Monitoring with tensorboard for yolov3 training not working

Please provide the following information when requesting support.

• Hardware (T4)
• Network Type (Yolov3)
• Training spec file

random_seed: 42
yolov3_config {
  big_anchor_shape: "[(114.94, 60.67), (159.06, 114.59), (297.59, 176.38)]"
  mid_anchor_shape: "[(42.99, 31.91), (79.57, 31.75), (56.80, 56.93)]"
  small_anchor_shape: "[(15.60, 13.88), (30.25, 20.25), (20.67, 49.63)]"
  matching_neutral_box_iou: 0.7
  arch: "resnet"
  nlayers: 18
  arch_conv_blocks: 2
  loss_loc_weight: 0.8
  loss_neg_obj_weights: 100.0
  loss_class_weights: 1.0
  freeze_bn: false
  #freeze_blocks: 0
  force_relu: false
}
training_config {
  batch_size_per_gpu: 4
  num_epochs: 80
  enable_qat: false
  checkpoint_interval: 1
  learning_rate {
  soft_start_annealing_schedule {
    min_learning_rate: 1e-6
    max_learning_rate: 1e-4
    soft_start: 0.1
    annealing: 0.5
    }
  }
  regularizer {
    type: L1
    weight: 3e-5
  }
  optimizer {
    adam {
      epsilon: 1e-7
      beta1: 0.9
      beta2: 0.999
      amsgrad: false
    }
  }
  pretrain_model_path: "/workspace/tao-experiments/yolo_v3/pretrained_resnet18/pretrained_object_detection_vresnet18/resnet_18.hdf5"
  visualizer{
    enabled: true
  }

}
eval_config {
  average_precision_mode: SAMPLE
  batch_size: 4
  matching_iou_threshold: 0.5
}
nms_config {
  confidence_threshold: 0.001
  clustering_iou_threshold: 0.5
  top_k: 200
  force_on_cpu: True
}
augmentation_config {
  hue: 0.1
  saturation: 1.5
  exposure:1.5
  vertical_flip:0
  horizontal_flip: 0.5
  jitter: 0.3
  output_width: 1248
  output_height: 384
  output_channel: 3
  randomize_input_shape_period: 0
}
dataset_config {
  data_sources: {
      tfrecords_path: "/workspace/tao-experiments/data/yolo_v3/kitti_trainval/kitti_trainval*"
      image_directory_path: "/workspace/tao-experiments/data/training"
  }
  include_difficult_in_training: true
  image_extension: "png"
  target_class_mapping {
      key: "car"
      value: "car"
  }
  target_class_mapping {
      key: "pedestrian"
      value: "pedestrian"
  }
  target_class_mapping {
      key: "cyclist"
      value: "cyclist"
  }
  target_class_mapping {
      key: "van"
      value: "car"
  }
  target_class_mapping {
      key: "person_sitting"
      value: "pedestrian"
  }
  validation_fold: 0
}

• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)
When we run training with yolov3 training tutorial notebook as i posted the link below

After stating the training , i tried to run the tensorboard monitoring with below command
tensorboard --logdir yolov3_init_test:training_home/yolo_v3/experiment_dir_unpruned/ --host 0.0.0.0 --port 8080

The directly is the parent directory of where the weights folder is there

But when i run the command i can able to access the tensorboard webpage
But i saw error in the terminal so i didn’t get any details in the page

The error is

Can you support on this

2 posts - 2 participants

Read full topic