Skip to content

GitLab

Commit c57621da authored by A. Unique TensorFlower's avatar A. Unique TensorFlower Committed by TF Object Detection Team
Browse files

Explicitly specify the parameters when calling provide_groundtruth. 

PiperOrigin-RevId: 382236941
parent 661248a2
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
research/object_detection/legacy/evaluator.py
View file @ c57621da
...@@ -122,7 +122,8 @@ def _extract_predictions_and_losses(model, ...@@ -122,7 +122,8 @@ def _extract_predictions_and_losses(model,
[input_dict[fields.InputDataFields.groundtruth_boxes]], [input_dict[fields.InputDataFields.groundtruth_boxes]],
[tf.one_hot(input_dict[fields.InputDataFields.groundtruth_classes] [tf.one_hot(input_dict[fields.InputDataFields.groundtruth_classes]
- label_id_offset, depth=model.num_classes)], - label_id_offset, depth=model.num_classes)],
groundtruth_masks_list, groundtruth_keypoints_list) groundtruth_masks_list=groundtruth_masks_list,
groundtruth_keypoints_list=groundtruth_keypoints_list)
losses_dict.update(model.loss(prediction_dict, true_image_shapes)) losses_dict.update(model.loss(prediction_dict, true_image_shapes))
result_dict = eval_util.result_dict_for_single_example( result_dict = eval_util.result_dict_for_single_example(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment