Object Detection Hyperparameters

In the CreateTrainingJob request, you specify the training algorithm that you want to use. You can also specify algorithm-specific hyperparameters that are used to help estimate the parameters of the model from a training dataset. The following table lists the hyperparameters provided by Amazon SageMaker for training the object detection algorithm. For more information about how object training works, see How Object Detection Works.

Parameter Name	Description
num_classes	The number of output classes. This parameter defines the dimensions of the network output and is typically set to the number of classes in the dataset. Required Valid values: positive integer
num_training_samples	The number of training examples in the input dataset. Note If there is a mismatch between this value and the number of samples in the training set, then the behavior of the lr_scheduler_step parameter will be undefined and distributed training accuracy may be affected. Required Valid values: positive integer
base_network	The base network architecture to use. Optional Valid values: 'vgg-16' or 'resnet-50' Default value: 'vgg-16'
early_stopping	True to use early stopping logic during training. False not to use it. Optional Valid values: True or False Default value: False
early_stopping_min_epochs	The minimum number of epochs that must be run before the early stopping logic can be invoked. It is used only when early_stopping = True. Optional Valid values: positive integer Default value: 10
early_stopping_patience	The number of epochs to wait before ending training if no improvement, as defined by the early_stopping_tolerance hyperparameter, is made in the relevant metric. It is used only when early_stopping = True. Optional Valid values: positive integer Default value: 5
early_stopping_tolerance	The tolerance value that the relative improvement in validation:mAP, the mean average precision (mAP), is required to exceed to avoid early stopping. If the ratio of the change in the mAP divided by the previous best mAP is smaller than the early_stopping_tolerance value set, early stopping considers that there is no improvement. It is used only when early_stopping = True. Optional Valid values: 0 ≤ float ≤ 1 Default value: 0.0
image_shape	The image size for input images. We rescale the input image to a square image with this size. We recommend using 300 and 512 for better performance. Optional Valid values: positive integer ≥300 Default: 300
epochs	The number of training epochs. Optional Valid values: positive integer Default: 30
freeze_layer_pattern	The regular expression (regex) for freezing layers in the base network. For example, if we set freeze_layer_pattern = "^(conv1_|conv2_).*", then any layers with a name that contains "conv1_" or "conv2_" are frozen, which means that the weights for these layers are not updated during training. The layer names can be found in the network symbol files vgg16-symbol.json and resnet-50-symbol.json. Freezing a layer means that its weights can not be modified further. This can reduce training time significantly in exchange for modest losses in accuracy. This technique is commonly used in transfer learning where the lower layers in the base network do not need to be retrained. Optional Valid values: string Default: No layers frozen.
kv_store	The weight update synchronization mode used for distributed training. The weights can be updated either synchronously or asynchronously across machines. Synchronous updates typically provide better accuracy than asynchronous updates but can be slower. See the Distributed Training MXNet tutorial for details. Note This parameter is not applicable to single machine training. Optional Valid values: 'dist_sync' or 'dist_async' 'dist_sync': The gradients are synchronized after every batch with all the workers. With 'dist_sync', batch-size now means the batch size used on each machine. So if there are n machines and we use batch size b, then dist_sync behaves like a single machine with batch size n*b. 'dist_async': Performs asynchronous updates. The weights are updated whenever gradients are received from any machine and the weight updates are atomic. However, the order is not guaranteed. Default: -
label_width	The force padding label width used to sync across training and validation data. For example, if one image in the data contains at most 10 objects, and each object's annotation is specified with 5 numbers, [class_id, left, top, width, height], then the label_width should be no smaller than (10*5 + header information length). The header information length is usually 2. We recommend using a slightly larger label_width for the training, such as 60 for this example. Optional Valid values: Positive integer large enough to accommodate the largest annotation information length in the data. Default: 350
learning_rate	The initial learning rate. Optional Valid values: float in (0, 1] Default: 0.001
lr_scheduler_factor	The ratio to reduce learning rate. Used in conjunction with the lr_scheduler_step parameter defined as lr_new = lr_old * lr_scheduler_factor. Optional Valid values: float in (0, 1) Default: 0.1
lr_scheduler_step	The epochs at which to reduce the learning rate. The learning rate is reduced by lr_scheduler_factor at epochs listed in a comma-delimited string: "epoch1, epoch2, ...". For example, if the value is set to "10, 20" and the lr_scheduler_factor is set to 1/2, then the learning rate is halved after 10th epoch and then halved again after 20th epoch. Optional Valid values: string Default: empty string
mini_batch_size	The batch size for training. In a single-machine multi-gpu setting, each GPU handles mini_batch_size/num_gpu training samples. For the multi-machine training in dist_sync mode, the actual batch size is mini_batch_size*number of machines. A large mini_batch_size usually leads to faster training, but it may cause out of memory problem. The memory usage is related to mini_batch_size, image_shape, and base_network architecture. For example, on a single p3.2xlarge instance, the largest mini_batch_size without an out of memory error is 32 with the base_network set to "resnet-50" and an image_shape of 300. With the same instance, you can use 64 as the mini_batch_size with the base network vgg-16 and an image_shape of 300. Optional Valid values: positive integer Default: 32
momentum	The momentum for sgd. Ignored for other optimizers. Optional Valid values: float in (0, 1] Default: 0.9
nms_threshold	The non-maximum suppression threshold. Optional Valid values: float in (0, 1] Default: 0.45
optimizer	The optimizer types. For details on optimizer values, see MXNet's API. Optional Valid values: ['sgd', 'adam', 'rmsprop', 'adadelta'] Default: 'sgd'
overlap_threshold	The evaluation overlap threshold. Optional Valid values: float in (0, 1] Default: 0.5
use_pretrained_model	Indicates whether to use a pre-trained model for training. If set to 1, then the pre-trained model with corresponding architecture is loaded and used for training. Otherwise, the network is trained from scratch. Optional Valid values: 0 or 1 Default: 1
weight_decay	The weight decay coefficient for sgd and rmsprop. Ignored for other optimizers. Optional Valid values: float in (0, 1) Default: 0.0005