models/bmshj2018.py [409:444]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      help="Path where to save/load the trained model.")
  subparsers = parser.add_subparsers(
      title="commands", dest="command",
      help="What to do: 'train' loads training data and trains (or continues "
           "to train) a new model. 'compress' reads an image file (lossless "
           "PNG format) and writes a compressed binary file. 'decompress' "
           "reads a binary file and reconstructs the image (in PNG format). "
           "input and output filenames need to be provided for the latter "
           "two options. Invoke '<command> -h' for more information.")

  # 'train' subcommand.
  train_cmd = subparsers.add_parser(
      "train",
      formatter_class=argparse.ArgumentDefaultsHelpFormatter,
      description="Trains (or continues to train) a new model. Note that this "
                  "model trains on a continuous stream of patches drawn from "
                  "the training image dataset. An epoch is always defined as "
                  "the same number of batches given by --steps_per_epoch. "
                  "The purpose of validation is mostly to evaluate the "
                  "rate-distortion performance of the model using actual "
                  "quantization rather than the differentiable proxy loss. "
                  "Note that when using custom training images, the validation "
                  "set is simply a random sampling of patches from the "
                  "training set.")
  train_cmd.add_argument(
      "--lambda", type=float, default=0.01, dest="lmbda",
      help="Lambda for rate-distortion tradeoff.")
  train_cmd.add_argument(
      "--train_glob", type=str, default=None,
      help="Glob pattern identifying custom training data. This pattern must "
           "expand to a list of RGB images in PNG format. If unspecified, the "
           "CLIC dataset from TensorFlow Datasets is used.")
  train_cmd.add_argument(
      "--num_filters", type=int, default=192,
      help="Number of filters per layer.")
  train_cmd.add_argument(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



models/ms2020.py [580:615]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
      help="Path where to save/load the trained model.")
  subparsers = parser.add_subparsers(
      title="commands", dest="command",
      help="What to do: 'train' loads training data and trains (or continues "
           "to train) a new model. 'compress' reads an image file (lossless "
           "PNG format) and writes a compressed binary file. 'decompress' "
           "reads a binary file and reconstructs the image (in PNG format). "
           "input and output filenames need to be provided for the latter "
           "two options. Invoke '<command> -h' for more information.")

  # 'train' subcommand.
  train_cmd = subparsers.add_parser(
      "train",
      formatter_class=argparse.ArgumentDefaultsHelpFormatter,
      description="Trains (or continues to train) a new model. Note that this "
                  "model trains on a continuous stream of patches drawn from "
                  "the training image dataset. An epoch is always defined as "
                  "the same number of batches given by --steps_per_epoch. "
                  "The purpose of validation is mostly to evaluate the "
                  "rate-distortion performance of the model using actual "
                  "quantization rather than the differentiable proxy loss. "
                  "Note that when using custom training images, the validation "
                  "set is simply a random sampling of patches from the "
                  "training set.")
  train_cmd.add_argument(
      "--lambda", type=float, default=0.01, dest="lmbda",
      help="Lambda for rate-distortion tradeoff.")
  train_cmd.add_argument(
      "--train_glob", type=str, default=None,
      help="Glob pattern identifying custom training data. This pattern must "
           "expand to a list of RGB images in PNG format. If unspecified, the "
           "CLIC dataset from TensorFlow Datasets is used.")
  train_cmd.add_argument(
      "--num_filters", type=int, default=192,
      help="Number of filters per layer.")
  train_cmd.add_argument(
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -