# Cannot train custom model, IndexError: list index (0) out of range

**URL:** <https://forums.developer.nvidia.com/t/cannot-train-custom-model-indexerror-list-index-0-out-of-range/257923>\
**Category:** TAO Toolkit\
**Created:** [June 26, 2023, 6:56pm UTC](https://forums.developer.nvidia.com/t/cannot-train-custom-model-indexerror-list-index-0-out-of-range/257923 "2023-06-26T18:56:09Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![natanel](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@natanel](https://forums.developer.nvidia.com/u/natanel)\
**Post date:** [June 26, 2023, 6:56pm UTC](https://forums.developer.nvidia.com/t/cannot-train-custom-model-indexerror-list-index-0-out-of-range/257923/1 "2023-06-26T18:56:09Z")

</div>

Hello, first time using TAO Toolkit, I’m trying to train a custom model for object detection on aerial imagery from a drone. I took the dataset from [here](https://universe.roboflow.com/igor-na/dota-v2.0---easy/dataset/7) in TFRecord format, and followed the instructions from the [tutorial](https://docs.nvidia.com/tao/tao-toolkit/text/object_detection/detectnet_v2.html#conversion-to-tfrecords-detectnet-v2), however when I run the command ` tao detectnet_v2 train -k custom_model -e ~/specs.txt` I get the following error:

```auto
Traceback (most recent call last):
  File "</usr/local/lib/python3.6/dist-packages/iva/detectnet_v2/scripts/train.py>", line 3, in <module>
  File "<frozen iva.detectnet_v2.scripts.train>", line 1022, in <module>
  File "<frozen iva.detectnet_v2.scripts.train>", line 1011, in <module>
  File "<decorator-gen-117>", line 2, in main
  File "<frozen iva.detectnet_v2.utilities.timer>", line 46, in wrapped_fn
  File "<frozen iva.detectnet_v2.scripts.train>", line 994, in main
  File "<frozen iva.detectnet_v2.scripts.train>", line 853, in run_experiment
  File "<frozen iva.detectnet_v2.scripts.train>", line 625, in train_gridbox
  File "<frozen iva.detectnet_v2.dataloader.build_dataloader>", line 273, in build_dataloader
  File "<frozen iva.detectnet_v2.dataloader.drivenet_dataloader>", line 491, in __init__
  File "<frozen iva.detectnet_v2.dataloader.drivenet_dataloader>", line 548, in _construct_data_sources
  File "<frozen iva.detectnet_v2.dataloader.drivenet_dataloader>", line 398, in __init__
  File "<frozen iva.detectnet_v2.dataloader.drivenet_dataloader>", line 439, in _get_max_image_size
IndexError: list index (0) out of range

```

Only solution I found was in [this thread](https://forums.developer.nvidia.com/t/error-when-training-detectnet-v2-resnet34-on-tfrecord-file/230464), but when I tried uploading the dataset to CVAT it stuck at 81%. Does anyone know what else I can try?

This is my spec file:

```auto
# Sample model config for to instantiate a resnet18 model with pretrained weights and freeze blocks 0, 1
# with all shortcuts having projection layers.
model_config {
  arch: "mobilenet_v2"
  pretrained_model_file: ''
  freeze_blocks: 0
  freeze_blocks: 1
  all_projections: False
  num_layers: 18
  use_pooling: False
  use_batch_norm: True
  dropout_rate: 0.0
  objective_set: {
    cov {}
    bbox {
      scale: 35.0
      offset: 0.5
    }
  }
}

################################################################################################################################################################

# Sample rasterizer configs to instantiate a 3 class bbox rasterizer
bbox_rasterizer_config {
  target_class_config {
    key: "airport"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "baseball-diamond"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "basketball-court"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "bridge"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "container-crane"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "ground-track-field"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "harbor"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "helicopter"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "helipad"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "large-vehicle"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "plane"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "roundabout"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "ship"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "small-vehicle"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "soccer-ball-field"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "storage-tank"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "swimming-pool"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "tennis-court"
    value: {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4
      cov_radius_y: 0.4
      bbox_min_radius: 1.0
    }
  }
  deadzone_radius: 0.67
}

################################################################################################################################################################

postprocessing_config {
  target_class_config {
    key: "airport"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "baseball-diamond"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "basketball-court"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "bridge"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "container-crane"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "ground-track-field"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "harbor"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "helicopter"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "helipad"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "large-vehicle"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "plane"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "roundabout"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "ship"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "small-vehicle"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "soccer-ball-field"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "storage-tank"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "swimming-pool"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
  target_class_config {
    key: "tennis-court"
    value: {
      clustering_config {
        coverage_threshold: 0.005
        dbscan_eps: 0.15
        dbscan_min_samples: 0.05
        minimum_bounding_box_height: 20
      }
    }
  }
}

################################################################################################################################################################

cost_function_config {
  target_classes {
    name: "airport"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "baseball-diamond"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "basketball-court"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "bridge"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "container-crane"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "ground-track-field"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "harbor"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "helicopter"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "helipad"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "large-vehicle"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "plane"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "roundabout"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "ship"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "small-vehicle"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "soccer-ball-field"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "storage-tank"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "swimming-pool"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  target_classes {
    name: "tennis-court"
    class_weight: 1.0
    coverage_foreground_weight: 0.05
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 10.0
    }
  }
  enable_autoweighting: True
  max_objective_weight: 0.9999
  min_objective_weight: 0.0001
}

################################################################################################################################################################

training_config {
  batch_size_per_gpu: 8
    num_epochs: 120
    learning_rate {
    soft_start_annealing_schedule {
      min_learning_rate: 5e-6
      max_learning_rate: 5e-4
      soft_start: 0.1
      annealing: 0.7
    }
  }
  regularizer {
    type: L1
    weight: 3e-9
  }
  optimizer {
    adam {
      epsilon: 1e-08
      beta1: 0.9
      beta2: 0.999
    }
  }
  cost_scaling {
    enabled: False
    initial_exponent: 20.0
    increment: 0.005
    decrement: 1.0
  }
  visualizer {
    enabled: true
    num_images: 3
    scalar_logging_frequency: 10
    infrequent_logging_frequency: 1
    target_class_config {
      key: "airport"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "baseball-diamond"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "basketball-court"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "bridge"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "container-crane"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "ground-track-field"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "harbor"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "helicopter"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "helipad"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "large-vehicle"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "plane"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "roundabout"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "ship"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "small-vehicle"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "soccer-ball-field"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "storage-tank"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "swimming-pool"
      value: {
        coverage_threshold: 0.005
      }
    }
    target_class_config {
      key: "tennis-court"
      value: {
        coverage_threshold: 0.005
      }
    }
  }
}

################################################################################################################################################################

# Sample augementation config for
augmentation_config {
  preprocessing {
    output_image_width: 640
    output_image_height: 480
    output_image_channel: 3
    min_bbox_width: 0.0
    min_bbox_height: 0.0
  }
  spatial_augmentation {

    hflip_probability: 0.5
    vflip_probability: 0.0
    zoom_min: 1.0
    zoom_max: 1.0
    translate_max_x: 8.0
    translate_max_y: 8.0
  }
  color_augmentation {
    color_shift_stddev: 0.0
    hue_rotation_max: 25.0
    saturation_shift_max: 0.2
    contrast_scale_max: 0.1
    contrast_center: 0.5
  }
}

################################################################################################################################################################

# Sample evaluation config to run evaluation in integrate mode for the given 3 class model,
# at every 10th epoch starting from the epoch 1.
evaluation_config {
  average_precision_mode: INTEGRATE
  validation_period_during_training: 10
  first_validation_epoch: 1
  minimum_detection_ground_truth_overlap {
    key: "airport"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "baseball-diamond"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "basketball-court"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "bridge"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "container-crane"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "ground-trank-field"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "harbor"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "helicopter"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "helipad"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "large-vehicle"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "plane"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "roundabout"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "ship"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "small-vehicle"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "soccer-ball-field"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "storage-tank"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "swimming-pool"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "tennis-court"
    value: 0.5
  }
  evaluation_box_config {
    key: "airport"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "baseball-diamond"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "basketball-court"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "bridge"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "container-crane"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "ground-trank-field"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "harbor"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "helicopter"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "helipad"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "large-vehicle"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "plane"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "roundabout"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "ship"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "small-vehicle"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "soccer-ball-field"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "storage-tank"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "swimming-pool"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "tennis-court"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
}

################################################################################################################################################################

dataset_config {
  data_sources: {
    tfrecords_path: "/home/rp-hyperx/Downloads/DOTA v2.0 --easy.v7-small_object.tfrecord/train/no.tfrecord"
    image_directory_path: "/home/rp-hyperx/Downloads/DOTA v2.0 --easy.v7-small_object.tfrecord/train/images/"
  }
  image_extension: "jpg"
  target_class_mapping {
      key: "airport"
      value: "airport"
  }
  target_class_mapping {
      key: "baseball-diamond"
      value: "baseball-diamond"
  }
  target_class_mapping {
      key: "basketball-court"
      value: "basketball-court"
  }
  target_class_mapping {
      key: "bridge"
      value: "bridge"
  }
  target_class_mapping {
      key: "container-crane"
      value: "container-crane"
  }
  target_class_mapping {
      key: "ground-track-field"
      value: "ground-track-field"
  }
  target_class_mapping {
      key: "harbor"
      value: "harbor"
  }
  target_class_mapping {
      key: "helicopter"
      value: "helicopter"
  }
  target_class_mapping {
      key: "helipad"
      value: "helipad"
  }
  target_class_mapping {
      key: "large-vehicle"
      value: "large-vehicle"
  }
  target_class_mapping {
      key: "plane"
      value: "plane"
  }
  target_class_mapping {
      key: "roundabout"
      value: "roundabout"
  }
  target_class_mapping {
      key: "ship"
      value: "ship"
  }
  target_class_mapping {
      key: "small-vehicle"
      value: "small-vehicle"
  }
  target_class_mapping {
      key: "soccer-ball-field"
      value: "soccer-ball-field"
  }
  target_class_mapping {
      key: "storage-tank"
      value: "storage-tank"
  }
  target_class_mapping {
      key: "swimming-pool"
      value: "swimming-pool"
  }
  target_class_mapping {
      key: "tennis-court"
      value: "tennis-court"
  }
  validation_fold: 0
}

```

Thank you in advance

---

<div class="post-metadata">

**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\
**Post date:** [June 27, 2023, 5:28pm UTC](https://forums.developer.nvidia.com/t/cannot-train-custom-model-indexerror-list-index-0-out-of-range/257923/3 "2023-06-27T17:28:01Z")

</div>

> [@natanel](#):
>
> and followed the instructions from the [tutorial](https://docs.nvidia.com/tao/tao-toolkit/text/object_detection/detectnet_v2.html#conversion-to-tfrecords-detectnet-v2),

Could you share the log when you generate tfrecords files?

---

<div class="post-metadata">

**Author:** ![natanel](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@natanel](https://forums.developer.nvidia.com/u/natanel)\
**Post date:** [June 27, 2023, 5:32pm UTC](https://forums.developer.nvidia.com/t/cannot-train-custom-model-indexerror-list-index-0-out-of-range/257923/4 "2023-06-27T17:32:12Z")

</div>

Unfortunately I don’t have logs, I downloaded them directly from the Roboflow website, and I don’t see a way to get any logs from there

---

<div class="post-metadata">

**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\
**Post date:** [June 27, 2023, 5:38pm UTC](https://forums.developer.nvidia.com/t/cannot-train-custom-model-indexerror-list-index-0-out-of-range/257923/5 "2023-06-27T17:38:03Z")

</div>

**There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks**

You can refer to [detectnet\_v2 html.](https://docs.nvidia.com/tao/tao-toolkit/text/object_detection/detectnet_v2.html#pre-processing-the-dataset)  
It provides command `dataset_convert` to generate tfrecords files.

---

<div class="post-metadata">

**Author:** ![system](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/system/32/68080_2.png) [@system](https://forums.developer.nvidia.com/u/system)\
**Post date:** [July 25, 2023, 1:30am UTC](https://forums.developer.nvidia.com/t/cannot-train-custom-model-indexerror-list-index-0-out-of-range/257923/7 "2023-07-25T01:30:29Z")

</div>

Closed on July 25, 2023, 1:30am UTC

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.