# Image Prediction - Quick Start¶

In this quick start, we’ll use the task of image classification to illustrate how to use AutoGluon’s APIs. This tutorial demonstrates how to load images and corresponding labels into AutoGluon and use this data to obtain a neural network that can classify new images. This is different from traditional machine learning where we need to manually define the neural network and then specify the hyperparameters in the training process. Instead, with just a single call to AutoGluon’s fit function, AutoGluon automatically trains many models with different hyperparameter configurations and returns the model that achieved the highest level of accuracy.

import autogluon.core as ag
from autogluon.vision import ImagePredictor, ImageDataset

/var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/venv/lib/python3.7/site-packages/gluoncv/__init__.py:40: UserWarning: Both mxnet==1.7.0 and torch==1.7.1+cu101 are installed. You might encounter increased GPU memory footprint if both framework are used at the same time.
warnings.warn(f'Both mxnet=={mx.__version__} and torch=={torch.__version__} are installed. '

## Create Image Dataset¶

For demonstration purposes, we use a subset of the Shopee-IET dataset from Kaggle. Each image in this data depicts a clothing item and the corresponding label specifies its clothing category. Our subset of the data contains the following possible labels: BabyPants, BabyShirt, womencasualshoes, womenchiffontop.

train_dataset, _, test_dataset = ImageDataset.from_folders('https://autogluon.s3.amazonaws.com/datasets/shopee-iet.zip')
print(train_dataset)

data/
├── test/
└── train/
image  label
0    /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      0
1    /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      0
2    /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      0
3    /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      0
4    /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      0
..                                                 ...    ...
795  /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      3
796  /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      3
797  /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      3
798  /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      3
799  /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...      3

[800 rows x 2 columns]


## Use AutoGluon to Fit Models¶

Now, we fit a classifier using AutoGluon as follows:

predictor = ImagePredictor()
# since the original dataset does not provide validation split, the fit function splits it randomly with 90/10 ratio
predictor.fit(train_dataset, hyperparameters={'epochs': 2})  # you can trust the default config, we reduce the # epoch to save some build time

time_limit=auto set to time_limit=7200.
Reset labels to [0, 1, 2, 3]
Randomly split train_data into train[720]/validation[80] splits.
The number of requested GPUs is greater than the number of available GPUs.Reduce the number to 1
Starting fit without HPO
modified configs(<old> != <new>): {
root.misc.seed       42 != 142
root.misc.num_workers 4 != 8
root.img_cls.model   resnet101 != resnet50
root.train.epochs    200 != 2
root.train.early_stop_max_value 1.0 != inf
root.train.early_stop_patience -1 != 10
root.train.batch_size 32 != 16
root.train.early_stop_baseline 0.0 != -inf
}
Saved config to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/73490176/.trial_0/config.yaml
Model resnet50 created, param count:                                         23516228
AMP not enabled. Training in float32.
Disable EMA as it is not supported for now.
Start training from [Epoch 0]
[Epoch 0] training: accuracy=0.376389
[Epoch 0] speed: 89 samples/sec     time cost: 7.880118
[Epoch 0] validation: top1=0.475000 top5=1.000000
[Epoch 0] Current best top-1: 0.475000 vs previous -inf, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/73490176/.trial_0/best_checkpoint.pkl
[Epoch 1] training: accuracy=0.526389
[Epoch 1] speed: 93 samples/sec     time cost: 7.548804
[Epoch 1] validation: top1=0.737500 top5=1.000000
[Epoch 1] Current best top-1: 0.737500 vs previous 0.475000, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/73490176/.trial_0/best_checkpoint.pkl
Applying the state from the best checkpoint...
Finished, total runtime is 24.19 s
{ 'best_config': { 'batch_size': 16,
'early_stop_baseline': -inf,
'early_stop_max_value': inf,
'early_stop_patience': 10,
'epochs': 2,
'final_fit': False,
'gpus': [0],
'log_dir': '/var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/73490176',
'lr': 0.01,
'model': 'resnet50',
'ngpus_per_trial': 8,
'num_trials': 1,
'num_workers': 8,
'problem_type': 'multiclass',
'scheduler': 'local',
'search_strategy': 'random',
'searcher': 'random',
'seed': 142,
'time_limits': 7200,
'wall_clock_tick': 1631937266.7289402},
'total_time': 16.869351625442505,
'train_acc': 0.5263888888888889,
'valid_acc': 0.7375}
<autogluon.vision.predictor.predictor.ImagePredictor at 0x7f75d3fc8e10>


Within fit, the dataset is automatically split into training and validation sets. The model with the best hyperparameter configuration is selected based on its performance on the validation set. The best model is finally retrained on our entire dataset (i.e., merging training+validation) using the best configuration.

The best Top-1 accuracy achieved on the validation set is as follows:

fit_result = predictor.fit_summary()
print('Top-1 train acc: %.3f, val acc: %.3f' %(fit_result['train_acc'], fit_result['valid_acc']))

Top-1 train acc: 0.526, val acc: 0.738


## Predict on a New Image¶

Given an example image, we can easily use the final model to predict the label (and the conditional class-probability denoted as score):

image_path = test_dataset.iloc[0]['image']
result = predictor.predict(image_path)
print(result)

0    1
Name: label, dtype: int64


If probabilities of all categories are needed, you can call predict_proba:

proba = predictor.predict_proba(image_path)
print(proba)

          0         1         2         3
0  0.260168  0.310625  0.238398  0.190809


You can also feed in multiple images all together, let’s use images in test dataset as an example:

bulk_result = predictor.predict(test_dataset)
print(bulk_result)

0     1
1     1
2     3
3     2
4     1
..
75    3
76    3
77    3
78    3
79    2
Name: label, Length: 80, dtype: int64


An extra column will be included in bulk prediction, indicate the corresponding image for the row. There will be (# image) rows in the result, each row includes class, score, id and image for prediction class, prediction confidence, class id, and image path respectively.

## Generate image features with a classifier¶

Extracting representation from the whole image learned by a model is also very useful. We provide predict_feature function to allow predictor to return the N-dimensional image feature where N depends on the model(usually a 512 to 2048 length vector)

image_path = test_dataset.iloc[0]['image']
feature = predictor.predict_feature(image_path)
print(feature)

                                       image_feature  0  [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, ...

image
0  /var/lib/jenkins/.gluoncv/datasets/shopee-iet/...

## Evaluate on Test Dataset¶

You can evaluate the classifier on a test dataset rather than retrieving the predictions.

The validation and test top-1 accuracy are:

test_acc = predictor.evaluate(test_dataset)
print('Top-1 test acc: %.3f' % test_acc['top1'])

[Epoch 1] validation: top1=0.725000 top5=1.000000

Top-1 test acc: 0.725


filename = 'predictor.ag'

0    1