Last active
January 12, 2021 07:32
-
-
Save Bhavesh-Joshi/4db376e4aa6a2ef808c4e54618acc987 to your computer and use it in GitHub Desktop.
VQA_Ludwig
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from ludwig.api import LudwigModel | |
| import logging | |
| import pandas as pd | |
| data_dict = {'Path': ['/data/Antenna.jpg'], 'Question': ['is antenna visible?'], 'Answer': ['No']} | |
| data = pd.DataFrame.from_dict(data_dict) | |
| print(data) | |
| config = {'combiner': {'type': 'concat'}, | |
| 'input_features': [{'column': 'Path', | |
| 'encoder': 'stacked_cnn', | |
| 'level': 'word', | |
| 'name': 'Path', | |
| 'preprocessing': {}, | |
| 'proc_column': 'Path_mZFLky', | |
| 'tied': None, | |
| 'type': 'image'}, | |
| {'column': 'Question', | |
| 'encoder': 'stacked_cnn', | |
| 'level': 'word', | |
| 'name': 'Question', | |
| 'proc_column': 'Question_mZFLky', | |
| 'tied': None, | |
| 'type': 'text'}], | |
| 'output_features': [{'cell_type': 'lstm', | |
| 'column': 'Answer', | |
| 'decoder': 'generator', | |
| 'dependencies': [], | |
| 'level': 'word', | |
| 'loss': {'class_similarities_temperature': 0, | |
| 'class_weights': 1, | |
| 'confidence_penalty': 0, | |
| 'distortion': 1, | |
| 'labels_smoothing': 0, | |
| 'negative_samples': 0, | |
| 'robust_lambda': 0, | |
| 'sampler': None, | |
| 'type': 'softmax_cross_entropy', | |
| 'unique': False, | |
| 'weight': 1}, | |
| 'name': 'Answer', | |
| 'proc_column': 'Answer_mZFLky', | |
| 'reduce_dependencies': 'sum', | |
| 'reduce_input': 'sum', | |
| 'type': 'text'}], | |
| 'preprocessing': {'audio': {'audio_feature': {'type': 'raw'}, | |
| 'audio_file_length_limit_in_s': 7.5, | |
| 'in_memory': True, | |
| 'missing_value_strategy': 'backfill', | |
| 'norm': None, | |
| 'padding_value': 0}, | |
| 'bag': {'fill_value': '<UNK>', | |
| 'lowercase': False, | |
| 'missing_value_strategy': 'fill_with_const', | |
| 'most_common': 10000, | |
| 'tokenizer': 'space'}, | |
| 'binary': {'fill_value': 0, | |
| 'missing_value_strategy': 'fill_with_const'}, | |
| 'category': {'fill_value': '<UNK>', | |
| 'lowercase': False, | |
| 'missing_value_strategy': 'fill_with_const', | |
| 'most_common': 10000}, | |
| 'date': {'datetime_format': None, | |
| 'fill_value': '', | |
| 'missing_value_strategy': 'fill_with_const'}, | |
| 'force_split': False, | |
| 'h3': {'fill_value': 576495936675512319, | |
| 'missing_value_strategy': 'fill_with_const'}, | |
| 'image': {'in_memory': True, | |
| 'missing_value_strategy': 'backfill', | |
| 'num_processes': 1, | |
| 'resize_method': 'interpolate', | |
| 'scaling': 'pixel_normalization'}, | |
| 'numerical': {'fill_value': 0, | |
| 'missing_value_strategy': 'fill_with_const', | |
| 'normalization': None}, | |
| 'sequence': {'fill_value': '<UNK>', | |
| 'lowercase': False, | |
| 'missing_value_strategy': 'fill_with_const', | |
| 'most_common': 20000, | |
| 'padding': 'right', | |
| 'padding_symbol': '<PAD>', | |
| 'sequence_length_limit': 256, | |
| 'tokenizer': 'space', | |
| 'unknown_symbol': '<UNK>', | |
| 'vocab_file': None}, | |
| 'set': {'fill_value': '<UNK>', | |
| 'lowercase': False, | |
| 'missing_value_strategy': 'fill_with_const', | |
| 'most_common': 10000, | |
| 'tokenizer': 'space'}, | |
| 'split_probabilities': (0.7, 0.1, 0.2), | |
| 'stratify': None, | |
| 'text': {'char_most_common': 70, | |
| 'char_sequence_length_limit': 1024, | |
| 'char_tokenizer': 'characters', | |
| 'char_vocab_file': None, | |
| 'fill_value': '<UNK>', | |
| 'lowercase': True, | |
| 'missing_value_strategy': 'fill_with_const', | |
| 'padding': 'right', | |
| 'padding_symbol': '<PAD>', | |
| 'pretrained_model_name_or_path': None, | |
| 'unknown_symbol': '<UNK>', | |
| 'word_most_common': 20000, | |
| 'word_sequence_length_limit': 256, | |
| 'word_tokenizer': 'space_punct', | |
| 'word_vocab_file': None}, | |
| 'timeseries': {'fill_value': '', | |
| 'missing_value_strategy': 'fill_with_const', | |
| 'padding': 'right', | |
| 'padding_value': 0, | |
| 'timeseries_length_limit': 256, | |
| 'tokenizer': 'space'}, | |
| 'vector': {'fill_value': '', | |
| 'missing_value_strategy': 'fill_with_const'}}, | |
| 'training': {'batch_size': 128, | |
| 'bucketing_field': None, | |
| 'decay': False, | |
| 'decay_rate': 0.96, | |
| 'decay_steps': 10000, | |
| 'early_stop': 5, | |
| 'epochs': 1, | |
| 'eval_batch_size': 0, | |
| 'gradient_clipping': None, | |
| 'increase_batch_size_on_plateau': 0, | |
| 'increase_batch_size_on_plateau_max': 512, | |
| 'increase_batch_size_on_plateau_patience': 5, | |
| 'increase_batch_size_on_plateau_rate': 2, | |
| 'learning_rate': 0.001, | |
| 'learning_rate_warmup_epochs': 1, | |
| 'optimizer': {'beta_1': 0.9, | |
| 'beta_2': 0.999, | |
| 'epsilon': 1e-08, | |
| 'type': 'adam'}, | |
| 'reduce_learning_rate_on_plateau': 0, | |
| 'reduce_learning_rate_on_plateau_patience': 5, | |
| 'reduce_learning_rate_on_plateau_rate': 0.5, | |
| 'regularization_lambda': 0, | |
| 'regularizer': 'l2', | |
| 'staircase': False, | |
| 'validation_field': 'combined', | |
| 'validation_metric': 'loss'}} | |
| model = LudwigModel(config, | |
| logging_level=logging.INFO) | |
| model.train(training_set=data, model_name="demo", output_directory="/data/model") | |
| model.save_savedmodel('/data/tensor') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment