco_dict)
+        coco_dict = DLCLoader._remove_nans(coco_dict)
+        return coco_dict
+
+    @staticmethod
+    def _add_bbox_annotations(coco_dict: dict) -> dict:
+        for annotation in coco_dict.get("annotations", []):
+            if "bbox" not in annotation:
+                image = [
+                    img
+                    for img in coco_dict.get("images")
+                    if img.get("id") == annotation.get("image_id")
+                ][0]
+                bbox = bbox_from_keypoints(
+                    keypoints=np.array(
+                        annotation["keypoints"]
+                    ),  # (..., num_keypoints, xy)
+                    image_h=image.get("height"),
+                    image_w=image.get("width"),
+                    margin=20,
+                )
+                annotation["bbox"] = list(bbox)
+        return coco_dict
+
+    @staticmethod
+    def _remove_nans(coco_dict: dict) -> dict:
+        # Iterate through annotations and fix keypoints
+        for annotation in coco_dict.get("annotations", []):
+            if "keypoints" in annotation:
+                for keypoint in annotation["keypoints"]:
+                    if any(isinstance(v, float) and np.isnan(v) for v in keypoint[:2]):
+                        keypoint[0] = 0.0  # Replace x with 0
+                        keypoint[1] = 0.0  # Replace y with 0
+                        keypoint[2] = 0.0  # Ensure visibility is also 0
+        return coco_dict
 
     @property
     def _dfs(self) -> dict[str, pd.DataFrame]: