Tltv3 yolov4 train set aren't loaded

Please provide the following information when requesting support.

• training on NGC
• Yolo_v4
• TLT Version

Configuration of the TLT Instance

dockers:
        nvidia/tlt-streamanalytics:
                docker_registry: nvcr.io
                docker_tag: v3.0-py3
                tasks:
                        1. augment
                        2. bpnet
                        3. classification
                        4. detectnet_v2
                        5. dssd
                        6. emotionnet
                        7. faster_rcnn
                        8. fpenet
                        9. gazenet
                        10. gesturenet
                        11. heartratenet
                        12. lprnet
                        13. mask_rcnn
                        14. multitask_classification
                        15. retinanet
                        16. ssd
                        17. unet
                        18. yolo_v3
                        19. yolo_v4
                        20. tlt-converter
        nvidia/tlt-pytorch:
                docker_registry: nvcr.io
                docker_tag: v3.0-py3
                tasks:
                        1. speech_to_text
                        2. speech_to_text_citrinet
                        3. text_classification
                        4. question_answering
                        5. token_classification
                        6. intent_slot_classification
                        7. punctuation_and_capitalization
format_version: 1.0
tlt_version: 3.0
published_date: 04/16/2021

• Training spec file

random_seed: 42
yolov4_config {
  big_anchor_shape: "[(26.00, 54.00), (47.00, 77.00), (79.00, 135.00)]"
  mid_anchor_shape: "[(15.00, 26.00), (16.00, 40.00), (21.00, 34.00)]"
  small_anchor_shape: "[(7.00, 14.00), (9.00, 19.00), (11.00, 29.00)]"
  box_matching_iou: 0.5
  # matching_neutral_box_iou: 0.5
  arch: "darknet"
  nlayers: 53
  arch_conv_blocks: 2
  loss_loc_weight: 0.8
  loss_neg_obj_weights: 100.0
  loss_class_weights: 0.5
  label_smoothing: 0.0
  big_grid_xy_extend: 0.05
  mid_grid_xy_extend: 0.1
  small_grid_xy_extend: 0.2
  freeze_bn: false
  freeze_blocks: 0
  force_relu: false
}
training_config {
  batch_size_per_gpu: 16
  num_epochs: 200
  enable_qat: true
  checkpoint_interval: 50
  learning_rate {
    soft_start_cosine_annealing_schedule {
      min_learning_rate: 1e-7
      max_learning_rate: 1e-4
      soft_start: 0.3
    }
  }
  regularizer {
    type: L1
    weight: 3e-5
  }
  optimizer {
    adam {
      epsilon: 1e-7
      beta1: 0.9
      beta2: 0.999
      amsgrad: false
    }
  }
  # pretrain_model_path: "/workspace/yolo/pretrained_model/resnet_18.hdf5"
}
eval_config {
  average_precision_mode: SAMPLE
  batch_size: 8
  matching_iou_threshold: 0.5
}
nms_config {
  confidence_threshold: 0.001
  clustering_iou_threshold: 0.5
  top_k: 200
}
augmentation_config {
  hue: 0.1
  saturation: 1.5
  exposure:1.5
  vertical_flip:0
  horizontal_flip: 0.5
  jitter: 0.3
  output_width: 960
  output_height: 544
  output_channel: 3
  randomize_input_shape_period: 0
  mosaic_prob: 0.5
  mosaic_min_ratio:0.2
  image_mean {
    key: 'b'
    value: 103.9
  }
  image_mean {
    key: 'g'
    value: 116.8
  }
  image_mean {
    key: 'r'
    value: 123.7
  }
}
dataset_config {
  data_sources: {
      label_directory_path: "/data/img"
      image_directory_path: "/data/label"
  }
  include_difficult_in_training: false
  target_class_mapping {
      key: "adult"
      value: "adult"
  }
  target_class_mapping {
      key: "child"
      value: "child"
  }
  validation_data_sources: {
      label_directory_path: "/data/label"
      image_directory_path: "/data/img"
  }
}

• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)

2021-06-23 07:06:06,800 [INFO] __main__: Number of images in the training dataset:           0

Image data are not loaded.

This forum is same case but it was not file extension problem.
Image files are not crashed. Also I put right path as I checked.

Can you double check the path? Please run following command.
$ tlt yolo_v4 run ls /data/label |wc -l

1 Like

I find the culprit in your training spec.

data_sources: {
label_directory_path: “/data/img”
image_directory_path: “/data/label”
}

Please modify it to

data_sources: {
image_directory_path: “/data/img”
label_directory_path: “/data/label”
}

1 Like

I couldn’t find this mistake! Thanks

This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.