What does mean «train_config» → «from_detection_checkpoint» in TensorFlow?

dmitrii_fediuk · May 16, 2019, 5:04am

tensorflow/models/blob/v1.13.0/research/object_detection/samples/configs/faster_rcnn_resnet101_coco.config#L107-L107


from_detection_checkpoint: true

dmitrii_fediuk · May 16, 2019, 5:05am

github.com

tensorflow/models/blob/v1.13.0/research/object_detection/protos/train.proto#L40-L45


      
          // [Deprecated]: use fine_tune_checkpoint_type instead.
          // Specifies if the finetune checkpoint is from an object detection model.
          // If from an object detection model, the model being trained should have
          // the same parameters with the exception of the num_classes parameter.
          // If false, it assumes the checkpoint was a object classification model.
          optional bool from_detection_checkpoint = 8 [default=false, deprecated=true];

If you want to fine tune a trained detection checkpoint, then you should assign a detection ckpt path to fine_tune_checkpoint and set from_detection_checkpoint to true.

If you want to load a pre-trained classification checkpoint to initialize your training, you should provide a classification ckpt path to fine_tune_checkpoint and set from_detection_checkpoint to false.

github.com/tensorflow/models/issues/3562#issuecomment-372703559