Multimodal Data Tables: Tabular, Text, and Image¶
Tip: Prior to reading this tutorial, it is recommended to have a basic understanding of the TabularPredictor API covered in Predicting Columns in a Table - Quick Start.
In this tutorial, we will train a multi-modal ensemble using data that contains image, text, and tabular features.
Note: A GPU is required for this tutorial in order to train the image and text models. Additionally, GPU installations are required for MXNet and Torch with appropriate CUDA versions.
The PetFinder Dataset¶
We will be using the PetFinder dataset. The PetFinder dataset provides information about shelter animals that appear on their adoption profile with the goal to predict the adoption rate of the animal. The end goal is for rescue shelters to use the predicted adoption rate to identify animals whose profiles could be improved so that they can find a home.
Each animal’s adoption profile contains a variety of information, such as pictures of the animal, a text description of the animal, and various tabular features such as age, breed, name, color, and more.
To get started, we first need to download the dataset. Datasets that contain images require more than a CSV file, so the dataset is packaged in a zip file in S3. We will first download it and unzip the contents:
download_dir = './ag_petfinder_tutorial'
zip_file = 'https://automl-mm-bench.s3.amazonaws.com/petfinder_kaggle.zip'
from autogluon.core.utils.loaders import load_zip
load_zip.unzip(zip_file, unzip_dir=download_dir)
Downloading ./ag_petfinder_tutorial/file.zip from https://automl-mm-bench.s3.amazonaws.com/petfinder_kaggle.zip...
100%|██████████| 2.00G/2.00G [00:47<00:00, 42.0MiB/s]
Now that the data is download and unzipped, let’s take a look at the contents:
import os
os.listdir(download_dir)
['file.zip', 'petfinder_processed']
‘file.zip’ is the original zip file we downloaded, and ‘petfinder_processed’ is a directory containing the dataset files.
dataset_path = download_dir + '/petfinder_processed'
os.listdir(dataset_path)
['train.csv', 'train_images', 'test.csv', 'test_images', 'dev.csv']
Here we can see the train, test, and dev CSV files, as well as two directories: ‘test_images’ and ‘train_images’ which contain the image JPG files.
Note: We will be using the dev data as testing data as dev contains the
ground truth labels for showing scores via predictor.leaderboard.
Let’s take a peek at the first 10 files inside of the ‘train_images’ directory:
os.listdir(dataset_path + '/train_images')[:10]
['d765ae877-1.jpg',
'756025f7c-2.jpg',
'e1a2d9477-4.jpg',
'6d18707ee-2.jpg',
'96607bca0-5.jpg',
'fde58f7fa-10.jpg',
'be7b65c23-3.jpg',
'dd36ab692-3.jpg',
'2d8db1c19-2.jpg',
'53037f091-2.jpg']
As expected, these are the images we will be training with alongside the other features.
Next, we will load the train and dev CSV files:
import pandas as pd
train_data = pd.read_csv(f'{dataset_path}/train.csv', index_col=0)
test_data = pd.read_csv(f'{dataset_path}/dev.csv', index_col=0)
train_data.head(3)
| Type | Name | Age | Breed1 | Breed2 | Gender | Color1 | Color2 | Color3 | MaturitySize | ... | Quantity | Fee | State | RescuerID | VideoAmt | Description | PetID | PhotoAmt | AdoptionSpeed | Images | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 10721 | 1 | Elbi | 2 | 307 | 307 | 2 | 5 | 0 | 0 | 3 | ... | 1 | 0 | 41336 | e9a86209c54f589ba72c345364cf01aa | 0 | I'm looking for people to adopt my dog | e4b90955c | 4.0 | 4 | train_images/e4b90955c-1.jpg;train_images/e4b9... |
| 13114 | 2 | Darling | 4 | 266 | 0 | 1 | 1 | 0 | 0 | 2 | ... | 1 | 0 | 41401 | 01f954cdf61526daf3fbeb8a074be742 | 0 | Darling was born at the back lane of Jalan Alo... | a0c1384d1 | 5.0 | 3 | train_images/a0c1384d1-1.jpg;train_images/a0c1... |
| 13194 | 1 | Wolf | 3 | 307 | 0 | 1 | 1 | 2 | 0 | 2 | ... | 1 | 0 | 41332 | 6e19409f2847326ce3b6d0cec7e42f81 | 0 | I found Wolf about a month ago stuck in a drai... | cf357f057 | 7.0 | 4 | train_images/cf357f057-1.jpg;train_images/cf35... |
3 rows × 25 columns
Looking at the first 3 examples, we can tell that there is a variety of tabular features, a text description (‘Description’), and an image path (‘Images’).
For the PetFinder dataset, we will try to predict the speed of adoption for the animal (‘AdoptionSpeed’), grouped into 5 categories. This means that we are dealing with a multi-class classification problem.
label = 'AdoptionSpeed'
image_col = 'Images'
Preparing the image column¶
Let’s take a look at what a value in the image column looks like:
train_data[image_col].iloc[0]
'train_images/e4b90955c-1.jpg;train_images/e4b90955c-2.jpg;train_images/e4b90955c-3.jpg;train_images/e4b90955c-4.jpg'
Currently, AutoGluon only supports one image per row. Since the PetFinder dataset contains one or more images per row, we first need to preprocess the image column to only contain the first image of each row.
train_data[image_col] = train_data[image_col].apply(lambda ele: ele.split(';')[0])
test_data[image_col] = test_data[image_col].apply(lambda ele: ele.split(';')[0])
train_data[image_col].iloc[0]
'train_images/e4b90955c-1.jpg'
AutoGluon loads images based on the file path provided by the image column.
Here we update the path to point to the correct location on disk:
def path_expander(path, base_folder):
path_l = path.split(';')
return ';'.join([os.path.abspath(os.path.join(base_folder, path)) for path in path_l])
train_data[image_col] = train_data[image_col].apply(lambda ele: path_expander(ele, base_folder=dataset_path))
test_data[image_col] = test_data[image_col].apply(lambda ele: path_expander(ele, base_folder=dataset_path))
train_data[image_col].iloc[0]
'/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/ag_petfinder_tutorial/petfinder_processed/train_images/e4b90955c-1.jpg'
train_data.head(3)
| Type | Name | Age | Breed1 | Breed2 | Gender | Color1 | Color2 | Color3 | MaturitySize | ... | Quantity | Fee | State | RescuerID | VideoAmt | Description | PetID | PhotoAmt | AdoptionSpeed | Images | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 10721 | 1 | Elbi | 2 | 307 | 307 | 2 | 5 | 0 | 0 | 3 | ... | 1 | 0 | 41336 | e9a86209c54f589ba72c345364cf01aa | 0 | I'm looking for people to adopt my dog | e4b90955c | 4.0 | 4 | /home/ci/autogluon/docs/_build/eval/tutorials/... |
| 13114 | 2 | Darling | 4 | 266 | 0 | 1 | 1 | 0 | 0 | 2 | ... | 1 | 0 | 41401 | 01f954cdf61526daf3fbeb8a074be742 | 0 | Darling was born at the back lane of Jalan Alo... | a0c1384d1 | 5.0 | 3 | /home/ci/autogluon/docs/_build/eval/tutorials/... |
| 13194 | 1 | Wolf | 3 | 307 | 0 | 1 | 1 | 2 | 0 | 2 | ... | 1 | 0 | 41332 | 6e19409f2847326ce3b6d0cec7e42f81 | 0 | I found Wolf about a month ago stuck in a drai... | cf357f057 | 7.0 | 4 | /home/ci/autogluon/docs/_build/eval/tutorials/... |
3 rows × 25 columns
Analyzing an example row¶
Now that we have preprocessed the image column, let’s take a look at an example row of data and display the text description and the picture.
example_row = train_data.iloc[1]
example_row
Type 2
Name Darling
Age 4
Breed1 266
Breed2 0
Gender 1
Color1 1
Color2 0
Color3 0
MaturitySize 2
FurLength 1
Vaccinated 2
Dewormed 2
Sterilized 2
Health 1
Quantity 1
Fee 0
State 41401
RescuerID 01f954cdf61526daf3fbeb8a074be742
VideoAmt 0
Description Darling was born at the back lane of Jalan Alo...
PetID a0c1384d1
PhotoAmt 5.0
AdoptionSpeed 3
Images /home/ci/autogluon/docs/_build/eval/tutorials/...
Name: 13114, dtype: object
example_row['Description']
'Darling was born at the back lane of Jalan Alor and was foster by a feeder. All his siblings had died of accident. His mother and grandmother had just been spayed. Darling make a great condo/apartment cat. He love to play a lot. He would make a great companion for someone looking for a cat to love.'
example_image = example_row['Images']
from IPython.display import Image, display
pil_img = Image(filename=example_image)
display(pil_img)
The PetFinder dataset is fairly large. For the purposes of the tutorial, we will sample 500 rows for training.
Training on large multi-modal datasets can be very computationally
intensive, especially if using the best_quality preset in AutoGluon.
When prototyping, it is recommended to sample your data to get an idea
of which models are worth training, then gradually train with larger
amounts of data and longer time limits as you would with any other
machine learning algorithm.
train_data = train_data.sample(500, random_state=0)
Constructing the FeatureMetadata¶
Next, let’s see what AutoGluon infers the feature types to be by constructing a FeatureMetadata object from the training data:
from autogluon.tabular import FeatureMetadata
feature_metadata = FeatureMetadata.from_df(train_data)
print(feature_metadata)
('float', []) : 1 | ['PhotoAmt']
('int', []) : 19 | ['Type', 'Age', 'Breed1', 'Breed2', 'Gender', ...]
('object', []) : 4 | ['Name', 'RescuerID', 'PetID', 'Images']
('object', ['text']) : 1 | ['Description']
Notice that FeatureMetadata automatically identified the column ‘Description’ as text, so we don’t need to manually specify that it is text.
In order to leverage images, we need to tell AutoGluon which column contains the image path. We can do this by specifying a FeatureMetadata object and adding the ‘image_path’ special type to the image column. We later pass this custom FeatureMetadata to TabularPredictor.fit.
feature_metadata = feature_metadata.add_special_types({image_col: ['image_path']})
print(feature_metadata)
('float', []) : 1 | ['PhotoAmt']
('int', []) : 19 | ['Type', 'Age', 'Breed1', 'Breed2', 'Gender', ...]
('object', []) : 3 | ['Name', 'RescuerID', 'PetID']
('object', ['image_path']) : 1 | ['Images']
('object', ['text']) : 1 | ['Description']
Specifying the hyperparameters¶
Next, we need to specify the models we want to train with. This is done
via the hyperparameters argument to TabularPredictor.fit.
AutoGluon has a predefined config that works well for multimodal datasets called ‘multimodal’. We can access it via:
from autogluon.tabular.configs.hyperparameter_configs import get_hyperparameter_config
hyperparameters = get_hyperparameter_config('multimodal')
hyperparameters
{'NN_TORCH': {},
'GBM': [{},
{'extra_trees': True, 'ag_args': {'name_suffix': 'XT'}},
'GBMLarge'],
'CAT': {},
'XGB': {},
'AG_TEXT_NN': {'presets': 'medium_quality_faster_train'},
'AG_IMAGE_NN': {},
'VW': {}}
This hyperparameter config will train a variety of Tabular models as well as finetune an Electra BERT text model, and a ResNet image model.
Fitting with TabularPredictor¶
Now we will train a TabularPredictor on the dataset, using the feature metadata and hyperparameters we defined prior. This TabularPredictor will leverage tabular, text, and image features all at once.
from autogluon.tabular import TabularPredictor
predictor = TabularPredictor(label=label).fit(
train_data=train_data,
hyperparameters=hyperparameters,
feature_metadata=feature_metadata,
time_limit=900,
)
No path specified. Models will be saved in: "AutogluonModels/ag-20221117_032922/"
Beginning AutoGluon training ... Time limit = 900s
AutoGluon will save models to "AutogluonModels/ag-20221117_032922/"
AutoGluon Version: 0.6.0b20221117
Python Version: 3.8.10
Operating System: Linux
Platform Machine: x86_64
Platform Version: #1 SMP Tue Nov 30 00:17:50 UTC 2021
Train Data Rows: 500
Train Data Columns: 24
Label Column: AdoptionSpeed
Preprocessing data ...
AutoGluon infers your prediction problem is: 'multiclass' (because dtype of label-column == int, but few unique label-values observed).
5 unique label values: [2, 3, 4, 0, 1]
If 'multiclass' is not the correct problem_type, please manually specify the problem_type parameter during predictor init (You may specify problem_type as one of: ['binary', 'multiclass', 'regression'])
Train Data Class Count: 5
Using Feature Generators to preprocess the data ...
Fitting AutoMLPipelineFeatureGenerator...
Available Memory: 31481.48 MB
Train Data (Original) Memory Usage: 0.49 MB (0.0% of available memory)
Stage 1 Generators:
Fitting AsTypeFeatureGenerator...
Note: Converting 1 features to boolean dtype as they only contain 2 unique values.
Stage 2 Generators:
Fitting FillNaFeatureGenerator...
Stage 3 Generators:
Fitting IdentityFeatureGenerator...
Fitting IdentityFeatureGenerator...
Fitting RenameFeatureGenerator...
Fitting CategoryFeatureGenerator...
Fitting CategoryMemoryMinimizeFeatureGenerator...
Fitting TextSpecialFeatureGenerator...
Fitting BinnedFeatureGenerator...
Fitting DropDuplicatesFeatureGenerator...
Fitting TextNgramFeatureGenerator...
Fitting CountVectorizer for text features: ['Description']
CountVectorizer fit with vocabulary size = 170
Fitting IdentityFeatureGenerator...
Fitting IsNanFeatureGenerator...
Stage 4 Generators:
Fitting DropUniqueFeatureGenerator...
Unused Original Features (Count: 1): ['PetID']
These features were not used to generate any of the output features. Add a feature generator compatible with these features to utilize them.
Features can also be unused if they carry very little information, such as being categorical but having almost entirely unique values or being duplicates of other features.
These features do not need to be present at inference time.
('object', []) : 1 | ['PetID']
Types of features in original data (raw dtype, special dtypes):
('float', []) : 1 | ['PhotoAmt']
('int', []) : 18 | ['Type', 'Age', 'Breed1', 'Breed2', 'Gender', ...]
('object', []) : 2 | ['Name', 'RescuerID']
('object', ['image_path']) : 1 | ['Images']
('object', ['text']) : 1 | ['Description']
Types of features in processed data (raw dtype, special dtypes):
('category', []) : 2 | ['Name', 'RescuerID']
('category', ['text_as_category']) : 1 | ['Description']
('float', []) : 1 | ['PhotoAmt']
('int', []) : 17 | ['Age', 'Breed1', 'Breed2', 'Gender', 'Color1', ...]
('int', ['binned', 'text_special']) : 24 | ['Description.char_count', 'Description.word_count', 'Description.capital_ratio', 'Description.lower_ratio', 'Description.digit_ratio', ...]
('int', ['bool']) : 1 | ['Type']
('int', ['text_ngram']) : 171 | ['__nlp__.about', '__nlp__.active', '__nlp__.active and', '__nlp__.adopt', '__nlp__.adopted', ...]
('object', ['image_path']) : 1 | ['Images']
('object', ['text']) : 1 | ['Description_raw_text']
0.5s = Fit runtime
23 features in original data used to generate 219 features in processed data.
Train Data (Processed) Memory Usage: 0.56 MB (0.0% of available memory)
Data preprocessing and feature engineering runtime = 0.49s ...
AutoGluon will gauge predictive performance using evaluation metric: 'accuracy'
To change this, specify the eval_metric parameter of Predictor()
Automatically generating train/validation split with holdout_frac=0.2, Train Rows: 400, Val Rows: 100
Fitting 9 L1 models ...
Fitting model: LightGBM ... Training model for up to 899.51s of the 899.5s of remaining time.
0.34 = Validation score (accuracy)
1.74s = Training runtime
0.01s = Validation runtime
Fitting model: LightGBMXT ... Training model for up to 897.75s of the 897.75s of remaining time.
0.34 = Validation score (accuracy)
1.46s = Training runtime
0.01s = Validation runtime
Fitting model: CatBoost ... Training model for up to 896.27s of the 896.27s of remaining time.
0.3 = Validation score (accuracy)
3.12s = Training runtime
0.01s = Validation runtime
Fitting model: XGBoost ... Training model for up to 893.13s of the 893.13s of remaining time.
0.35 = Validation score (accuracy)
2.03s = Training runtime
0.01s = Validation runtime
Fitting model: NeuralNetTorch ... Training model for up to 891.08s of the 891.08s of remaining time.
0.35 = Validation score (accuracy)
2.06s = Training runtime
0.03s = Validation runtime
Fitting model: VowpalWabbit ... Training model for up to 888.99s of the 888.98s of remaining time.
0.24 = Validation score (accuracy)
0.66s = Training runtime
0.03s = Validation runtime
Fitting model: LightGBMLarge ... Training model for up to 888.03s of the 888.02s of remaining time.
0.37 = Validation score (accuracy)
2.51s = Training runtime
0.01s = Validation runtime
Fitting model: TextPredictor ... Training model for up to 885.5s of the 885.5s of remaining time.
The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling transformers.utils.move_cache().
Moving 0 files to the new cache system
0it [00:00, ?it/s]
INFO:pytorch_lightning.utilities.seed:Global seed set to 0 INFO:pytorch_lightning.trainer.connectors.accelerator_connector:Auto select gpus: [0] INFO:pytorch_lightning.utilities.rank_zero:Using 16bit native Automatic Mixed Precision (AMP) INFO:pytorch_lightning.utilities.rank_zero:GPU available: True (cuda), used: True INFO:pytorch_lightning.utilities.rank_zero:TPU available: False, using: 0 TPU cores INFO:pytorch_lightning.utilities.rank_zero:IPU available: False, using: 0 IPUs INFO:pytorch_lightning.utilities.rank_zero:HPU available: False, using: 0 HPUs INFO:pytorch_lightning.accelerators.cuda:LOCAL_RANK: 0 - CUDA_VISIBLE_DEVICES: [0] INFO:pytorch_lightning.callbacks.model_summary: | Name | Type | Params ---------------------------------------------------------- 0 | model | MultimodalFusionMLP | 13.7 M 1 | validation_metric | Accuracy | 0 2 | loss_func | CrossEntropyLoss | 0 ---------------------------------------------------------- 13.7 M Trainable params 0 Non-trainable params 13.7 M Total params 27.305 Total estimated model params size (MB) INFO:pytorch_lightning.utilities.rank_zero:Epoch 0, global step 1: 'val_accuracy' reached 0.24000 (best 0.24000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=0-step=1.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 0, global step 4: 'val_accuracy' reached 0.23000 (best 0.24000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=0-step=4.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 1, global step 5: 'val_accuracy' reached 0.23000 (best 0.24000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=1-step=5.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 1, global step 8: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 2, global step 9: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 2, global step 12: 'val_accuracy' reached 0.30000 (best 0.30000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=2-step=12.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 3, global step 13: 'val_accuracy' reached 0.29000 (best 0.30000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=3-step=13.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 3, global step 16: 'val_accuracy' reached 0.34000 (best 0.34000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=3-step=16.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 4, global step 17: 'val_accuracy' reached 0.34000 (best 0.34000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=4-step=17.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 4, global step 20: 'val_accuracy' reached 0.31000 (best 0.34000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=4-step=20.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 5, global step 21: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 5, global step 24: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 6, global step 25: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 6, global step 28: 'val_accuracy' reached 0.34000 (best 0.34000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=6-step=28.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 7, global step 29: 'val_accuracy' reached 0.35000 (best 0.35000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=7-step=29.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 7, global step 32: 'val_accuracy' reached 0.35000 (best 0.35000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=7-step=32.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 8, global step 33: 'val_accuracy' reached 0.35000 (best 0.35000), saving model to '/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/epoch=8-step=33.ckpt' as top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 8, global step 36: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 9, global step 37: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Epoch 9, global step 40: 'val_accuracy' was not in top 3 INFO:pytorch_lightning.utilities.rank_zero:Trainer.fit stopped: max_epochs=10 reached. Configuration saved in AutogluonModels/ag-20221117_032922/models/TextPredictor/text_nn/hf_text/config.json tokenizer config file saved in AutogluonModels/ag-20221117_032922/models/TextPredictor/text_nn/hf_text/tokenizer_config.json Special tokens file saved in AutogluonModels/ag-20221117_032922/models/TextPredictor/text_nn/hf_text/special_tokens_map.json 0.35 = Validation score (accuracy) 73.67s = Training runtime 1.24s = Validation runtime Fitting model: ImagePredictor ... Training model for up to 810.4s of the 810.4s of remaining time. AutoGluon ImagePredictor will be deprecated in v0.7. Please use AutoGluon MultiModalPredictor instead for more functionalities and better support. Visit https://auto.gluon.ai/stable/tutorials/multimodal/index.html for more details! ImagePredictor sets accuracy as default eval_metric for classification problems. The number of requested GPUs is greater than the number of available GPUs.Reduce the number to 1 INFO:TorchImageClassificationEstimator:modified configs(<old> != <new>): { INFO:TorchImageClassificationEstimator:root.img_cls.model resnet101 != resnet50 INFO:TorchImageClassificationEstimator:root.train.early_stop_patience -1 != 10 INFO:TorchImageClassificationEstimator:root.train.batch_size 32 != 16 INFO:TorchImageClassificationEstimator:root.train.early_stop_max_value 1.0 != inf INFO:TorchImageClassificationEstimator:root.train.epochs 200 != 15 INFO:TorchImageClassificationEstimator:root.train.early_stop_baseline 0.0 != -inf INFO:TorchImageClassificationEstimator:root.misc.seed 42 != 542 INFO:TorchImageClassificationEstimator:root.misc.num_workers 4 != 8 INFO:TorchImageClassificationEstimator:} INFO:TorchImageClassificationEstimator:Saved config to /home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/ImagePredictor/54f44c9d/.trial_0/config.yaml Downloading: "https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-rsb-weights/resnet50_a1_0-14fe96d1.pth" to /home/ci/.cache/torch/hub/checkpoints/resnet50_a1_0-14fe96d1.pth INFO:TorchImageClassificationEstimator:Model resnet50 created, param count: 23518277 INFO:TorchImageClassificationEstimator:AMP not enabled. Training in float32. INFO:TorchImageClassificationEstimator:Disable EMA as it is not supported for now. INFO:TorchImageClassificationEstimator:Start training from [Epoch 0] INFO:TorchImageClassificationEstimator:[Epoch 0] training: accuracy=0.212500 INFO:TorchImageClassificationEstimator:[Epoch 0] speed: 83 samples/sec time cost: 4.613183 INFO:TorchImageClassificationEstimator:[Epoch 0] validation: top1=0.240000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 0] Current best top-1: 0.240000 vs previous -inf, saved to /home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/ImagePredictor/54f44c9d/.trial_0/best_checkpoint.pkl INFO:TorchImageClassificationEstimator:[Epoch 1] training: accuracy=0.292500 INFO:TorchImageClassificationEstimator:[Epoch 1] speed: 91 samples/sec time cost: 4.190000 INFO:TorchImageClassificationEstimator:[Epoch 1] validation: top1=0.210000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 2] training: accuracy=0.272500 INFO:TorchImageClassificationEstimator:[Epoch 2] speed: 91 samples/sec time cost: 4.197323 INFO:TorchImageClassificationEstimator:[Epoch 2] validation: top1=0.240000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 3] training: accuracy=0.330000 INFO:TorchImageClassificationEstimator:[Epoch 3] speed: 91 samples/sec time cost: 4.215506 INFO:TorchImageClassificationEstimator:[Epoch 3] validation: top1=0.220000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 4] training: accuracy=0.350000 INFO:TorchImageClassificationEstimator:[Epoch 4] speed: 91 samples/sec time cost: 4.198305 INFO:TorchImageClassificationEstimator:[Epoch 4] validation: top1=0.230000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 5] training: accuracy=0.407500 INFO:TorchImageClassificationEstimator:[Epoch 5] speed: 90 samples/sec time cost: 4.222308 INFO:TorchImageClassificationEstimator:[Epoch 5] validation: top1=0.230000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 6] training: accuracy=0.377500 INFO:TorchImageClassificationEstimator:[Epoch 6] speed: 90 samples/sec time cost: 4.223247 INFO:TorchImageClassificationEstimator:[Epoch 6] validation: top1=0.240000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 7] training: accuracy=0.450000 INFO:TorchImageClassificationEstimator:[Epoch 7] speed: 90 samples/sec time cost: 4.237841 INFO:TorchImageClassificationEstimator:[Epoch 7] validation: top1=0.250000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 7] Current best top-1: 0.250000 vs previous 0.240000, saved to /home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/ImagePredictor/54f44c9d/.trial_0/best_checkpoint.pkl INFO:TorchImageClassificationEstimator:[Epoch 8] training: accuracy=0.420000 INFO:TorchImageClassificationEstimator:[Epoch 8] speed: 90 samples/sec time cost: 4.236771 INFO:TorchImageClassificationEstimator:[Epoch 8] validation: top1=0.260000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 8] Current best top-1: 0.260000 vs previous 0.250000, saved to /home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/ImagePredictor/54f44c9d/.trial_0/best_checkpoint.pkl INFO:TorchImageClassificationEstimator:[Epoch 9] training: accuracy=0.385000 INFO:TorchImageClassificationEstimator:[Epoch 9] speed: 90 samples/sec time cost: 4.237117 INFO:TorchImageClassificationEstimator:[Epoch 9] validation: top1=0.220000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 10] training: accuracy=0.435000 INFO:TorchImageClassificationEstimator:[Epoch 10] speed: 90 samples/sec time cost: 4.257750 INFO:TorchImageClassificationEstimator:[Epoch 10] validation: top1=0.220000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 11] training: accuracy=0.400000 INFO:TorchImageClassificationEstimator:[Epoch 11] speed: 89 samples/sec time cost: 4.275775 INFO:TorchImageClassificationEstimator:[Epoch 11] validation: top1=0.290000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 11] Current best top-1: 0.290000 vs previous 0.260000, saved to /home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/ImagePredictor/54f44c9d/.trial_0/best_checkpoint.pkl INFO:TorchImageClassificationEstimator:[Epoch 12] training: accuracy=0.427500 INFO:TorchImageClassificationEstimator:[Epoch 12] speed: 89 samples/sec time cost: 4.277533 INFO:TorchImageClassificationEstimator:[Epoch 12] validation: top1=0.250000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 13] training: accuracy=0.397500 INFO:TorchImageClassificationEstimator:[Epoch 13] speed: 89 samples/sec time cost: 4.277427 INFO:TorchImageClassificationEstimator:[Epoch 13] validation: top1=0.230000 top5=1.000000 INFO:TorchImageClassificationEstimator:[Epoch 14] training: accuracy=0.460000 INFO:TorchImageClassificationEstimator:[Epoch 14] speed: 89 samples/sec time cost: 4.285224 INFO:TorchImageClassificationEstimator:[Epoch 14] validation: top1=0.170000 top5=1.000000 INFO:TorchImageClassificationEstimator:Applying the state from the best checkpoint... 0.29 = Validation score (accuracy) 74.47s = Training runtime 0.85s = Validation runtime Fitting model: WeightedEnsemble_L2 ... Training model for up to 360.0s of the 734.42s of remaining time. 0.37 = Validation score (accuracy) 0.22s = Training runtime 0.0s = Validation runtime AutoGluon training complete, total runtime = 165.82s ... Best model: "WeightedEnsemble_L2" TabularPredictor saved. To load, use: predictor = TabularPredictor.load("AutogluonModels/ag-20221117_032922/")
After the predictor is fit, we can take a look at the leaderboard and see the performance of the various models:
leaderboard = predictor.leaderboard(test_data)
loading file vocab.txt
loading file tokenizer.json
loading file added_tokens.json
loading file special_tokens_map.json
loading file tokenizer_config.json
loading configuration file /home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/text_nn/hf_text/config.json
Model config ElectraConfig {
"_name_or_path": "/home/ci/autogluon/docs/_build/eval/tutorials/tabular_prediction/AutogluonModels/ag-20221117_032922/models/TextPredictor/text_nn/hf_text",
"architectures": [
"ElectraForPreTraining"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"embedding_size": 128,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 256,
"initializer_range": 0.02,
"intermediate_size": 1024,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "electra",
"num_attention_heads": 4,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"transformers_version": "4.23.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}
Token indices sequence length is longer than the specified maximum sequence length for this model (587 > 512). Running this sequence through the model will result in indexing errors
Token indices sequence length is longer than the specified maximum sequence length for this model (1394 > 512). Running this sequence through the model will result in indexing errors
model score_test score_val pred_time_test pred_time_val fit_time pred_time_test_marginal pred_time_val_marginal fit_time_marginal stack_level can_infer fit_order
0 TextPredictor 0.328443 0.35 9.847726 1.235950 73.669594 9.847726 1.235950 73.669594 1 True 8
1 LightGBMLarge 0.323775 0.37 0.355263 0.005661 2.508864 0.355263 0.005661 2.508864 1 True 7
2 WeightedEnsemble_L2 0.323775 0.37 0.358679 0.006077 2.727630 0.003416 0.000416 0.218766 2 True 10
3 NeuralNetTorch 0.319773 0.35 0.065685 0.025325 2.059081 0.065685 0.025325 2.059081 1 True 5
4 CatBoost 0.319106 0.30 0.019486 0.010632 3.120211 0.019486 0.010632 3.120211 1 True 3
5 LightGBMXT 0.315772 0.34 0.036528 0.006484 1.458186 0.036528 0.006484 1.458186 1 True 2
6 ImagePredictor 0.305769 0.29 11.172094 0.848009 74.470711 11.172094 0.848009 74.470711 1 True 9
7 XGBoost 0.292431 0.35 0.056645 0.006397 2.027815 0.056645 0.006397 2.027815 1 True 4
8 LightGBM 0.289763 0.34 0.014313 0.005880 1.740600 0.014313 0.005880 1.740600 1 True 1
9 VowpalWabbit 0.278760 0.24 0.723644 0.030333 0.663287 0.723644 0.030333 0.663287 1 True 6
That’s all it takes to train with image, text, and tabular data (at the same time) using AutoGluon!
For an in-depth tutorial on text + tabular multimodal functionality, refer to Multimodal Data Tables: Combining BERT/Transformers and Classical Tabular Models.
For more tutorials, refer to Predicting Columns in a Table - Quick Start and Predicting Columns in a Table - In Depth.