alibi_detect.utils.tensorflow.prediction module¶
-
alibi_detect.utils.tensorflow.prediction.
predict_batch
(x, model, batch_size=10000000000, preprocess_fn=None, dtype=numpy.float32)[source]¶ Make batch predictions on a model.
- Parameters
model (
Union
[Callable
,Model
]) – tf.keras model or one of the other permitted types defined in Data.batch_size (
int
) – Batch size used during prediction.preprocess_fn (
Optional
[Callable
]) – Optional preprocessing function for each batch.dtype (
Union
[dtype
,DType
]) – Model output type, e.g. np.float32 or tf.float32.
- Return type
- Returns
Numpy array, tensorflow tensor or tuples of those with model outputs.
-
alibi_detect.utils.tensorflow.prediction.
predict_batch_transformer
(x, model, tokenizer, max_len, batch_size=10000000000, dtype=numpy.float32)[source]¶ Make batch predictions using a transformers tokenizer and model.
- Parameters
- Return type
Union
[ndarray
,Tensor
]- Returns
Numpy array or tensorflow tensor with model outputs.