Amazon SageMaker
Developer Guide

Image Classification Algorithm

The Amazon SageMaker image classification algorithm is a supervised learning algorithm that takes an image as input and classifies it into one of multiple output categories. It uses a convolutional neural network (ResNet) that can be trained from scratch, or trained using transfer learning when a large number of training images are not available.

The recommended input format for the Amazon SageMaker image classification algorithms is Apache MXNet RecordIO. However, you can also use raw images in .jpg or .png format.


To maintain better interoperability with existing deep learning frameworks, this differs from the protobuf data formats commonly used by other Amazon SageMaker algorithms.

For more information on convolutional networks, see:

Input/Output Interface

The Amazon SageMaker Image Classification algorithm supports both RecordIO (application/x-recordio) and image (application/x-image) content types for training. The algorithm supports only application/x-image for inference.

Training with RecordIO Format

If you use the RecordIO format for training, specify both train and validation channels as values for the InputDataConfig parameter of the CreateTrainingJob request. Specify one RecordIO (.rec) file in the train channel and one RecordIO file in the validation channel. Set the content type for both channels to application/x-recordio.

Training with Image Format

If you use the Image format for training, specify train, validation, train_lst, and validation_lst channels as values for the InputDataConfig parameter of the CreateTrainingJob request. Specify the individual image data (.jpg or .png files) for the train and validation channels. Specify one .lst file in each of the train_lst and validation_lst channels. Set the content type for all four channels to application/x-image.

A .lst file is a tab-separated file with three columns that contains a list of image files. The first column specifies the image index, the second column specifies the class label index for the image, and the third column specifies the relative path of the image file. The image index in the first column must be unique across all of the images. The set of class label indices are numbered successively and the numbering should start with 0. For example, 0 for the cat class, 1 for the dog class, and so on for additional classes.

The following is an example of a .lst file:

5 1 your_image_directory/train_img_dog1.jpg 1000 0 your_image_directory/train_img_cat1.jpg 22 1 your_image_directory/train_img_dog2.jpg

For example, if your training images are stored in s3://<your_bucket>/train/class_dog, s3://<your_bucket>/train/class_cat, and so on, specify the path for your train channel as s3://<your_bucket>/train, which is the top-level directory for your data. In the .lst file, specify the relative path for an individual file named train_image_dog1.jpg in the class_dog class directory as class_dog/train_image_dog1.jpg. You can also store all your image files under one subdirectory inside the train directory. In that case, use that subdirectory for the relative path. For example, s3://<your_bucket>/train/your_image_directory.

Incremental Training

You can also seed the training of a new model with the artifacts from a model that you trained previously with Amazon SageMaker. Incremental training saves training time when you want to train a new model with the same or similar data. Amazon SageMaker image classification models can be seeded only with another build-in image classification model trained in Amazon SageMaker.

To use a pretrained model, in the CreateTrainingJob request, specify the ChannelName as "model" in the InputDataConfig parameter. Set the ContentType for the model channel to application/x-sagemaker-model. The input hyperparameters of both the new model and the pretrained model that you upload to the model channel must have the same settings for the num_layers, image_shape and num_classes input parameters. These parameters define the network architecture. For the pretrained model file, use the compressed model artifacts (in .tar.gz format) output by Amazon SageMaker. You can use either RecordIO or image formats for input data.

For a sample notebook that shows how to use incremental training with the Amazon SageMaker image classification algorithm, see the End-to-End Incremental Training Image Classification Example. For more information on incremental training and for instructions on how to use it, see Incremental Training in Amazon SageMaker.

Inference with Image Format

The generated models can be hosted for inference and support encoded .jpg and .png image formats as application/x-image content-type. The output is the probability values for all classes encoded in JSON format, or in JSON Lines text format for batch transform. The image classification model processes a single image per request and so outputs only one line in the JSON or JSON Lines format. The following is an example of a response in JSON Lines format:

accept: application/jsonlines {"prediction": [prob_0, prob_1, prob_2, prob_3, ...]}

For more details on training and inference, see the image classification sample notebook instances referenced in the introduction.

EC2 Instance Recommendation

For image classification, we support the following GPU instances for training: ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.p3.2xlarge, ml.p3.8xlargeand ml.p3.16xlarge. We recommend using GPU instances with more memory for training with large batch sizes. However, both CPU (such as C4) and GPU (such as P2 and P3) instances can be used for the inference. You can also run the algorithm on multi-GPU and multi-machine settings for distributed training.

Both P2 and P3 instances are supported in the image classification algorithm.

Image Classification Sample Notebooks

For a sample notebook that uses the Amazon SageMaker image classification algorithm to train a model on the caltech-256 dataset and then to deploy it to perform inferences, see the End-to-End Multiclass Image Classification Example. For instructions how to create and access Jupyter notebook instances that you can use to run the example in Amazon SageMaker, see Using Notebook Instances. Once you have created a notebook instance and opened it, select the SageMaker Examples tab to see a list of all the Amazon SageMaker samples. The example image classification notebooks are located in the Introduction to Amazon algorithms section. To open a notebook, click on its Use tab and select Create copy.