.. _sec_imgadvanced: Image Prediction - Search Space and Hyperparameter Optimization (HPO) ===================================================================== While the :ref:`sec_imgquick` introduced basic usage of AutoGluon ``fit``, ``evaluate``, ``predict`` with default configurations, this tutorial dives into the various options that you can specify for more advanced control over the fitting process. These options include: - Defining the search space of various hyperparameter values for the training of neural networks - Specifying how to search through your choosen hyperparameter space - Specifying how to schedule jobs to train a network under a particular hyperparameter configuration. The advanced functionalities of AutoGluon enable you to use your external knowledge about your particular prediction problem and computing resources to guide the training process. If properly used, you may be able to achieve superior performance within less training time. **Tip**: If you are new to AutoGluon, review :ref:`sec_imgquick` to learn the basics of the AutoGluon API. Since our task is to classify images, we will use AutoGluon to produce an `ImagePredictor <../../api/autogluon.predictor.html#autogluon.vision.ImagePredictor>`__: .. code:: python import autogluon.core as ag from autogluon.vision import ImagePredictor, ImageDataset .. parsed-literal:: :class: output /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 AutoGluon Dataset ------------------------ Let's first create the dataset using the same subset of the ``Shopee-IET`` dataset as the :ref:`sec_imgquick` tutorial. Recall that there's no validation split in original data, a 90/10 train/validation split is automatically performed when ``fit`` with ``train_data``. .. code:: python train_data, _, test_data = ImageDataset.from_folders('https://autogluon.s3.amazonaws.com/datasets/shopee-iet.zip') .. parsed-literal:: :class: output data/ ├── test/ └── train/ Specify which Networks to Try ----------------------------- We start with specifying the pretrained neural network candidates. Given such a list, AutoGluon tries to train different networks from this list to identify the best-performing candidate. This is an example of a :class:`autogluon.core.space.Categorical` search space, in which there are a limited number of values to choose from. .. code:: python model = ag.Categorical('resnet18_v1b', 'mobilenetv3_small') # you may choose more than 70+ available model in the model zoo provided by GluonCV: model_list = ImagePredictor.list_models() Specify the training hyper-parameters ------------------------------------- Similarly, we can manually specify many crucial hyper-parameters, with specific value or search space(\ ``autogluon.core.space``). .. code:: python batch_size = 8 lr = ag.Categorical(1e-2, 1e-3) Search Algorithms ----------------- In AutoGluon, ``autogluon.core.searcher`` supports different search search strategies for both hyperparameter optimization and architecture search. Beyond simply specifying the space of hyperparameter configurations to search over, you can also tell AutoGluon what strategy it should employ to actually search through this space. This process of finding good hyperparameters from a given search space is commonly referred to as *hyperparameter optimization* (HPO) or *hyperparameter tuning*. ``autogluon.core.scheduler`` orchestrates how individual training jobs are scheduled. We currently support FIFO (standard) and Hyperband scheduling, along with search by random sampling or Bayesian optimization. These basic techniques are rendered surprisingly powerful by AutoGluon's support of asynchronous parallel execution. Bayesian Optimization ~~~~~~~~~~~~~~~~~~~~~ Here is an example of using Bayesian Optimization using :class:`autogluon.core.searcher.GPFIFOSearcher`. Bayesian Optimization fits a probabilistic *surrogate model* to estimate the function that relates each hyperparameter configuration to the resulting performance of a model trained under this hyperparameter configuration. Our implementation makes use of a Gaussian process surrogate model along with expected improvement as acquisition function. It has been developed specifically to support asynchronous parallel evaluations. .. code:: python hyperparameters={'model': model, 'batch_size': batch_size, 'lr': lr, 'epochs': 2} predictor = ImagePredictor() predictor.fit(train_data, time_limit=60*10, hyperparameters=hyperparameters, hyperparameter_tune_kwargs={'searcher': 'bayesopt', 'num_trials': 2}) print('Top-1 val acc: %.3f' % predictor.fit_summary()['valid_acc']) .. parsed-literal:: :class: output 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 HPO experiments .. parsed-literal:: :class: output 0%| | 0/2 [00:00 != ): { root.train.data_dir ~/.mxnet/datasets/imagenet != auto root.train.lr 0.1 != 0.01 root.train.rec_val ~/.mxnet/datasets/imagenet/rec/val.rec != auto root.train.early_stop_max_value 1.0 != inf root.train.batch_size 128 != 8 root.train.rec_val_idx ~/.mxnet/datasets/imagenet/rec/val.idx != auto root.train.rec_train ~/.mxnet/datasets/imagenet/rec/train.rec != auto root.train.early_stop_patience -1 != 10 root.train.num_training_samples 1281167 != -1 root.train.epochs 10 != 2 root.train.early_stop_baseline 0.0 != -inf root.train.num_workers 4 != 8 root.train.rec_train_idx ~/.mxnet/datasets/imagenet/rec/train.idx != auto root.img_cls.model resnet50_v1 != resnet18_v1b root.valid.num_workers 4 != 8 root.valid.batch_size 128 != 8 } Saved config to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/872f9a58/.trial_0/config.yaml Start training from [Epoch 0] Epoch[0] Batch [49] Speed: 232.671533 samples/sec accuracy=0.380000 lr=0.010000 [Epoch 0] training: accuracy=0.494444 [Epoch 0] speed: 246 samples/sec time cost: 2.893334 [Epoch 0] validation: top1=0.762500 top5=1.000000 [Epoch 0] Current best top-1: 0.762500 vs previous -inf, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/872f9a58/.trial_0/best_checkpoint.pkl Epoch[1] Batch [49] Speed: 255.750283 samples/sec accuracy=0.620000 lr=0.010000 [Epoch 1] training: accuracy=0.623611 [Epoch 1] speed: 259 samples/sec time cost: 2.747482 [Epoch 1] validation: top1=0.812500 top5=1.000000 [Epoch 1] Current best top-1: 0.812500 vs previous 0.762500, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/872f9a58/.trial_0/best_checkpoint.pkl Applying the state from the best checkpoint... modified configs( != ): { root.train.data_dir ~/.mxnet/datasets/imagenet != auto root.train.lr 0.1 != 0.001 root.train.rec_val ~/.mxnet/datasets/imagenet/rec/val.rec != auto root.train.early_stop_max_value 1.0 != inf root.train.batch_size 128 != 8 root.train.rec_val_idx ~/.mxnet/datasets/imagenet/rec/val.idx != auto root.train.rec_train ~/.mxnet/datasets/imagenet/rec/train.rec != auto root.train.early_stop_patience -1 != 10 root.train.num_training_samples 1281167 != -1 root.train.epochs 10 != 2 root.train.early_stop_baseline 0.0 != -inf root.train.num_workers 4 != 8 root.train.rec_train_idx ~/.mxnet/datasets/imagenet/rec/train.idx != auto root.img_cls.model resnet50_v1 != resnet18_v1b root.valid.num_workers 4 != 8 root.valid.batch_size 128 != 8 } Saved config to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/872f9a58/.trial_1/config.yaml Start training from [Epoch 0] Epoch[0] Batch [49] Speed: 227.835839 samples/sec accuracy=0.295000 lr=0.001000 [Epoch 0] training: accuracy=0.313889 [Epoch 0] speed: 241 samples/sec time cost: 2.947158 [Epoch 0] validation: top1=0.350000 top5=1.000000 [Epoch 0] Current best top-1: 0.350000 vs previous -inf, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/872f9a58/.trial_1/best_checkpoint.pkl Epoch[1] Batch [49] Speed: 250.488870 samples/sec accuracy=0.380000 lr=0.001000 [Epoch 1] training: accuracy=0.387500 [Epoch 1] speed: 255 samples/sec time cost: 2.784068 [Epoch 1] validation: top1=0.487500 top5=1.000000 [Epoch 1] Current best top-1: 0.487500 vs previous 0.350000, saved to /var/lib/jenkins/workspace/workspace/autogluon-tutorial-image-classification-v3/docs/_build/eval/tutorials/image_prediction/872f9a58/.trial_1/best_checkpoint.pkl Applying the state from the best checkpoint... Finished, total runtime is 21.77 s { 'best_config': { 'estimator': , 'gpus': [0], 'img_cls': { 'batch_norm': False, 'last_gamma': False, 'model': 'resnet18_v1b', 'use_gn': False, 'use_pretrained': True, 'use_se': False}, 'train': { 'batch_size': 8, 'crop_ratio': 0.875, 'data_dir': 'auto', 'dtype': 'float32', 'early_stop_baseline': -inf, 'early_stop_max_value': inf, 'early_stop_min_delta': 0.001, 'early_stop_patience': 10, 'epochs': 2, 'hard_weight': 0.5, 'input_size': 224, 'label_smoothing': False, 'log_interval': 50, 'lr': 0.01, 'lr_decay': 0.1, 'lr_decay_epoch': '40, 60', 'lr_decay_period': 0, 'lr_mode': 'step', 'mixup': False, 'mixup_alpha': 0.2, 'mixup_off_epoch': 0, 'mode': '', 'momentum': 0.9, 'no_wd': False, 'num_training_samples': -1, 'num_workers': 8, 'output_lr_mult': 0.1, 'pretrained_base': True, 'rec_train': 'auto', 'rec_train_idx': 'auto', 'rec_val': 'auto', 'rec_val_idx': 'auto', 'resume_epoch': 0, 'start_epoch': 0, 'teacher': None, 'temperature': 20, 'transfer_lr_mult': 0.01, 'use_rec': False, 'warmup_epochs': 0, 'warmup_lr': 0.0, 'wd': 0.0001}, 'valid': {'batch_size': 8, 'num_workers': 8}}, 'total_time': 21.772123098373413, 'train_acc': 0.3875, 'valid_acc': 0.4875} .. parsed-literal:: :class: output Top-1 val acc: 0.487 The BO searcher can be configured by ``search_options``, see :class:`autogluon.core.searcher.GPFIFOSearcher`. Load the test dataset and evaluate: .. code:: python results = predictor.evaluate(test_data) print('Test acc on hold-out data:', results) .. parsed-literal:: :class: output Test acc on hold-out data: {'top1': 0.7625, 'top5': 1.0} Note that ``num_trials=2`` above is only used to speed up the tutorial. In normal practice, it is common to only use ``time_limit`` and drop ``num_trials``.