Skip to main content
Version: v1.4.0

Experiment settings: Image semantic segmentation

The settings for an image semantic segmentation experiment are listed and described below.

General settings​

Dataset​

This setting defines the dataset for the experiment.

Problem category​

This setting defines a particular general problem type category, for example, image.

note
  • The selected problem category (for example, image) determines the options in the Problem type setting.
  • The From experiment option enables you to utilize the settings of an experiment (another experiment).

Experiment​

This setting defines the experiment H2O Hydrogen Torch references to initialize the experiment settings. H2O Hydrogen Torch initializes the experiment settings with the values from the selected (built) experiment.

Setting dependency

This setting is available only if From experiment is selected in the Problem category setting.

Problem type​

This setting defines the problem type of the experiment, which also defines the settings H2O Hydrogen Torch displays for the experiment.

Note
  • The selected problem category (in the Problem category setting) determines the available problem types.
  • The selected problem type and experience level determine the settings H2O Hydrogen Torch displays for the experiment.

Import config from YAML​

This setting defines the YML file that defines the experiment settings.

Note
  • H2O Hydrogen Torch supports a YML file import and export functionality. You can download the config settings of finished experiments, make changes, and re-upload them when starting a new experiment in any instance of H2O Hydrogen Torch.

Use previous experiment weights​

This setting determines whether to initialize the model weights with the weights from the experiment specified in the Experiment setting.

note

A model's weights are available for an experiment (model) of the same problem type and backbone.

tip

This setting might be useful in case you want to continue training from a built experiment.

Setting dependency

The Use previous experiment weights setting is available only if From experiment is selected in the Problem category setting.

Experiment name​

This setting defines the name of the experiment.

Dataset settings​

Train dataframe​

This setting specifies the path to a file that contains a dataframe comprising training records utilized by H2O Hydrogen Torch for model training within the experiment. Here, the term 'file' denotes a specific file adhering to a dataset format tailored for the problem type addressed in the experiment. To learn more, see Dataset formats.

note
  • The records are combined into mini-batches when training the model.
  • If a validation dataframe is provided, a fold column is not needed in the train dataframe.
  • To import datasets for inference only, when defining the settings for an experiment, set the Train dataframe setting to None while setting the Test dataframe setting to the relevant dataframe (as a result, H2O Hydrogen Torch utilizes the relevant dataset for predictions and not for training).

Data folder​

Defines the location of the folder containing assets (for example, images or audio clips) the model utilizes for training. H2O Hydrogen Torch loads assets from this folder during training.

Validation strategy​

This setting specifies the validation strategy H2O Hydrogen Torch uses for the experiment.

tip

To properly assess the performance of your trained models, it is common practice to evaluate it on separate holdout data that the model has not seen during training.

Options

  • K-fold cross validation
    • This option splits the data using the provided optional fold column in the train data or performs an automatic 5-fold cross-validation in the absence of a fold column.
  • Grouped k-fold cross-validation
    • This option allows you to specify a group column based on which the data is split into folds.
  • Custom holdout validation
    • This option specifies a separate holdout dataframe.
  • Automatic holdout validation
    • This option allows you to specify a holdout validation sample size that is automatically generated.

Validation dataframe​

This setting defines a file containing a dataframe with validation records that H2O Hydrogen Torch uses to evaluate the model during training.

Note
  • To set a Validation dataframe requires the Validation strategy to be set to Custom holdout validation. In the case of providing a validation dataframe, H2O Hydrogen Torch fully respects the choice of a separate validation dataframe and does not perform any internal cross-validation. In other words, the model is trained on the full provided train dataframe, and model performance is evaluated on the provided validation dataframe.
  • The validation dataframe should have the same format as the train dataframe but does not require a fold column.
Setting dependency

The Validation dataframe settings is only available when you select Validation strategy in the Custom holdout validation setting.

Selected folds​

This setting defines the selected validation fold(s) in case of cross-validation; a separate model is trained for each value selected. Each model utilizes the corresponding part of the data as a holdout sample to assess performance while the model is fitted to the rest of the records from the training dataframe. As a result, folds estimate how the model performs in general when used to make predictions on data not used during model training.

Note

H2O Hydrogen Torch allows running experiments on a single selected fold for faster experimenting and multiple selected folds to gain more trust in the model's generalization and performance capabilities.

Setting dependency

This setting is available only when the Validation strategy setting is not set to Custom holdout validation or Automatic holdout validation.

Test dataframe​

This setting defines a file containing a dataframe with test records that H2O Hydrogen Torch uses to test the model.

note
  • The test dataframe should have the same format as the train dataframe but does not require a label column.
  • To import datasets for inference only, when defining the setting for an experiment, set the Train dataframe setting to None while setting the Test dataframe setting to the relevant dataframe (as a result, H2O Hydrogen Torch utilizes the relevant dataset for predictions and not for training).

Data folder test​

Defines the location of the folder containing assets (for example, images, texts, or audio clips) H2O Hydrogen Torch utilizes to test the model. H2O Hydrogen Torch loads the assets from this folder when testing the model. This setting is only available if a test dataframe is selected.

Setting dependency
  • This setting is only available if a test dataframe is selected.
  • The Data folder test setting appears when you specify a test dataframe in the Test dataframe setting.

Class name column​

Defines the dataset column containing a list of class names that H2O Hydrogen Torch uses for each instance mask.

Rle mask column​

Defines the dataset column containing a list of run-length encoded (RLE) masks that H2O Hydrogen Torch uses for instance class.

Image column​

Defines the dataframe column storing the names of images that H2O Hydrogen Torch loads from the Data folder and Data folder test when training and testing the model.

Data sample​

This setting defines the percentage of the data to use for the experiment. The default percentage is 100%.

tip

Changing the default value can significantly increase the training speed. Still, it might lead to a substantially poor accuracy value. Using 100% of the data for final models is highly recommended.

Data sample choice​

This setting specifies the data H2O Hydrogen Torch samples according to the percentage set in the Data sample setting. H2O Hydrogen Torch does not sample the unselected data.

Setting dependency

The Data sample choice setting is only available if the value in the Data sample setting is less than 1.0.

Image settings​

Image width​

Defines the width H2O Hydrogen Torch uses to rescale the images for training and predictions.

note

Depending on the original image size, a bigger width can generate a higher accuracy value.

Image height​

Defines the width H2O Hydrogen Torch uses to rescale the images for training and predictions.

note

Depending on the original image size, a bigger width can generate a higher accuracy value.

Image channels​

Defines the number of channels the train images contain.

note
  • Typically images have three input channels (red, green, and blue (RGB)), but grayscale images have only 1. When you provide image data in a NumPy data format, any number of channels is allowed. For this reason, data scientists can specify the number of channels
  • The defined number of channels also refers to the provided validation and test datasets

Image normalization​

Grid search hyperparameter

Defines the transformer to normalize the image data before training the model.

note

Usually, state-of-the-art image models normalize the training images by scaling values of each of the input channels to predefined means and standard deviations.

Options

Image regression | Image classification | Image object detection | Image semantic segmentation | Image instance segmentation | Image metric learning

  • Channel
    • Calculates mean and standard deviation per channel in all the images in the batch and then applies per channel normalization: subtracts mean and divides by standard deviation.
  • Image
    • Calculates mean and standard deviation per image and then applies normalization.
  • ImageNet
    • Divides input images by 255 and normalizes with mean and standard deviation equal to (0.485, 0.456, 0.406) and (0.229, 0.224, 0.225) per channel, respectively.
  • Inception
    • Divides input images by 255 and normalizes with mean and standard deviation equal to 0.5.
  • Min_Max
    • Calculates minimum and maximum values in all the images in the batch and then applies min-max normalization: subtracts min and divides by the max and min difference.
  • No
    • No normalization is applied to the input images.
  • Simple
    • Divides input images by 255.

3D image classification | 3D image regression | 3D image semantic segmentation

  • No
    • No normalization is applied to the input images.
  • Simple
    • Divides input images by 255.
  • Min_Max
    • Calculates minimum and maximum values in all the images in the batch and then applies min-max normalization: subtracts min and divides by the max and min difference.

note

Usually, state-of-the-art image models normalize the training images by scaling values of each of the input channels to predefined means and standard deviations.

Augmentation settings​

Augmentations strategy​

Grid search hyperparameter

Defines the augmentation strategy to apply to the input images. Soft, Medium, and Hard values correspond to the strength of the augmentations to apply.

Options

Image regression | Image classification | Image object detection | Image semantic segmentation | Image instance segmentation | Image metric learning | Image and text classification

  • Soft
    • The Soft strategy applies image Resize and random HorizontalFlip during model training while applying image Resize during model inference.
  • Medium
    • The Medium strategy adds ShiftScaleRotate and CoarseDropout to the list of the train augmentations.
  • Hard
    • The Hard strategy applies RandomResizedCrop (instead of Resize) during model training while adding RandomBrightnessContrast to the list of train augmentations.
  • Custom
    • The Custom strategy allows users to use their own augmentations that can be defined in the following two settings:
      • Custom train augmentations
      • Custom inference augmentations

3D image classification | 3D image regression | 3D image semantic segmentation

  • Soft
    • The Soft strategy applies image Resize and random HorizontalFlip during model training while applying image Resize during model inference.
  • Medium
    • The Medium strategy adds ShiftScaleRotate and CoarseDropout to the list of the train augmentations.
  • Hard
    • The Hard strategy applies RandomResizedCrop (instead of Resize) during model training while adding RandomBrightnessContrast to the list of train augmentations.

note

Augmentations are ways to modify train images while keeping the target values valid, such as flipping the image or adding noise. Distorting training images do not influence the expected prediction of the model but enrich the training data. Augmentations help generalize the model better and improve its accuracy.

Custom train augmentations​

This setting specifies a list of custom augmentations to be applied to the training data. The augmentations are defined in a JSON file generated by calling the albumentations.save() function from the Albumentations library. You can use the placeholders IMAGE_HEIGHT and IMAGE_WIDTH to dynamically incorporate the image dimensions from the experiment configuration.

note

Augmentations are ways to modify train images while keeping the target values valid, such as flipping the image or adding noise. Distorting training images do not influence the expected prediction of the model but enrich the training data. Augmentations help generalize the model better and improve its accuracy. Augmentations are applied to every image at each epoch with the provided probability.

Setting dependency

The Custom train augmentations setting is only available when you select Custom in the Augmentations strategy setting.

Custom inference augmentations​

This setting allows you to define a list of custom inference augmentations that are applied to the test and validation data. The augmentations are specified in a JSON format, which is generated by calling the albumentations.save() function from the Albumentations library. To make it easier to adapt the augmentations to different image dimensions, you can use the IMAGE_HEIGHT and IMAGE_WIDTH placeholders, which are replaced with the actual image dimensions from the experiment configuration.

note

Inference augmentations serve the same purpose as training augmentations, but the difference is that inference augmentations are applied to validation and test data. Typically, inference augmentations only contain resizing or very simple augmentations.

Setting dependency

The Custom inference augmentations setting is only available when you select Custom in the Augmentations strategy setting.

Mix image​

Grid search hyperparameter

Defines the image mix augmentation to use during model training.

Options

Image regression | Image classification | Image object detection | Image semantic segmentation | Image instance segmentation

  • Mixup
    • Mixup overlays (mixes) two images one on another based on a random ratio. To learn more about this mix augmentation approach, refer to the following article: mixup: BEYOND EMPIRICAL RISK MINIMIZATION.
      note

      For an image object detection experiment using Mixup, H2O Hydrogen Torch uses the union of all the target boxes in mixed images.

  • Cutmix
    • Cutmix replaces an image region with a patch from another image; the region size is based on a random ratio. To learn more about this mix augmentation approach, refer to the following article: SOLVING LINEAR SYSTEMS OVER TROPICAL SEMIRINGS THROUGH NORMALIZATION METHOD AND ITS APPLICATIONS.
      note

      For an image object detection experiment using Cutmix, H2O Hydrogen Torch uses the target boxes from the corresponding region from each image. Also, with Cutmix selected, H2O Hydrogen Torch cuts out and replaces only the corners of the images with a patch from another image.

  • Disabled
    • No augmentation is applied.

3D image classification | 3D image regression | 3D image semantic segmentation

  • Mixup
    • Mixup overlays (mixes) two images one on another based on a random ratio. To learn more about this mix augmentation approach, refer to the following article: mixup: BEYOND EMPIRICAL RISK MINIMIZATION.
      note

      For an image object detection experiment using Mixup, H2O Hydrogen Torch uses the union of all the target boxes in mixed images.

  • Disabled
    • No augmentation is applied.

Mix target​

Grid search hyperparameter

This setting defines the target (label) mix augmentation to apply during model training.

Options

Image regression | 3D image regression | Image classification | 3D image classification | Image object detection | Image semantic segmentation | 3D image semantic segmentation | Image instance segmentation | Audio regression | Audio classification

  • Ratio: Two classification targets are averaged based on the sample ratio during model training.
  • Min: The minimum of both targets is taken while ignoring the ratio during model training.
  • Max: The maximum of both targets is taken while ignoring the ratio during model training.

Cutmix corner​

Grid search hyperparameter

When turned On, cutmix augmentation is applied where only the corners of an image are replaced with a patch from another image.

setting dependency

The Cutmix corner setting is only available when the Cutmix option is selected in the Mix image setting.

Mix concentration​

Grid search hyperparameter

This setting defines the concentration parameter value of the Beta probability distribution to generate mix ratios. A larger value leads to more equal ratios (50% - 50%) for mixing.

setting dependency
  • Image problem types: The Mix concentration setting is only available when the Mixup option is selected in the Mix image setting.
  • Audio problem types: The Mix concentration setting is only available when the Mixup option is selected in the Mix audio setting.

Mix probability​

Grid search hyperparameter

This setting defines the probability value to apply mix augmentation. The mix probability value is used for each batch or mix iteration.

example

If the mixing probability is specified as 0.3, mix augmentation is applied to each batch (or mix iteration) with a probability of 0.3.

setting dependency
  • Image problem types: The Mix probability setting is only available when the Mixup option is selected in the Mix image setting.
  • Audio problem types: The Mix probability setting is only available when the Mixup option is selected in the Mix audio setting.

Mix iterations​

Grid search hyperparameter

  • Image problem types: This setting defines the number of times to apply mix augmentation on each batch. The larger the value, the more images are mixed into a single train sample.
  • Audio problem types: This setting defines the number of times to apply mix augmentation on each batch. The larger the value, the more audios are mixed into a single train sample.
setting dependency
  • Image problem types: The Mix iterations setting is only available when the Mixup option is selected in the Mix image setting.
  • Audio problem types: The Mix iterations setting is only available when the Mixup option is selected in the Mix audio setting.

Architecture settings​

Pretrained​

Grid search hyperparameter

Defines whether the neural network should start with pre-trained weights. When this setting is On, the training of the neural network starts with a pre-trained model on a generic task. When turned Off, the initial weights of the neural network to train become random.

Backbone​

Grid search hyperparameter

Defines the backbone neural network architecture to train the model.

Note
  • Image regression | Image classification | Image metric learning | Audio regression | Audio classification
    • H2O Hydrogen Torch accepts backbone neural network architectures from the timm library (select or enter the architecture name)
  • Image object detection
    • H2O Hydrogen Torch provides several backbone state-of-the-art neural network architectures for model training. When you select Faster RCnn or Fcos as the model type for the experiment, you can input any architecture name from the timm library. When you select Efficientdet as the model type for the experiment, you can input any architecture name from the efficientdet-pytorch library
  • Image semantic segmentation | Image instance segmentation
    • H2O Hydrogen Torch accepts backbone neural network architectures from the segmentation-models-pytorch library (select or enter the architecture name).
  • 3D image regression | 3D image classification
    • H2O Hydrogen Torch accepts backbone (encoder) neural network architectures from a subset (resnet and efficientnet) of the timm library (select or enter the architecture name).
  • Text regression | Text classification | Text token classification | Text span prediction | Text sequence to sequence | Text metric learning
    • H2O Hydrogen Torch accepts backbone neural network architectures from the Hugging Face library (select or enter the architecture name)
  • Speech recognition
    • HuggingFace Wav2Vec2 CTC models are supported
tip
  • All problem types
    • Usually, it is good to use simpler architectures for quicker experiments and larger models when aiming for the highest accuracy
  • Speech recognition
    • If possible, leverage backbones pre-trained closely to your use case (for example, noisy audio, casual speech, etc.)

Architecture​

Grid search hyperparameter

Defines the architecture (decoder) to use for the experiment. H2O Hydrogen Torch uses semantic segmentation architectures with additional postprocessing to separate masks into individual instances.

Options

Image semantic segmentation | Image instance segmentation

Training settings​

Loss function​

Grid search hyperparameter

This setting defines the loss function H2O Hydrogen Torch utilizes during model training. The loss function is a differentiable function measuring the prediction error. The model utilizes gradients of the loss function to update the model weights during training.

Options

Image regression | 3D image regression | Text regression | Audio regression

  • MAE
    • H2O Hydrogen Torch utilizes the mean absolute error (L1 norm) as the loss function.
  • MSE
    • H2O Hydrogen Torch utilizes the mean squared error (squared L2 norm) as the loss function.
  • RMSE
    • H2O Hydrogen Torch utilizes the mean squared error (L2 norm) as a loss function.

Image classification | 3D image classification | Text classification | Audio classification

  • BCE
    • H2O Hydrogen Torch uses binary cross entropy loss.
  • Classification
    • This default classification loss automatically chooses between BCE (multi-label) and CrossEntropy (multi-class) for classification.
  • CrossEntropy
    • H2O Hydrogen Torch utilizes multi-class cross entropy loss as a loss function.
  • SigmoidFocal
  • SoftmaxFocal

Image semantic segmentation | 3D image semantic segmentation | Image instance segmentation

  • BCE
    • H2O Hydrogen Torch uses binary cross entropy loss.
  • BCEDice
    • H2O Hydrogen Torch uses binary cross entropy loss and Dice loss weights 2 and 1, respectively.
  • BCELovasz
    • H2O Hydrogen Torch uses binary cross entropy loss and Lovasz loss with equal weights.
  • Dice
    • H2O Hydrogen Torch uses Dice loss.
  • Focal
  • FocalDice
    • H2O Hydrogen Torch uses Focal loss and Dice loss with weights 2 and 1, respectively.
  • Jaccard
    • H2O Hydrogen Torch uses Jaccard loss.

Image metric learning | Text metric learning

Text token classification | Text span prediction | Text sequence to sequence

  • CrossEntropy
    • H2O Hydrogen Torch utilizes multi-class cross entropy loss as a loss function.

Speech recognition

  • CTC Loss
    • H2O Hydrogen Torch utilizes Conectionist Temporal Classification loss as a loss function.

BCE weight​

Grid search hyperparameter

note

The BCE weight is available for certain Loss functions. Accordingly, its definition is determined by the selected Loss function.

  • BCEDice
    • If the selected Loss function is BCEDice, the BCE weight takes the following defitniton: BCEDice loss = BCE loss * BCE weight + Dice loss * Dice weight
  • BCELovasz
    • If the selected Loss function is BCELovasz, the BCE weight takes the following defitniton: BCELovasz loss = BCE loss * BCE weight + Lovasz loss * Lovasz weight

Dice weight​

Grid search hyperparameter

note

The Dice weight is available for certain Loss functions. Accordingly, its definition is determined by the selected Loss function.

  • BCEDice
    • If the selected Loss function is BCEDice, the Dice weight takes the following defitniton: BCEDice loss = BCE loss * BCE weight + Dice loss * Dice weight
  • FocalDice
    • If the selected Loss function is FocalDice, the Dice weight take the following definition: FocalDice loss = Focal loss * Focal weight + Dice loss * Dice weight

Lovasz weight​

Grid search hyperparameter

note

The Lovasz weight is available for certain Loss functions. Accordingly, its definition is determined by the selected Loss function.

  • BCELovasz
    • If the selected Loss function is BCELovasz, the Lovasz weight takes the following defitniton: BCELovasz loss = BCE loss * BCE weight + Lovasz loss * Lovasz weight

Focal weight​

Grid search hyperparameter

note

The Focal weight is available for certain Loss functions. Accordingly, its definition is determined by the selected Loss function.

  • FocalDice
    • If the selected Loss function is FocalDice, the Focal weight takes the following defitniton: FocalDice loss = Focal loss * Focal weight + Dice loss * Dice weight

Optimizer​

Grid search hyperparameter

This setting defines the algorithm or method (optimizer) to use for model training. The selected algorithm or method defines how the model should change the attributes of the neural network, such as weights and learning rate. Optimizers solve optimization problems and make more accurate updates to attributes to reduce learning losses.

Options

Learning rate​

Grid search hyperparameter

This setting defines the learning rate H2O Hydrogen Torch uses when training the model, specifically when updating the neural network's weights. The learning rate is the speed at which the model updates its weights after processing each mini-batch of data.

note
  • The learning rate is an important setting to tune as it balances under and overfitting.
  • The number of epochs highly impacts the optimal value of the learning rate.

Differential learning rate layers​

Defines the learning rate to apply to certain layers of a model. H2O Hydrogen Torch applies the regular learning rate to layers without a specified learning rate.

Options

Image regression | Image classification | Text regression | Text classification | Text token classification | Audio regression | Audio classification

  • Backbone
    • H2O Hydrogen Torch applies a different learning rate to a body of the neural network architecture.
  • Head
    • H2O Hydrogen Torch applies a different learning rate to a head of the neural network architecture.

Image object detection

The options for an image object detection experiment are different based on the selected Model type (setting). Options:

  • If you select EfficientDet as the experiment's Model type (setting), the following options are available:

    Options

    • Backbone
      • H2O Hydrogen Torch applies a different learning rate to a body of the EfficientDet architecture.
    • FPN
      • H2O Hydrogen Torch applies a different learning rate to a Feature Pyramid Network (FPN) block of the EfficientDet architecture.
    • class_net
      • H2O Hydrogen Torch applies a different learning rate to a classification head of the EfficientDet architecture.
    • box_net
      • H2O Hydrogen Torch applies a different learning rate to a box regression head of the EfficientDet architecture.

  • If you select Faster R-CNN as the experiment's Model type (setting), the following options are available:

    Options

    • Body
      • H2O Hydrogen Torch applies a different learning rate to a body of the Faster R-CNN architecture.
    • FPN
      • H2O Hydrogen Torch applies a different learning rate to a Feature Pyramid Network (FPN) block in the Faster R-CNN architecture.
    • RPN
      • H2O Hydrogen Torch applies a different learning rate to a Region Proposal block of the Faster R-CNN architecture.
    • ROI heads
      • H2O Hydrogen Torch applies a different learning rate to the Faster R-CNN architecture proposal heads.

  • If you select FCOS as the experiment's Model type (setting), the following options are available:

    Options

    • Body
      • H2O Hydrogen Torch applies a different learning rate to a body of the FCOS architecture.
    • FPN
      • H2O Hydrogen Torch applies a different learning rate to a Feature Pyramid Network (FPN) block of the FCOS architecture.
    • classification_head
      • H2O Hydrogen Torch applies a different learning rate to the classification head of the FCOS architecture.
    • regression_head
      • H2O Hydrogen Torch applies a different learning rate to a box regression head of the FCOS architecture.

Image semantic segmentation

  • Encoder
    • H2O Hydrogen Torch applies a different learning rate to the encoder of the neural network architecture.
  • Decoder
    • H2O Hydrogen Torch applies a different learning rate to the decoder of the neural network architecture.
  • Segmentation head
    • H2O Hydrogen Torch applies a different learning rate to the head of the neural network architecture.

3D image semantic segmentation | Text sequence to sequence

  • Encoder
    • H2O Hydrogen Torch applies a different learning rate to the encoder of the neural network architecture.
  • Decoder
    • H2O Hydrogen Torch applies a different learning rate to the decoder of the neural network architecture.

Image instance segmentation

  • Encoder
    • H2O Hydrogen Torch applies a different learning rate to the encoder of the neural network architecture.
  • Decoder
    • H2O Hydrogen Torch applies a different learning rate to the decoder of the neural network architecture.
  • Segmentation head
    • H2O Hydrogen Torch applies a different learning rate to the head of the neural network architecture.

Image metric learning | Text metric learning

  • Backbone
    • H2O Hydrogen Torch applies a different learning rate to a body of the neural network architecture.
  • Neck
    • H2O Hydrogen Torch applies a different learning rate to a neck of the neural network architecture.
  • Loss
    • H2O Hydrogen Torch applies a different learning rate to an ArcFace block of the neural network architecture.

Text regression

  • Backbone
    • H2O Hydrogen Torch applies a different learning rate to a body of the neural network architecture.

Text span prediction

  • qa_outputs

tip

A common strategy is to apply a lower learning rate to the backbone of a model for better convergence and training stability.

note

Different layers are available for different problem types.

Batch size​

Grid search hyperparameter

This setting defines the number of training examples a mini-batch uses during an iteration of the training model to estimate the error gradient before updating the model weights. In other words, this setting defines the batch size used per GPU.

note

During model training, the training data is packed into mini-batches of a fixed size.

Automatically adjust batch size​

If this setting is turned On, H2O Hydrogen Torch checks whether the Batch size specified fits into the GPU memory. If a GPU out-of-memory (OOM) error occurs, H2O Hydrogen Torch automatically decreases the Batch size by a factor of 2 units until it fits into the GPU memory or Batch size equals 1.

Drop last batch​

This setting drops the last incomplete batch during model training when turned On.

note

H2O Hydrogen Torch groups the train data into mini-batches of equal size during the training process, but the last batch can have fewer records than the others. Not dropping the last batch can lead to a less robust gradient estimation while causing a more volatile training step.

Epochs​

Grid search hyperparameter

This setting defines the number of epochs to train the model. In other words, it specifies the number of times the learning algorithm goes through the entire training dataset.

note
  • The Epochs setting is an important setting to tune because it balances under- and overfitting.
  • The learning rate highly impacts the optimal value of the epochs.
  • For the following supported problem types, H2O Hydrogen Torch now enables you to utilize/deploy a pre-trained model trained on zero epochs (where H2O Hydrogen Torch does not train the model and the pretrained model (experiment) can be deployed as-is):
    • Speech recognition
    • Text sequence to sequence
    • text span prediction

Schedule​

Grid search hyperparameter

This setting defines the learning rate schedule H2O Hydrogen Torch utilizes during model training. Specifying a learning rate schedule prevents the learning rate from staying the same. Instead, a learning rate schedule causes the learning rate to change over iterations, typically decreasing the learning rate to achieve a better model performance and training convergence.

Options

  • Constant
    • H2O Hydrogen Torch applies a constant learning rate during the training process.
  • Cosine
    • H2O Hydrogen Torch applies a cosine learning rate that follows the values of the cosine function.
  • Linear
    • H2O Hydrogen Torch applies a linear learning rate that decreases the learning rate linearly.

Warmup epochs​

Grid search hyperparameter

This setting determines the number of epochs to warmup for gradually increasing the learning rate from 0 to the specified value. The learning rate increases linearly during the warmup period, allowing the model to adapt to the learning process gradually.

Note

You can set the value of this setting as a ratio of an epoch. For instance, setting it to 0.1 means warmup is performed for only 10% of the first full epoch.

Weight decay​

Grid search hyperparameter

This setting defines the weight decay that H2O Hydrogen Torch uses for the optimizer during model training.

note

Weight decay is a regularization technique that adds an L2 norm of all model weights to the loss function while increasing the probability of improving the model generalization.

Gradient clip​

Grid search hyperparameter

This setting defines the maximum norm of the gradients H2O Hydrogen Torch specifies during model training. Defaults to 0, no clipping. When a value greater than 0 is specified, H2O Hydrogen Torch modifies the gradients during model training. H2O Hydrogen Torch uses the specified value as an upper limit for the norm of the gradients, calculated using the Euclidean norm over all gradients per batch.

note

This setting can help model convergence when extreme gradient values cause high volatility of weight updates.

Grad accumulation​

Grid search hyperparameter

This setting defines the number of gradient accumulations before H2O Hydrogen Torch updates the neural network weights during model training.

note
  • Grad accumulation can be beneficial if only small batches are selected for training. With gradient accumulation, the loss and gradients are calculated after each batch, but it waits for the selected accumulations before updating the model weights. You can control the batch size through the Batch size setting.
  • Changing the default value of Grad Accumulation might require adjusting the learning rate and batch size.

Save best checkpoint​

This setting determines if H2O Hydrogen Torch should save the model weights of the epoch exhibiting the best validation metric. When turned On, H2O Hydrogen Torch saves the model weights for the epoch exhibiting the best validation metric. When turned Off, H2O Hydrogen Torch saves the model weights after the last epoch is executed.

note
  • This setting should be turned On with care as it has the potential to lead to overfitting of the validation data.
  • The default goal should be to attempt to tune models so that the last or very last epoch is the best epoch.
  • Suppose an evident decline for later epochs is observed in logging. In that case, it is usually better to adjust hyperparameters, such as reducing the number of epochs or increasing regularization, instead of turning this setting On.

Evaluation epochs​

This setting defines the number of epochs H2O Hydrogen Torch uses before each validation loop for model training. In other words, it determines the frequency (in a number of epochs) to run the model evaluation on the validation data.

note
  • Increasing the number of Evaluation Epochs can speed up an experiment.
Setting dependency

The Evaluation epochs setting is available only if the following setting is turned Off: Save Best Checkpoint.

Evaluate before training​

Determines whether to perform a validation run before training. This setting is potentially helpful for assessing the performance of zero-shot pertained backbones and checking the modeling pipeline.

note

The following supported problem types support externally pretrained zero-shot models (while problem types that do not contain this support fit a new head on top of a backbone):

  • Text span prediction
  • Text sequence to sequence
  • Speech recognition

Calculate train metric​

This setting determines whether the model metric should also be calculated for the training data at the end of the training. When On, the model metric is calculated for the training data. The resulting values do not indicate the true model performance because they are based on H2O Hydrogen Torch's identical data records for model training but can give insights into over/underfitting.

Train validation data​

This setting defines whether the model should use the entire train and validation dataset during model training. When turned On, H2O Hydrogen Torch uses the whole train dataset and validation data to train the model.

note
  • H2O Hydrogen Torch also evaluates the model on the provided validation fold. Validation is always only on the provided validation fold.
  • H2O Hydrogen Torch uses both datasets for model training if you provide a train and validation dataset.
    • To define a training dataset, use the Train dataframe setting. For more information, see Train dataframe.
    • To define a validation dataset, use the Validation dataframe setting. For more information, see Validation dataframe.
  • Turning On the Train validation data setting should produce a model that you can expect to perform better because H2O Hydrogen Torch trained the model on more data. Thought, also note that using the entire train dataset and out-of-fold validation dataset generally causes the model's accuracy to be overstated as information from the validation data is incorporated into the model during the training process.
    note

    If you have five folds and set fold 0 as validation, H2O Hydrogen Torch usually trains on folds 1-4 and reports on fold 0. With Train validation data turned On, we can add fold 0 to the training, but H2O Hydrogen Torch still reports its accuracy. As a result, it overstated for fold 0 but should be better for any unseen (test) data/production scenarios. For that reason, you usually want to consider this setting after running your experiments and deciding on models.

note

This setting is only available if you turned the Save best checkpoint setting Off.

Build scoring pipelines​

Determines whether the experiment (model) automatically generates an H2O MLOps pipeline and Python scoring pipeline at the end of the experiment. If turned Off, you can still create scoring pipelines on demand when the experiment is complete (e.g., when you click Download soring or Download MLOps).

Prediction settings​

Metric​

This setting defines the metric to evaluate the model's performance.

Options

Image regression | 3D image regression | Text regression | Audio regression

  • MAE: Mean absolute error
    • The Mean Absolute Error (MAE) is an average of the absolute errors. The MAE units are the same as the predicted target, which is useful for understanding whether the size of the error is of concern or not. The smaller the MAE the better the model’s performance.
  • MSE: Mean squared error
    • The MSE metric measures the average of the squares of the errors or deviations. MSE takes the distances from the points to the regression line (these distances are the “errors”) and squaring them to remove any negative signs. MSE incorporates both the variance and the bias of the predictor.
    • MSE also gives more weight to larger differences. The bigger the error, the more it is penalized. For example, if your correct answers are 2,3,4 and the algorithm guesses 1,4,3, then the absolute error on each one is exactly 1, so squared error is also 1, and the MSE is 1. But if the algorithm guesses 2,3,6, then the errors are 0,0,2, the squared errors are 0,0,4, and the MSE is a higher 1.333. The smaller the MSE, the better the model’s performance.
  • RMSE: Root mean squared error
    • The Root Mean Sqaured Error (RMSE) metric evaluates how well a model can predict a continuous value. The RMSE units are the same as the predicted target, which is useful for understanding if the size of the error is of concern or not. The smaller the RMSE, the better the model’s performance.
    • RMSE penalizes outliers more, as compared to MAE, so it is useful if we want to avoid having large errors.
  • MAPE: Mean absolute percentage error
    • Mean Absolute Percentage Error (MAPE) measures the size of the error in percentage terms. It is calculated as the average of the unsigned percentage error.
    • MAPE is useful when target values are across different scales.
  • SMAPE Symmetric mean absolute percentage error
    • Unlike the MAPE, which divides the absolute errors by the absolute actual values, the SMAPE divides by the mean of the absolute actual and the absolute predicted values. This is important when the actual values can be 0 or near 0. Actual values near 0 cause the MAPE value to become infinitely high. Because SMAPE includes both the actual and the predicted values, the SMAPE value can never be greater than 200%.
  • R2: R squared
    • The R2 value represents the degree that the predicted value and the actual value move in unison. The R2 value varies between 0 and 1 where 0 represents no correlation between the predicted and actual value and 1 represents complete correlation.

Image classification | 3D image classification | Text classification | Audio classification

  • LogLoss: Logarithmic loss
    • The logarithmic loss metric can be used to evaluate the performance of a binomial or multinomial classifier. Unlike AUC which looks at how well a model can classify a binary target, logloss evaluates how close a model’s predicted values (uncalibrated probability estimates) are to the actual target value. For example, does a model tend to assign a high predicted value like .80 for the positive class, or does it show a poor ability to recognize the positive class and assign a lower predicted value like .50? Logloss can be any value greater than or equal to 0, with 0 meaning that the model correctly assigns a probability of 0% or 100%.
  • ROC_AUC: Area under the receiver operating characteristic curve
    • This model metric is used to evaluate how well a binary classification model is able to distinguish between true positives and false positives. For multi-class problems, this score is computed by micro-averaging the ROC curves for each class.
    • An Area Under the Curve (AUC) of 1 indicates a perfect classifier, while an AUC of .5 indicates a poor classifier whose performance is no better than random guessing.
  • F1
    • The F1 score is calculated from the harmonic mean of the precision and recall. An F1 score of 1 means both precision and recall are perfect, and the model correctly identified all the positive cases and didn’t mark a negative case as a positive case. If either precision or recall is very low, it is reflected with an F1 score closer to 0.
    • Formula: F1 = 2 (Precision * Recall / Precision + Recall)
      • Precision is the positive observations (true positives) the model correctly identified from all the observations it labeled as positive (the true positives + the false positives).
      • Recall is the positive observations (true positives) the model correctly identified from all the actual positive cases (the true positives + the false negatives).
    • Micro-averaging: H2O Hydrogen Torch micro-averages the F1 metric (score).
      • Multi-class: For multi-class classification experiments utilizing an F1 metric, the derived micro-average F1 metric might look suspicious; in that case, the micro-average F1 metric is numerically equivalent to the accuracy score.
      • Binary: For binary classification experiments utilizing an F1 metric, the label column needs to contain 0/1 values. If the column contains string values, the column is transformed into multiple columns using a one-hot encoder method resulting in the experiment being treated as a multi-class classification experiment while leading to an incorrect calculation of the F1 metric.
  • F2
    • The F2 score is the weighted harmonic mean of the precision and recall (given a threshold value). Unlike the F1 score, which gives equal weight to precision and recall, the F2 score gives more weight to recall than to precision. More weight should be given to recall for cases where False Negatives are considered worse than False Positives. For example, if your use case is to predict which customers will churn, you may consider False Negatives worse than False Positives. In this case, you want your predictions to capture all of the customers that will churn. Some of these customers may not be at risk for churning, but the extra attention they receive is not harmful. More importantly, no customers actually at risk of churning have been missed.
    • Formula: F2 = 5 (Precision * Recall / (4 * Precision) + Recall)
      • Precision is the positive observations (true positives) the model correctly identified from all the observations it labeled as positive (the true positives + the false positives).
      • Recall is the positive observations (true positives) the model correctly identified from all the actual positive cases (the true positives + the false negatives).
    • Micro-averaging: H2O Hydrogen Torch micro-averages the F2 metric (score).
      • Multi-class: For multi-class classification experiments utilizing an F2 metric, the derived micro-average F2 metric might look suspicious; in that case, the micro-average F2 metric is numerically equivalent to the accuracy score.
      • Binary: For binary classification experiments utilizing an F2 metric, the label column needs to contain 0/1 values. If the column contains string values, the column is transformed into multiple columns using a one-hot encoder method resulting in the experiment being treated as a multi-class classification experiment while leading to an incorrect calculation of the F2 metric.
  • F05
    • The F05 score is the weighted harmonic mean of the precision and recall (given a threshold value). Unlike the F1 score, which gives equal weight to precision and recall, the F05 score gives more weight to precision than to recall. More weight should be given to precision for cases where False Positives are considered worse than False Negatives. For example, if your use case is to predict which products you will run out of, you may consider False Positives worse than False Negatives. In this case, you want your predictions to be very precise and only capture the products that will definitely run out. If you predict a product will need to be restocked when it actually doesn’t, you incur cost by having purchased more inventory than you actually need.
    • Formula: F05 = 1.25 (Precision * Recall / (0.25 * Precision) + Recall)
      • Precision is the positive observations (true positives) the model correctly identified from all the observations it labeled as positive (the true positives + the false positives).
      • Recall is the positive observations (true positives) the model correctly identified from all the actual positive cases (the true positives + the false negatives).
    • Micro-averaging: H2O Hydrogen Torch micro-averages the F05 metric (score).
      • Multi-class: For multi-class classification experiments utilizing an F05 metric, the derived micro-average F05 metric might look suspicious; in that case, the micro-average F05 metric is numerically equivalent to the accuracy score.
      • Binary: For binary classification experiments utilizing an F05 metric, the label column needs to contain 0/1 values. If the column contains string values, the column is transformed into multiple columns using a one-hot encoder method resulting in the experiment being treated as a multi-class classification experiment while leading to an incorrect calculation of the F05 metric.
  • Precision
    • The precision metric measures the ratio of correct true positives among all predicted positives.
    • Formula: Precision = True Positive / (True Positive + False Positive)
    • Micro-averaging: H2O Hydrogen Torch micro-averages the precision metric (score).
      • Multi-class: For multi-class classification experiments utilizing a precision metric, the derived micro-average precision metric might look suspicious; in that case, the micro-average precision metric is numerically equivalent to the accuracy score.
      • Binary: For binary classification experiments utilizing a precision metric, the label column needs to contain 0/1 values. If the column contains string values, the column is transformed into multiple columns using a one-hot encoder method resulting in the experiment being treated as a multi-class classification experiment while leading to an incorrect calculation of the precision metric.
  • Recall
    • The recall metric measures the ratio of true positives predicted correctly.
    • Formula: Recall = True Positive / (True Positive + False Negative)
    • Micro-averaging: H2O Hydrogen Torch micro-averages the recall metric (score).
      • Multi-class: For multi-class classification experiments utilizing a recall metric, the derived micro-average recall metric might look suspicious; in that case, the micro-average recall metric is numerically equivalent to the accuracy score.
      • Binary: For binary classification experiments utilizing a recall metric, the label column needs to contain 0/1 values. If the column contains string values, the column is transformed into multiple columns using a one-hot encoder method resulting in the experiment being treated as a multi-class classification experiment while leading to an incorrect calculation of the recall metric.
  • Accuracy
    • In binary classification, Accuracy is the number of correct predictions made as a ratio of all predictions made. In multiclass classification, the set of labels predicted for a sample must exactly match the corresponding set of labels in target values.
  • MCC: Matthews correlation coefficient
    • The goal of the Matthews Correlation Coefficient (MCC) metric is to represent the confusion matrix of a model as a single number. The MCC metric combines the true positives, false positives, true negatives, and false negatives using the following MCC equation: 𝑀𝐶𝐶=𝑇𝑃𝑥𝑇𝑁−𝐹𝑃𝑥𝐹𝑁/√(𝑇𝑃+𝐹𝑃)(𝑇𝑃+𝐹𝑁)(𝑇𝑁+𝐹𝑃)(𝑇𝑁+𝐹𝑁).
    • Unlike metrics like Accuracy, MCC is a good scorer to use when the target variable is imbalanced. In the case of imbalanced data, high Accuracy can be found by predicting the majority class. Metrics like Accuracy and F1 can be misleading, especially in the case of imbalanced data, because they do not consider the relative size of the four confusion matrix categories. MCC, on the other hand, takes the proportion of each class into account. The MCC value ranges from -1 to 1 where -1 indicates a classifier that predicts the opposite class from the actual value, 0 means the classifier does no better than random guessing, and 1 indicates a perfect classifier.

Image object detection

  • mAP: Mean average precision

Image semantic segmentation | 3D image semantic segmentation

  • IoU: Intersection over union
  • Dice

Image instance segmentation

  • COCO_mAP: COCO (Common Objects in Context) mean average precision

Image metric learning | Text metric learning

  • mAP: Mean average precision

Text token classification

  • CONLL_MICRO_F1_SCORE
    • Macro F1 score calculated in CoNLL style
  • CONLL_MACRO_F1_SCORE
    • Micro F1 score calculated in CoNLL style
  • MICRO_F1_SCORE: Micro F1 score
  • MACRO_F1_SCORE: Macro F1 score

Text span prediction

  • Jaccard
  • F1
  • Accuracy
  • Top_2_Accuracy
  • Top_3_Accuracy
  • Top_4_Accuracy
  • Top_5_Accuracy

Text sequence to sequence

  • BLEU
    • Computes the BLEU metric given hypotheses and references
  • CHRF
    • Computes the chrF(++) metric given hypotheses and references
  • TER
    • Computes the translation edit rate metric given hypotheses and references

Speech recognition

  • WER: Word error rate
  • CER: Character error rate

Batch size inference​

This setting defines the batch size of examples to utilize for inference.

note

Selecting 0 sets the Batch size inference to the same value used for the Batch size setting.

Probability threshold​

This setting determines the cutoff point for classifying instances into one of the classes.

In the context of machine learning, the probability threshold is a hyperparameter that is used when generating predictions from a model. It is specifically relevant in binary classification tasks where the goal is to classify instances into one of two classes.

When a machine learning model makes predictions, it assigns a probability or confidence score to each instance, indicating the likelihood of it belonging to a particular class. The probability threshold is a value that is set to determine the cutoff point for classifying instances into one of the classes.

By default, a probability threshold of 0.5 is often used, meaning that if the predicted probability of an instance belonging to a certain class is greater than or equal to 0.5, it is classified as belonging to that class. Conversely, if the predicted probability is less than 0.5, it is classified as belonging to the other class.

Test time augmentations​

This setting defines the test time augmentation(s) to apply during inference. Test time augmentations are applied when the model makes predictions on new data. The final prediction is an average of the predictions for all the augmented versions of an image.

Options

Image regression | 3D image regression | Image classification | 3D image classification | Image semantic segmentation | 3D image semantic segmentation | Image instance segmentation | Image metric learning

  • Horizontal flip
    • H2O Hydrogen Torch applies a horizontal flip as the test time augmentation(s).
  • Vertical flip
    • H2O Hydrogen Torch applies a vertical flip as the test time augmentation(s).

tip

Utilizing this setting can be a technique to improve the model accuracy.

Save prediction probabilities​

This setting determines whether to include and save the model prediction probabilities in the raw prediction output files. That is, in the validation_raw_predictions.pkl and test_raw_predictions.pkl files that you can download after the model is built. To learn more, see Download an experiment's predictions.

Environment settings​

GPUs​

This setting determines the list of GPUs H2O Hydrogen Torch can use for the experiment. GPUs are listed by name, referring to their system ID (starting from 1). If no GPUs are selected, H2O Hydrogen Torch utilizes the CPU for model training.

Number of seeds per run​

This setting defines the number of seeds to use for a single run. If more than one seed is selected, each experiment runs multiple times.

note
  • Deep learning models can sometimes exhibit certain randomness in individual runs. Running an experiment multiple times with multiple seeds, can give insights into stability of results.
  • In case of high randomness, better judgement can be made about the performance of a model with certain hyperparameter settings, by comparing the average results across seeds, for example in a grid search scenario.

Number of GPUs per run​

This setting defines the number of GPUs to use for a single run when training the model. A single run might represent a single fold, a single seed run or a single grid search run.

example

If 5 GPUs are available, it is possible to run a 5-fold cross-validation in parallel using a single GPU per fold.

note
  • The available GPUs are the ones that can be enabled using the GPUs setting.
  • If the number of GPUs is less than or equal to 1, this setting (Number of GPUs per run ) is not available.

Mixed precision training​

Determines whether to use mixed-precision during model training. When turned Off, H2O Hydrogen Torch does not use mixed-precision for training.

Note

Mixed-precision is a technique that helps decrease memory consumption and increases training speed.

Mixed precision inference​

Determines whether to use mixed-precision during model inference.

note

Mixed-precision is a technique that helps decrease memory consumption and increases inference speed.

Sync batch normalization​

Determines whether to synchronize batch normalization across GPUs in a distributed data-parallel (DDP) mode. In other words, when turned On, multi-GPU training is enabled to synchronize the batch normalization layers of the model across GPUs. In a nutshell, H2O Hydrogen Torch with multi GPU splits the batch across GPUs, and therefore, when a normalization layer wants to normalize data, it has access only to the part of the batch stored on the device. As a result, it works out of the box but gives better results if the data in all GPUs are collected to normalize the data of the entire batch.

Note

When turned On, data scientists can expect the training speed to drop slightly while the model's accuracy improves. However, this rarely happens in practice and only occurs under specific problem types and defined batch sizes.

Number of workers​

This setting defines the number of workers H2O Hydrogen Torch uses for the DataLoader. In other words, it defines the number of CPU processes to use when reading and loading data to GPUs during model training.

Seed​

This setting defines the random seed value that H2O Hydrogen Torch uses during model training. It defaults to -1, an arbitrary value. When the value is modified (not -1), the random seed allows results to be reproducible—defining a seed aids in obtaining predictable and repeatable results every time. Otherwise, not modifying the default seed value (-1) leads to random numbers at every invocation.

Logging settings​

Logger​

This setting defines the logger type that H2O Hydrogen Torch uses for model training

Options

  • None
    • This option does does not use any logger.
  • Neptune
    • This option utilizes Neptune as a logger to track the experiment. To use Neptune, you must define the following settings: Neptune API token and Neptune project.

Neptune API token​

This setting defines the Neptune API token to validate all subsequent Neptune API calls.

setting dependency

This setting is available if you select Neptune in the Logger setting.

Neptune project​

This setting defines the Neptune project.

setting dependency

This setting is available if you select Neptune in the Logger setting.

Log grad norm​

This setting determines whether to log the total grad norm before and after clipping.

note

This setting adds a small overhead during the experiment runtime but can help determine if the gradients are exploding or unstable.

tip

Turn this setting on if you suspect unstable gradients; as a result, you may then choose a value for the gradient clip to prevent exploding gradients.

Feedback