Unable to see Validation loss in Tensorflow object detection API

Question

I am using tensorflow object detection api for last 1 year. As I am retraining my model again, I want to get a plot of validation loss. I don't see any validation loss plot in the tensorboard.

The training config looks like:

# Faster R-CNN with Inception Resnet v2, Atrous version;
# Configured for MSCOCO Dataset.
   train_input_reader: {
  tf_record_input_reader {
    input_path: "../data/train.record"
  }
  label_map_path: "../data/object-detection.pbtxt"
}

eval_config: {
  num_examples: 1000
  # Note: The below line limits the evaluation process to 10 evaluations.
  # Remove the below line to evaluate indefinitely.
  max_evals: 100
  visualization_export_dir: "../annotated"
  num_visualizations: 5
  eval_interval_secs: 3 
  metrics_set: "coco_detection_metrics"
}

eval_input_reader: {
  tf_record_input_reader {
    input_path: "../data/val.record"
  }
  label_map_path: "../data/object-detection.pbtxt"
  shuffle: false
  num_readers: 1
  num_epochs: 2
}

Is there anything wrong with the config file?

netanel-sam netanel-sam · Accepted Answer · 2019-02-28T14:55:26

Are you using the latest OD API? The validation loss is plotted both under "Loss" and under "loss". On the first you can see the total loss and the split between localization, classification and regularization, while the latter only shows the total loss. Note that "loss_1" and "loss_2" are both the training loss, not sure why it's plotted twice, and there aren't split plots for loc, cls and reg.

Unable to see Validation loss in Tensorflow object detection API

1 Answers