ValueError: steps_per_epoch must be > 0

Things I have confirmed from the previous issues

image extensions: jpg
image height,width: multiple of 16
batch size : low
update in tfrecords

Command run :
tao detectnet_v2 train -k 7221 -r /home/usr/train/task2_detectNet_train.cfg

error :

2022-07-05 11:38:27,519 [INFO] root: Sampling mode of the dataloader was set to user_defined.
Traceback (most recent call last):
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 917, in <module>
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 906, in <module>
  File "<decorator-gen-2>", line 2, in main
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/utilities/timer.py", line 46, in wrapped_fn
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 893, in main
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 757, in run_experiment
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 638, in train_gridbox
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py", line 26, in build_cost_auto_weight_hook
ValueError: steps_per_epoch must be > 0
2022-07-05 11:38:29,408 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

Spec file :

dataset_config {
  data_sources {
    tfrecords_path: "~/dataset/tf/-fold*"
    image_directory_path: "~/dataset/data/train/images"
  }
  image_extension: "jpg"
  target_class_mapping {
    key: "bicycle"
    value: "bicycle"
  }
  target_class_mapping {
    key: "pedestrian"
    value: "pedestrian"
  }
  validation_fold: 0
}
augmentation_config {
  preprocessing {
    output_image_width: 1088
    output_image_height: 544
    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: 0.20000000298023224
    contrast_scale_max: 0.10000000149011612
    contrast_center: 0.5
  }
}
postprocessing_config {
  target_class_config {
    key: "bicycle"
    value {
      clustering_config {
        coverage_threshold: 0.004999999888241291
        minimum_bounding_box_height: 20
        dbscan_eps: 0.15000000596046448
        dbscan_min_samples: 0.05000000074505806
      }
    }
  }
  target_class_config {
    key: "pedestrian"
    value {
      clustering_config {
        coverage_threshold: 0.004999999888241291
        minimum_bounding_box_height: 20
        dbscan_eps: 0.15000000596046448
        dbscan_min_samples: 0.05000000074505806
      }
    }
  }
}
model_config {
  num_layers: 18
  use_batch_norm: true
  objective_set {
    bbox {
      scale: 35.0
      offset: 0.5
    }
    cov {
    }
  }
  arch: "resnet"
  load_graph: true
  all_projections: true
}
evaluation_config {
  validation_period_during_training: 20
  first_validation_epoch: 5
  minimum_detection_ground_truth_overlap {
    key: "bicycle"
    value: 0.5
  }
  minimum_detection_ground_truth_overlap {
    key: "pedestrian"
    value: 0.699999988079071
  }
  evaluation_box_config {
    key: "bicycle"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  evaluation_box_config {
    key: "pedestrian"
    value {
      minimum_height: 4
      maximum_height: 9999
      minimum_width: 4
      maximum_width: 9999
    }
  }
  average_precision_mode: INTEGRATE
}
cost_function_config {
  target_classes {
    name: "pedestrian"
    class_weight: 1.0
    coverage_foreground_weight: 0.05000000074505806
    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: "bicycle"
    class_weight: 1.0
    coverage_foreground_weight: 0.05000000074505806
    objectives {
      name: "cov"
      initial_weight: 1.0
      weight_target: 1.0
    }
    objectives {
      name: "bbox"
      initial_weight: 10.0
      weight_target: 1.0
    }
  }
  enable_autoweighting: true
  max_objective_weight: 0.9998999834060669
  min_objective_weight: 9.999999747378752e-05
}
training_config {
  batch_size_per_gpu: 4
  num_epochs: 20
  learning_rate {
    soft_start_annealing_schedule {
      min_learning_rate: 4.999999873689376e-06
      max_learning_rate: 0.0005000000237487257
      soft_start: 0.10000000149011612
      annealing: 0.699999988079071
    }
  }
  regularizer {
    weight: 3.000000026176508e-09
  }
  optimizer {
    adam {
      epsilon: 9.99999993922529e-09
      beta1: 0.8999999761581421
      beta2: 0.9990000128746033
    }
  }
  cost_scaling {
    initial_exponent: 20.0
    increment: 0.005
    decrement: 1.0
  }
}
bbox_rasterizer_config {
  target_class_config {
    key: "bicycle"
    value {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4000000059604645
      cov_radius_y: 0.4000000059604645
      bbox_min_radius: 1.0
    }
  }
  target_class_config {
    key: "pedestrian"
    value {
      cov_center_x: 0.5
      cov_center_y: 0.5
      cov_radius_x: 0.4000000059604645
      cov_radius_y: 0.4000000059604645
      bbox_min_radius: 1.0
    }
  }
  deadzone_radius: 0.6700000166893005
}

Please make sure all the tfrecords files are not empty.

Output of tao detectnet_v2 run ls -rltsh ~/tfrecord
I dont think the records are empty.

022-07-06 04:54:10,102 [INFO] root: Registry: ['nvcr.io']
2022-07-06 04:54:10,453 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit-tf:v3.22.05-tf1.15.4-py3
2022-07-06 04:54:10,573 [WARNING] tlt.components.docker_handler.docker_handler:
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the "user":"UID:GID" in the
DockerOptions portion of the "/home/saiteja/.tao_mounts.json" file. You can obtain your
users UID and GID by using the "id -u" and "id -g" commands on the
terminal.
total 24M
2.3M -rw-r--r-- 1 root root 2.3M Jul  5 11:36 -fold-000-of-002-shard-00000-of-00010
2.5M -rw-r--r-- 1 root root 2.5M Jul  5 11:36 -fold-000-of-002-shard-00001-of-00010
2.5M -rw-r--r-- 1 root root 2.5M Jul  5 11:36 -fold-000-of-002-shard-00002-of-00010
2.3M -rw-r--r-- 1 root root 2.3M Jul  5 11:36 -fold-000-of-002-shard-00003-of-00010
2.4M -rw-r--r-- 1 root root 2.4M Jul  5 11:36 -fold-000-of-002-shard-00004-of-00010
2.3M -rw-r--r-- 1 root root 2.3M Jul  5 11:36 -fold-000-of-002-shard-00005-of-00010
2.4M -rw-r--r-- 1 root root 2.4M Jul  5 11:36 -fold-000-of-002-shard-00006-of-00010
2.4M -rw-r--r-- 1 root root 2.4M Jul  5 11:36 -fold-000-of-002-shard-00007-of-00010
2.5M -rw-r--r-- 1 root root 2.5M Jul  5 11:36 -fold-000-of-002-shard-00008-of-00010
2.4M -rw-r--r-- 1 root root 2.4M Jul  5 11:36 -fold-000-of-002-shard-00009-of-00010
2022-07-06 04:54:11,678 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

Please share the full log. Thanks.

Complete details of log

2022-07-06 06:57:07,781 [INFO] root: Registry: ['nvcr.io']
2022-07-06 06:57:08,094 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit-tf:v3.22.05-tf1.15.4-py3
2022-07-06 06:57:08,225 [WARNING] tlt.components.docker_handler.docker_handler:
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the "user":"UID:GID" in the
DockerOptions portion of the "/home/saiteja/.tao_mounts.json" file. You can obtain your
users UID and GID by using the "id -u" and "id -g" commands on the
terminal.
Using TensorFlow backend.
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
/usr/local/lib/python3.6/dist-packages/requests/__init__.py:91: RequestsDependencyWarning: urllib3 (1.26.5) or chardet (3.0.4) doesn't match a supported version!
  RequestsDependencyWarning)
Using TensorFlow backend.
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:43: The name tf.train.SessionRunHook is deprecated. Please use tf.estimator.SessionRunHook instead.

2022-07-06 06:57:19,714 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py:43: The name tf.train.SessionRunHook is deprecated. Please use tf.estimator.SessionRunHook instead.

WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/tfhooks/checkpoint_saver_hook.py:25: The name tf.train.CheckpointSaverHook is deprecated. Please use tf.estimator.CheckpointSaverHook instead.

2022-07-06 06:57:19,829 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/tfhooks/checkpoint_saver_hook.py:25: The name tf.train.CheckpointSaverHook is deprecated. Please use tf.estimator.CheckpointSaverHook instead.

2022-07-06 06:57:20,713 [INFO] iva.common.logging.logging: Log file already exists at /home/saiteja/results/status.json
2022-07-06 06:57:20,713 [INFO] root: Starting DetectNet_v2 Training job
2022-07-06 06:57:20,714 [INFO] __main__: Loading experiment spec at /home/saiteja/scripts/train/task2_detectNet_train.cfg.
2022-07-06 06:57:20,715 [INFO] iva.detectnet_v2.spec_handler.spec_loader: Merging specification from /home/saiteja/scripts/train/task2_detectNet_train.cfg
2022-07-06 06:57:20,720 [INFO] root: Training gridbox model.
WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:153: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

2022-07-06 06:57:20,721 [WARNING] tensorflow: From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow_backend.py:153: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

2022-07-06 06:57:21,184 [INFO] root: Sampling mode of the dataloader was set to user_defined.
Traceback (most recent call last):
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 917, in <module>
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 906, in <module>
  File "<decorator-gen-2>", line 2, in main
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/utilities/timer.py", line 46, in wrapped_fn
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 893, in main
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 757, in run_experiment
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/scripts/train.py", line 638, in train_gridbox
  File "/root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/cost_function/cost_auto_weight_hook.py", line 26, in build_cost_auto_weight_hook
ValueError: steps_per_epoch must be > 0
2022-07-06 06:57:23,072 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

Can you modify ~ to absolute path?

I have done that and it looks like, but still the error exists

    tfrecords_path: "/home/saiteja/tf/-fold*"
    image_directory_path: "/home/saiteja/data/images"

Are you sure the path is correct?

Please run below to check.
$ tao detectnet_v2 run ls /home/saiteja/data/images |wc -l

the output for the above command is

usage: tao [-h]
           {list,stop,info,action_recognition,augment,bpnet,classification,converter,detectnet_v2,dssd,efficientdet,emotionnet,faster_rcnn,fpenet,gazenet,gesturenet,heartratenet,intent_slot_classification,lprnet,mask_rcnn,multitask_classification,n_gram,pointpillars,pose_classification,punctuation_and_capitalization,question_answering,retinanet,spectro_gen,speech_to_text,speech_to_text_citrinet,speech_to_text_conformer,ssd,text_classification,token_classification,unet,vocoder,yolo_v3,yolo_v4,yolo_v4_tiny}
           ...
tao: error: invalid choice: 'detectnet_2' (choose from 'list', 'stop', 'info', 'action_recognition', 'augment', 'bpnet', 'classification', 'converter', 'detectnet_v2', 'dssd', 'efficientdet', 'emotionnet', 'faster_rcnn', 'fpenet', 'gazenet', 'gesturenet', 'heartratenet', 'intent_slot_classification', 'lprnet', 'mask_rcnn', 'multitask_classification', 'n_gram', 'pointpillars', 'pose_classification', 'punctuation_and_capitalization', 'question_answering', 'retinanet', 'spectro_gen', 'speech_to_text', 'speech_to_text_citrinet', 'speech_to_text_conformer', 'ssd', 'text_classification', 'token_classification', 'unet', 'vocoder', 'yolo_v3', 'yolo_v4', 'yolo_v4_tiny')
0

$ tao detectnet_v2 run ls /home/saiteja/data/images |wc -l

The output is

2022-07-06 07:20:35,417 [INFO] root: Registry: ['nvcr.io']
2022-07-06 07:20:35,763 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit-tf:v3.22.05-tf1.15.4-py3
2022-07-06 07:20:35,898 [WARNING] tlt.components.docker_handler.docker_handler:
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the "user":"UID:GID" in the
DockerOptions portion of the "/home/saiteja/.tao_mounts.json" file. You can obtain your
users UID and GID by using the "id -u" and "id -g" commands on the
terminal.
1

So, there is only 1 training image, right?

How about
$ tao detectnet_v2 run ls /home/saiteja/data/image

There are 5478 files. when I run the command ls | wc -l.

But when I run the command(tao detectnet_v2 run ls /home/saiteja/data/images |wc -l) it gives me only 1.

I have added a slash at the end,

 tao detectnet_v2 run ls /home/saiteja/data/images/ |wc -l

Now the output is

2022-07-06 07:28:11,230 [INFO] root: Registry: ['nvcr.io']
2022-07-06 07:28:11,585 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit-tf:v3.22.05-tf1.15.4-py3
2022-07-06 07:28:11,723 [WARNING] tlt.components.docker_handler.docker_handler:
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the "user":"UID:GID" in the
DockerOptions portion of the "/home/saiteja/.tao_mounts.json" file. You can obtain your
users UID and GID by using the "id -u" and "id -g" commands on the
terminal.
2022-07-06 07:28:15,038 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.
2744

Can you find the images when you run "$tao detectnet_v2 run ls /home/saiteja/data/images "?

If yes, please modify the spec file with this path.

Yes i can find the images

So, please modify your image_directory_path.

I have modified and still, the error exists.

Can you share the full command and full log how did you generate the tfrecord files?

Command:

tao detectnet_v2 dataset_convert -d /home/saiteja/scripts/train/train.cfg -o /home/saiteja/tf/
2022-07-06 08:01:28,884 [INFO] root: Registry: ['nvcr.io']
2022-07-06 08:01:29,208 [INFO] tlt.components.instance_handler.local_instance: Running command in container: nvcr.io/nvidia/tao/tao-toolkit-tf:v3.22.05-tf1.15.4-py3
2022-07-06 08:01:29,337 [WARNING] tlt.components.docker_handler.docker_handler:
Docker will run the commands as root. If you would like to retain your
local host permissions, please add the "user":"UID:GID" in the
DockerOptions portion of the "/home/saiteja/.tao_mounts.json" file. You can obtain your
users UID and GID by using the "id -u" and "id -g" commands on the
terminal.
Using TensorFlow backend.
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
/usr/local/lib/python3.6/dist-packages/requests/__init__.py:91: RequestsDependencyWarning: urllib3 (1.26.5) or chardet (3.0.4) doesn't match a supported version!
  RequestsDependencyWarning)
Using TensorFlow backend.
2022-07-06 08:01:41,051 [INFO] iva.detectnet_v2.dataio.build_converter: Instantiating a kitti converter
2022-07-06 08:01:41,067 [INFO] iva.detectnet_v2.dataio.kitti_converter_lib: Num images in
Train: 5487     Val: 0
2022-07-06 08:01:41,067 [INFO] iva.detectnet_v2.dataio.kitti_converter_lib: Skipped validation data...
2022-07-06 08:01:41,072 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 0
WARNING:tensorflow:From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/dataio/dataset_converter_lib.py:169: The name tf.python_io.TFRecordWriter is deprecated. Please use tf.io.TFRecordWriter instead.

2022-07-06 08:01:41,072 [WARNING] tensorflow: From /root/.cache/bazel/_bazel_root/b770f990bb7b9e2db5771981fb3a38b4/execroot/ai_infra/bazel-out/k8-fastbuild/bin/magnet/packages/iva/build_wheel.runfiles/ai_infra/iva/detectnet_v2/dataio/dataset_converter_lib.py:169: The name tf.python_io.TFRecordWriter is deprecated. Please use tf.io.TFRecordWriter instead.

/usr/local/lib/python3.6/dist-packages/iva/detectnet_v2/dataio/kitti_converter_lib.py:315: VisibleDeprecationWarning: Reading unicode strings without specifying the encoding argument is deprecated. Set the encoding, use None for the system default.
2022-07-06 08:01:41,843 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 1
2022-07-06 08:01:42,694 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 2
2022-07-06 08:01:43,512 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 3
2022-07-06 08:01:44,327 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 4
2022-07-06 08:01:45,124 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 5
2022-07-06 08:01:45,953 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 6
2022-07-06 08:01:46,744 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 7
2022-07-06 08:01:47,619 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 8
2022-07-06 08:01:48,442 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing partition 0, shard 9
2022-07-06 08:01:49,314 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib:
Wrote the following numbers of objects:
b'bicycle': 10480
b'pedestrian': 79337

2022-07-06 08:01:49,315 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Cumulative object statistics
2022-07-06 08:01:49,315 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib:
Wrote the following numbers of objects:
b'bicycle': 10480
b'pedestrian': 79337

2022-07-06 08:01:49,315 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Class map.
Label in GT: Label in tfrecords file
b'bicycle': b'bicycle'
b'pedestrian': b'pedestrian'
For the dataset_config in the experiment_spec, please use labels in the tfrecords file, while writing the classmap.

2022-07-06 08:01:49,315 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Tfrecords generation complete.
2022-07-06 08:01:51,005 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

Specs file

kitti_config {
  root_directory_path: "/home/saiteja/"
  image_dir_name: "data/images"
  label_dir_name: "data/labels"
  image_extension: ".jpg"
  partition_mode: "random"
  num_partitions: 2
  val_split: 0
  num_shards: 10
}
image_directory_path: "/home/saiteja/data/images"
  target_class_mapping {
      key: "pedestrian"
      value: "pedestrian"
  }
  target_class_mapping {
      key: "bicycle"
      value: "bicycle"
  }

I suddenly find a potential culprit. Why you set the spec file after “-r” ?
“-r” means the result folder.