Return zero-pose for top-down models in absence of detections.

When the detector does not detect any crops (with a supra-threshold confidence), no pose-detection is applied and  and a zero-vector is returned for the pose-prediction.

This solves #137 and copies the already existing intended behavior of returning zeros for empty pose-predictions in single animals.

Author: deruyter92

dlclive/pose_estimation_pytorch/runner.py

@@ -202,9 +202,14 @@ def get_pose(self, frame: np.ndarray) -> np.ndarray:
 
             frame_batch, offsets_and_scales = self._prepare_top_down(tensor, detections)
             if len(frame_batch) == 0:
-                offsets_and_scales = [(0, 0), 1]
-            else:
-                tensor = frame_batch  # still CHW, batched
+                zero_pose = (
+                    np.zeros((self.n_bodyparts, 3)) 
+                    if self.n_individuals < 2 else 
+                    np.zeros((self.n_individuals, self.n_bodyparts, 3))
+                )
+                return zero_pose
+            
+            tensor = frame_batch  # still CHW, batched
 
         if self.dynamic is not None:
             tensor = self.dynamic.crop(tensor)