This Pull Request fixes the edge case in the CTD pipeline when the conditions passed to the CTDInferenceRunner.predict() method are empty. This typically can happen when the FilterLowConfidencePoses processing stage filters out all poses.
Thus, this Pull Request solves #3001.

The following changes were introduced to fix the edge case:

• Always add a "model_kwargs" item to the context in the ConditionalKeypointsToModelInputs preprocessing stage, even in the case of empty conditions. This parameter is expected in downstream inference stages.
• Shortcut the prediction and return an empty poses list in the CTDInferenceRunner when the received conditions are empty.

• Additionally, the TopDownCrop processing stage has been modified to always output images of the cropped shape, even in the case of an empty context["bboxes"] list. The first dimension length of the returned images (corresponding to the number of bounding boxes) obviously remains 0 in that case.