Quantcast
Channel: TAO Toolkit - NVIDIA Developer Forums
Viewing all articles
Browse latest Browse all 499

LPRNet: Inference was interrrupted without any error messages

$
0
0

• Hardware: A100
• Network Type: LPRNet
• TLT Version: 5.2.0
• How to reproduce the issue:

I tried testing inference with LPRNet before training like so:

lprnet inference -m us_lprnet_baseline18_trainable.tlt -i inference/1152.jpg -e experiment.txt

However I get this result:

2024-01-09 11:28:38.963247: I tensorflow/stream_executor/platform/default/dso_loader.cc:50] Successfully opened dynamic library libcudart.so.12
2024-01-09 11:28:39,010 [TAO Toolkit] [WARNING] tensorflow 40: Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
Using TensorFlow backend.
2024-01-09 11:28:40,577 [TAO Toolkit] [WARNING] tensorflow 43: TensorFlow will not use sklearn by default. This improves performance in some cases. To enable sklearn export the environment variable TF_ALLOW_IOLIBS=1.
2024-01-09 11:28:40,606 [TAO Toolkit] [WARNING] tensorflow 42: TensorFlow will not use Dask by default. This improves performance in some cases. To enable Dask export the environment variable TF_ALLOW_IOLIBS=1.
2024-01-09 11:28:40,610 [TAO Toolkit] [WARNING] tensorflow 43: TensorFlow will not use Pandas by default. This improves performance in some cases. To enable Pandas export the environment variable TF_ALLOW_IOLIBS=1.
WARNING:tensorflow:Deprecation warnings have been disabled. Set TF_ENABLE_DEPRECATION_WARNINGS=1 to re-enable them.
Using TensorFlow backend.
WARNING:tensorflow:TensorFlow will not use sklearn by default. This improves performance in some cases. To enable sklearn export the environment variable TF_ALLOW_IOLIBS=1.
WARNING: TensorFlow will not use sklearn by default. This improves performance in some cases. To enable sklearn export the environment variable TF_ALLOW_IOLIBS=1.
WARNING:tensorflow:TensorFlow will not use Dask by default. This improves performance in some cases. To enable Dask export the environment variable TF_ALLOW_IOLIBS=1.
WARNING: TensorFlow will not use Dask by default. This improves performance in some cases. To enable Dask export the environment variable TF_ALLOW_IOLIBS=1.
WARNING:tensorflow:TensorFlow will not use Pandas by default. This improves performance in some cases. To enable Pandas export the environment variable TF_ALLOW_IOLIBS=1.
WARNING: TensorFlow will not use Pandas by default. This improves performance in some cases. To enable Pandas export the environment variable TF_ALLOW_IOLIBS=1.
INFO: Log file already exists at /home/nikola.stojanovic.mcs/lprnet/status.json
INFO: Starting LPRNet Inference.
INFO: Merging specification from experiment.txt
INFO: Inference was interrupted
Execution status: PASS

My experiment spec file:

random_seed: 42
lpr_config {
  hidden_units: 512
  max_label_length: 8
  arch: "baseline"
  nlayers: 10
}
training_config {
  batch_size_per_gpu: 32
  num_epochs: 100
  learning_rate {
  soft_start_annealing_schedule {
    min_learning_rate: 1e-6
    max_learning_rate: 1e-4
    soft_start: 0.001
    annealing: 0.7
  }
  }
  regularizer {
    type: L2
    weight: 5e-4
  }
}
eval_config {
  validation_period_during_training: 5
  batch_size: 1
}
augmentation_config {
  output_width: 96
  output_height: 48
  output_channel: 3
  max_rotate_degree: 5
  rotate_prob: 0.5
  gaussian_kernel_size: 5
  gaussian_kernel_size: 7
  gaussian_kernel_size: 15
  blur_prob: 0.5
  reverse_color_prob: 0.5
  keep_original_prob: 0.3
}
dataset_config {
  data_sources: {
    label_directory_path: "dataset/train/labels"
    image_directory_path: "dataset/train/images"
  }
  characters_list_file: "chars.txt"
  validation_data_sources: {
    label_directory_path: "dataset/val/labels"
    image_directory_path: "dataset/val/images"
  }
}

What am I doing wrong?

2 posts - 1 participant

Read full topic


Viewing all articles
Browse latest Browse all 499

Trending Articles