load_linear_multiclass_bias_initializer( ckpt_path, bias_tensor_name, new_class_vocab_size, old_class_vocab_file, new_class_vocab_file, num_class_oov_buckets=0, initializer=None, max_rows_in_memory=-1 )
Loads pre-trained multi-class biases for linear models from checkpoint.
load_and_remap_matrix_initializer() specialized for loading multi-class bias and remapping according to the provided vocab files. See docs for
load_and_remap_matrix_initializer() for more details. In this case, the provided row_vocab is the class vocabulary, and the expected shape is
ckpt_path: Path to the TensorFlow checkpoint (version 2,
TensorBundle) from which the old matrix
Tensorwill be loaded.
bias_tensor_name: Tensor name to load from in the checkpoints.
new_class_vocab_size: Number of entries in the new class vocab.
old_class_vocab_file: A scalar
stringcontaining the path to the old class vocabulary file.
new_class_vocab_file: A scalar
stringcontaining the path to the new class vocabulary file.
intspecifying the number of out-of-vocabulary buckets to use for the classes. Must be >= 0.
initializer: Initializer function that accepts a 1-D tensor as the arg to specify the shape of the returned tensor. If
None, defaults to using
intspecifying the maximum number of rows to load from the checkpoint at once. If less than or equal to 0, the entire matrix will be loaded into memory. Setting this arg trades increased disk reads for lower memory usage.
A variable initializer function.
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.