Empty label files in custom dataset

• Network Type: Detectnet_v2
• Format_version: 2.0
• toolkit_version: 3.22.05
• published_date: 05/25/2022
• Training spec file:
detectnet_v2_train_resnet10_coco.txt (16.5 KB)

Hi there,
I want to train detectNet_v2 with resnet-10 arch. with a custom dataset. My dataset contains empty labels images, here is my dataset converter message:

Converting Tfrecords for coco trainval dataset
2022-12-14 14:01:11,739 [INFO] root: Registry: ['nvcr.io']
2022-12-14 14:01:11,809 [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
2022-12-14 14:01:11,816 [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 "/root/.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.
2022-12-14 14:01:17,122 [INFO] iva.detectnet_v2.dataio.build_converter: Instantiating a coco converter
2022-12-14 14:01:17,122 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Creating output directory /workspace/tao-experiments/data/tfrecords/coco_trainval
loading annotations into memory...
Done (t=0.20s)
creating index...
index created!
2022-12-14 14:01:17,336 [INFO] iva.detectnet_v2.dataio.coco_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/coco_converter_lib.py:136: The name tf.python_io.TFRecordWriter is deprecated. Please use tf.io.TFRecordWriter instead.

2022-12-14 14:01:17,336 [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/coco_converter_lib.py:136: The name tf.python_io.TFRecordWriter is deprecated. Please use tf.io.TFRecordWriter instead.

2022-12-14 14:01:17,420 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 1
2022-12-14 14:01:17,501 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 2
2022-12-14 14:01:17,582 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 3
2022-12-14 14:01:17,664 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 4
2022-12-14 14:01:17,745 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 5
2022-12-14 14:01:17,826 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 6
2022-12-14 14:01:17,907 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 7
2022-12-14 14:01:17,990 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 8
2022-12-14 14:01:18,071 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 9
2022-12-14 14:01:18,154 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 10
2022-12-14 14:01:18,235 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 11
2022-12-14 14:01:18,317 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 12
2022-12-14 14:01:18,398 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 13
2022-12-14 14:01:18,478 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 14
2022-12-14 14:01:18,559 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 15
2022-12-14 14:01:18,641 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 16
2022-12-14 14:01:18,722 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 17
2022-12-14 14:01:18,804 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 18
2022-12-14 14:01:18,884 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 19
2022-12-14 14:01:18,965 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 20
2022-12-14 14:01:19,046 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 21
2022-12-14 14:01:19,126 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 22
2022-12-14 14:01:19,207 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 23
2022-12-14 14:01:19,288 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 24
2022-12-14 14:01:19,370 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 25
2022-12-14 14:01:19,452 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 26
2022-12-14 14:01:19,533 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 27
2022-12-14 14:01:19,614 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 28
2022-12-14 14:01:19,695 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 29
2022-12-14 14:01:19,777 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 30
2022-12-14 14:01:19,858 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Writing partition 0, shard 31
2022-12-14 14:01:19,947 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: 
Wrote the following numbers of objects:
b'tsa': 3361
b'peo': 1766
b'sgn': 5319
b'jp6': 4982
b'vad': 1574
b'tel': 6844
b'sld': 218
b'tdb': 2145
b'xng': 2184
b'vov': 803
b'sig': 672
b'von': 4210
b'ash': 1375

2022-12-14 14:01:19,947 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Cumulative object statistics
2022-12-14 14:01:19,947 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: 
Wrote the following numbers of objects:
b'tsa': 3361
b'peo': 1766
b'sgn': 5319
b'jp6': 4982
b'vad': 1574
b'tel': 6844
b'sld': 218
b'tdb': 2145
b'xng': 2184
b'vov': 803
b'sig': 672
b'von': 4210
b'ash': 1375

2022-12-14 14:01:19,947 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Class map. 
Label in GT: Label in tfrecords file 
TSA: tsa
PEO: peo
SGN: sgn
JP6: jp6
VAD: vad
TEL: tel
SLD: sld
TDB: tdb
XNG: xng
VOV: vov
SIG: sig
VON: von
ASH: ash
For the dataset_config in the experiment_spec, please use labels in the tfrecords file, while writing the classmap.

2022-12-14 14:01:19,947 [INFO] iva.detectnet_v2.dataio.coco_converter_lib: Tfrecords generation complete.
2022-12-14 14:01:19,947 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: Writing the log_warning.json
2022-12-14 14:01:19,947 [INFO] iva.detectnet_v2.dataio.dataset_converter_lib: There were errors in the labels. Details are logged at /workspace/tao-experiments/data/tfrecords/coco_trainval/coco_trainval_waring.json
2022-12-14 14:01:20,849 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

I get this error:
There were errors in the labels. Details are logged at /workspace/tao-experiments/data/tfrecords/coco_trainval/coco_trainval_waring.json

coco_trainval_waring.json contains :

{
  "6658": [
    384,
    306,
    390,
    306
  ]
}

therefore I get an error while running train command.
I get this error:

2022-12-14 14:54:42,732 [INFO] root: Registry: ['nvcr.io']
2022-12-14 14:54:42,803 [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
2022-12-14 14:54:42,810 [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 "/root/.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.

2022-12-14 14:54:48,031 [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.

2022-12-14 14:54:48,130 [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.

2022-12-14 14:54:48,610 [INFO] iva.common.logging.logging: Log file already exists at /workspace/tao-experiments/USER_EXPERIMENT_detectnet_v2/experiment_dir_unpruned/status.json
2022-12-14 14:54:48,610 [INFO] root: Starting DetectNet_v2 Training job
2022-12-14 14:54:48,610 [INFO] __main__: Loading experiment spec at /workspace/tao-experiments/detectnet_v2/specs/detectnet_v2_train_resnet10_coco.txt.
2022-12-14 14:54:48,611 [INFO] iva.detectnet_v2.spec_handler.spec_loader: Merging specification from /workspace/tao-experiments/detectnet_v2/specs/detectnet_v2_train_resnet10_coco.txt
2022-12-14 14:54:48,626 [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.

2022-12-14 14:54:48,626 [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.

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 626, 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/dataloader/build_dataloader.py", line 273, in build_dataloader
  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/dataloader/drivenet_dataloader.py", line 491, in __init__
  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/dataloader/drivenet_dataloader.py", line 548, in _construct_data_sources
  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/dataloader/drivenet_dataloader.py", line 395, in __init__
  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/dataloader/drivenet_dataloader.py", line 395, in <listcomp>
  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/dataloader/drivenet_dataloader.py", line 394, in <genexpr>
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/lib/io/tf_record.py", line 181, in tf_record_iterator
    reader.GetNext()
  File "/usr/local/lib/python3.6/dist-packages/tensorflow_core/python/pywrap_tensorflow_internal.py", line 1034, in GetNext
    return _pywrap_tensorflow_internal.PyRecordReader_GetNext(self)
tensorflow.python.framework.errors_impl.DataLossError: corrupted record at 0
2022-12-14 14:54:49,685 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

When I delete the warning.json file in tfrecords folder and run the training command again I get this error:

2022-12-14 14:55:52,930 [INFO] root: Registry: ['nvcr.io']
2022-12-14 14:55:53,001 [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
2022-12-14 14:55:53,008 [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 "/root/.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.

2022-12-14 14:55:58,258 [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.

2022-12-14 14:55:58,358 [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.

2022-12-14 14:55:58,813 [INFO] iva.common.logging.logging: Log file already exists at /workspace/tao-experiments/USER_EXPERIMENT_detectnet_v2/experiment_dir_unpruned/status.json
2022-12-14 14:55:58,813 [INFO] root: Starting DetectNet_v2 Training job
2022-12-14 14:55:58,814 [INFO] __main__: Loading experiment spec at /workspace/tao-experiments/detectnet_v2/specs/detectnet_v2_train_resnet10_coco.txt.
2022-12-14 14:55:58,814 [INFO] iva.detectnet_v2.spec_handler.spec_loader: Merging specification from /workspace/tao-experiments/detectnet_v2/specs/detectnet_v2_train_resnet10_coco.txt
2022-12-14 14:55:58,828 [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.

2022-12-14 14:55:58,828 [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.

2022-12-14 14:55:59,627 [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
2022-12-14 14:56:00,663 [INFO] tlt.components.docker_handler.docker_handler: Stopping container.

Does the TAO toolkit accept empty label images (background images) or do I have to use non-empty label images?

It does not. You can move out empty label images and retry with new tfreocrds.
Or find the tfrecords file which has empty label images and move out it.

1 Like

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