Get error when training lpdnet with TLT3.0

I want to train lpdnet on my own dataset using usa_unpruned.tlt. Everything is ok and I successfully recorded tfrecords.
When I run the below command:

tlt detectnet_v2 train -e $SPECS_DIR/lpdnet_train_usa_unpruned_kitti.txt \
                        -r $USER_EXPERIMENT_DIR/exp_unpruned/exp_dir_unpruned/tlt_lpdnet_vunpruned_v1.0/usa_unpruned.tlt \
                        -k nvidia_tlt \
                        -n resnet18_lpd \
                        --gpus 4

But the following error occurred:

Illegal instruction (core dumped)
Traceback (most recent call last):
  File "/usr/local/bin/detectnet_v2", line 8, in <module>
    sys.exit(main())
  File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/entrypoint/detectnet_v2.py", line 12, in main
  File "/home/vpraveen/.cache/dazel/_dazel_vpraveen/216c8b41e526c3295d3b802489ac2034/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/common/entrypoint/entrypoint.py", line 296, in launch_job
AssertionError: Process run failed.

Here is my train specs:

random_seed: 42
dataset_config {
  data_sources {
    tfrecords_path: "/workspace/openalpr/data/tfrecords/kitti_trainval/*"
    image_directory_path: "/workspace/openalpr/data/training/"
  }
  image_extension: "jpg"
  target_class_mapping {
    key: "lpd"
    value: "plate"
  }
  validation_fold: 0
}
augmentation_config {
  preprocessing {
    output_image_width: 640
    output_image_height: 480
    min_bbox_width: 1.0
    min_bbox_height: 1.0
    output_image_channel: 3
  }
  spatial_augmentation {
    hflip_probability: 0.5
    zoom_min: 1.0
    zoom_max: 1.0
    translate_max_x: 8.0
    translate_max_y: 8.0
  }
  color_augmentation {
    hue_rotation_max: 25.0
    saturation_shift_max: 0.20000000298
    contrast_scale_max: 0.10000000149
    contrast_center: 0.5
  }
}
postprocessing_config {
  target_class_config {
    key: "plate"
    value {
      clustering_config {
        coverage_threshold: 0.00499999988824
        dbscan_eps: 0.20000000298
        dbscan_min_samples: 0.0500000007451
        minimum_bounding_box_height: 4
      }
    }
  }
}
model_config {
  pretrained_model_file: "/workspace/openalpr/exp_dir_unpruned/tlt_lpdnet_vunpruned_v1.0/usa_unpruned.tlt"
  num_layers: 18
  use_batch_norm: true
  objective_set {
    bbox {
      scale: 35.0
      offset: 0.5
    }
    cov {
    }
  }
  training_precision {
    backend_floatx: FLOAT32
  }
  arch: "resnet"
}
evaluation_config {
  validation_period_during_training: 10
  first_validation_epoch: 1
  minimum_detection_ground_truth_overlap {
    key: "plate"
    value: 0.699999988079
  }
  evaluation_box_config {
    key: "plate"
    value {
      minimum_height: 10
      maximum_height: 9999
      minimum_width: 10
      maximum_width: 9999
    }
  }
  average_precision_mode: INTEGRATE
}
cost_function_config {
  target_classes {
    name: "plate"
    class_weight: 1.0
    coverage_foreground_weight: 0.0500000007451
    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: 0.999899983406
  min_objective_weight: 9.99999974738e-05
}
training_config {
  batch_size_per_gpu: 4
  num_epochs: 120
  enable_qat: False
  learning_rate {
    soft_start_annealing_schedule {
      min_learning_rate: 5e-06
      max_learning_rate: 5e-04
      soft_start: 0.10000000149
      annealing: 0.699999988079
    }
  }
  regularizer {
    type: L1
    weight: 3.00000002618e-09
  }
  optimizer {
    adam {
      epsilon: 9.99999993923e-09
      beta1: 0.899999976158
      beta2: 0.999000012875
    }
  }
  cost_scaling {
    initial_exponent: 20.0
    increment: 0.005
    decrement: 1.0
  }
  checkpoint_interval: 10
}
bbox_rasterizer_config {
  target_class_config {
    key: "plate"
    value {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.40000000596
      cov_radius_y: 0.40000000596
      bbox_min_radius: 1.0
    }
  }
  deadzone_radius: 0.400000154972
}

and my tfrecords specs:

kitti_config {
  root_directory_path: "/workspace/openalpr/data/training"
  image_dir_name: "image"
  label_dir_name: "label"
  image_extension: ".jpg"
  partition_mode: "random"
  num_partitions: 2
  val_split: 20
  num_shards: 10
}

image_directory_path: "/workspace/openalpr/data/training"

Any ideas as to what is going on and how to solve this issue?

Thanks,
Cagla

It may be related to your old CPU.
Reference:

Actually my CPU is Intel (R) Core ™ i7-6700K CPU @ 4.00Ghz. It is not very old.

Could you please check if AVX2 instruction support on the CPU?
Reference: Illegal Instruction When Running the TLT

I run the below command:

grep avx2 /proc/cpuinfo

it didn’t print anything. As I understand it, no output means, it is not supported. I saw in the reference you shared, avx2 instruction support is needed. I should another CPU that does support AVX2 instructions for training my model. Thank you for the response.