sparknlp.annotator.cv.paligemma_for_multimodal
#
Module Contents#
Classes#
PaliGemmaForMultiModal can load PaliGemma models for visual question answering. |
- class PaliGemmaForMultiModal(classname='com.johnsnowlabs.nlp.annotators.cv.PaliGemmaForMultiModal', java_model=None)[source]#
PaliGemmaForMultiModal can load PaliGemma models for visual question answering. The model consists of a vision encoder, a text encoder, a text decoder and a model merger. The vision encoder will encode the input image, the text encoder will encode the input text, the model merger will merge the image and text embeddings, and the text decoder will output the answer.
Pretrained models can be loaded with
pretrained()
of the companion object:>>> visualQAClassifier = PaliGemmaForMultiModal.pretrained() \ ... .setInputCols(["image_assembler"]) \ ... .setOutputCol("answer")
The default model is
"paligemma_3b_pt_224_int4"
, if no name is provided.For available pretrained models please see the Models Hub.
Input Annotation types
Output Annotation type
IMAGE
DOCUMENT
- Parameters:
- batchSize
Batch size. Large values allows faster processing but requires more memory, by default 2
- maxSentenceLength
Max sentence length to process, by default 50
Examples
>>> import sparknlp >>> from sparknlp.base import * >>> from sparknlp.annotator import * >>> from pyspark.ml import Pipeline >>> image_df = SparkSessionForTest.spark.read.format("image").load(path=images_path) >>> test_df = image_df.withColumn("text", lit("USER: \n <image> \nDescribe this image. \nASSISTANT:\n")) >>> imageAssembler = ImageAssembler() \ ... .setInputCol("image") \ ... .setOutputCol("image_assembler") >>> visualQAClassifier = PaliGemmaForMultiModal.pretrained() \ ... .setInputCols("image_assembler") \ ... .setOutputCol("answer") >>> pipeline = Pipeline().setStages([ ... imageAssembler, ... visualQAClassifier ... ]) >>> result = pipeline.fit(test_df).transform(test_df) >>> result.select("image_assembler.origin", "answer.result").show(false) +--------------------------------------+------+ |origin |result| +--------------------------------------+------+ |[file:///content/images/bluetick.jpg] |[A dog is standing on a grassy field.]| +--------------------------------------+------+
- setMaxSentenceSize(value)[source]#
Sets Maximum sentence length that the annotator will process, by default 50.
- Parameters:
- valueint
Maximum sentence length that the annotator will process
- setIgnoreTokenIds(value)[source]#
A list of token ids which are ignored in the decoder’s output.
- Parameters:
- valueList[int]
The words to be filtered out
- setMinOutputLength(value)[source]#
Sets minimum length of the sequence to be generated.
- Parameters:
- valueint
Minimum length of the sequence to be generated
- setMaxOutputLength(value)[source]#
Sets maximum length of output text.
- Parameters:
- valueint
Maximum length of output text
- setDoSample(value)[source]#
Sets whether or not to use sampling, use greedy decoding otherwise.
- Parameters:
- valuebool
Whether or not to use sampling; use greedy decoding otherwise
- setTemperature(value)[source]#
Sets the value used to module the next token probabilities.
- Parameters:
- valuefloat
The value used to module the next token probabilities
- setTopK(value)[source]#
Sets the number of highest probability vocabulary tokens to keep for top-k-filtering.
- Parameters:
- valueint
Number of highest probability vocabulary tokens to keep
- setTopP(value)[source]#
Sets the top cumulative probability for vocabulary tokens.
If set to float < 1, only the most probable tokens with probabilities that add up to
topP
or higher are kept for generation.- Parameters:
- valuefloat
Cumulative probability for vocabulary tokens
- setRepetitionPenalty(value)[source]#
Sets the parameter for repetition penalty. 1.0 means no penalty.
- Parameters:
- valuefloat
The repetition penalty
References
See Ctrl: A Conditional Transformer Language Model For Controllable Generation for more details.
- setNoRepeatNgramSize(value)[source]#
Sets size of n-grams that can only occur once.
If set to int > 0, all ngrams of that size can only occur once.
- Parameters:
- valueint
N-gram size can only occur once
- setBeamSize(value)[source]#
Sets the number of beam size for beam search, by default 4.
- Parameters:
- valueint
Number of beam size for beam search
- static loadSavedModel(folder, spark_session, use_openvino=False)[source]#
Loads a locally saved model.
- Parameters:
- folderstr
Folder of the saved model
- spark_sessionpyspark.sql.SparkSession
The current SparkSession
- Returns:
- PaliGemmaForMultiModal
The restored model
- static pretrained(name='paligemma_3b_pt_224_int4', lang='en', remote_loc=None)[source]#
Downloads and loads a pretrained model.
- Parameters:
- namestr, optional
Name of the pretrained model, by default “paligemma_3b_pt_224_int4”
- langstr, optional
Language of the pretrained model, by default “en”
- remote_locstr, optional
Optional remote address of the resource, by default None. Will use Spark NLPs repositories otherwise.
- Returns:
- PaliGemmaForMultiModal
The restored model