Experiment settings: Image object detection
The settings for an image object detection 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.
- 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.
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.
- 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.
Model type
It defines the model type for the experiment.
- The selected problem type, experience level, and model type determine the settings H2O Hydrogen Torch displays for the experiment.
- Not all problem types support the specification of a model type; in that case, the selected problem type and experience level determine the settings H2O Hydrogen Torch displays for the experiment.
Options
EfficientDet is the default model type for image object detection in H2O Hydrogen Torch. To learn more about EfficientDet, see EfficientDet: Scalable and efficient object detection. The implementation of FasterRCNNs in H2O Hydrogen Torch enables the selection of a pre-trained vision backbone from an extensive selection. To learn more about FasterRCNN, see Faster R-CNN: Towards real-time object detection with Region Proposal Networks. The implementation of FCOS in H2O Hydrogen Torch enables the selection of a pre-trained vision backbone from an extensive selection. To learn more about FCOS, see FCOS: Fully Convolutional One-Stage Object Detection. To learn more about Wav2vec2, see wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. To learn more about the Whisper architecture, see Robust Speech Recognition via Large-Scale Weak Supervision.Image object detection
Speech recognition
Import config from YAML
This setting defines the YML file that defines the experiment settings.
- 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.
- To learn how to download the YML file (configuration file) of a completed experiment, see Download an experiment's logs/config file.
Use previous experiment weights
This setting determines whether to initialize the model weights with the weights from the experiment specified in the Experiment setting.
A model's weights are available for an experiment (model) of the same problem type and backbone.
This setting might be useful in case you want to continue training from a built experiment.
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.
- 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.
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.
- 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.
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.
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.
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.
- 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.
- 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.
Unlabeled dataframe
Defines a separate CSV or Parquet file (depending on the problem type) containing a dataframe with unlabeled records that H2O Hydrogen Torch utilizes to generate pseudo labels. H2O Hydrogen Torch first trains the model with the provided labeled data (Train dataframe). Right after, the model predicts pseudo labels for the provided unlabeled dataframe before doing another training run that combines the original labels and pseudo labels.
- Image regression | Image classification | Image object detection
- The unlabeled dataframe just needs to contain a single image column
- Text regression | Text classification
- The unlabeled dataframe just needs to contain a single text column
- Audio regression | Audio classification | Speech recognition
- The unlabeled dataframe just needs to contain a single audio column
- Image regression | Image classification | Image object detection | Audio regression | Audio classification | Speech recognition
- Assets (images or audios) need to be located in the Data folder (setting)
- All supported problem types
- The training time can significantly increase depending on the size of the unlabeled data
As labeling can be expensive, having additional unlabeled data is quite common. Providing this unlabeled data in H2O Hydrogen Torch trains the model semi-supervised, potentially improving the model quality in contrast to only training on labeled data.
Class name column
Defines the dataset column containing a list of class names that H2O Hydrogen Torch uses for each instance mask.
X min column
Defines the dataset column containing a list of minimum X positions H2O Hydrogen Torch uses for each bounding box.
Y min column
Defines the dataset column containing a list of minimum Y positions H2O Hydrogen Torch uses for each bounding box.
X max column
Defines the dataset column containing a list of maximum X positions H2O Hydrogen Torch uses for each bounding box.
Y max column
Defines the dataset column containing a list of maximum Y positions H2O Hydrogen Torch uses for each bounding box.
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%.
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.
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.
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.
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.
- 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.
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
3D image classification | 3D image regression | 3D image semantic segmentation
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
3D image classification | 3D image regression | 3D image semantic segmentation
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.
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.
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.
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.
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
For an image object detection experiment using Mixup, H2O Hydrogen Torch uses the union of all the target boxes in mixed images. 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. For an image object detection experiment using Mixup, H2O Hydrogen Torch uses the union of all the target boxes in mixed images. Image regression | Image classification | Image object detection | Image semantic segmentation | Image instance segmentation
3D image classification | 3D image regression | 3D image semantic segmentation
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
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.
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.
- 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.
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.
- 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.
- 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.
- 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
- 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.)
Drop path rate
Grid search hyperparameter
Defines the drop path rate for the Backbone to use during training. The drop path rate prevents co-adaptation of parallel paths in networks, similar to how dropout prevents co-adaption of activations. If set to Default, it picks the default setting for the respective backbone.
This setting is available when Efficientdet is selected as the model type for the experiment.
Anchor num scales
Grid search hyperparameter
Defines the number of anchor scales to use for each anchor box. You may want to change this to work with more fine-grained scales. Note that changing this setting resets the head of the pre-trained model; in most use cases, it is recommended to use the default value.
This setting is available when Efficientdet is selected as the model type for the experiment.
Anchor scale
Grid search hyperparameter
Defines the general scale factor for all anchor boxes; you may want to change this if your dataset contains a large amount of particularly small or large boxes.
This setting is available when Efficientdet is selected as the model type for the experiment.
Anchor aspect ratios
Defines the different anchor aspect ratios for anchor boxes; in the best case, the selected anchor aspect ratios should match the default shapes in the dataset. Note that changing this setting resets the head of the pre-trained model: in most use cases, it is recommended to use the default value.
This setting is available when Efficientdet is selected as the model type for the experiment.
Anchor Iou match threshold
Grid search hyperparameter
Defines the IoU threshold for matching anchor boxes. In particular, the IoU threshold is used to determine whether an anchor box matches a ground truth box.
If you set the Anchor IoU match threshold to 0.5, the anchor box only matches a ground truth box if the IoU is greater than 50%.
In other words, the IoU threshold determines positive labels for anchors.
This setting is available when Efficientdet is selected as the model type for the experiment.
Training settings
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
- Adadelta
- To learn about Adadelta, see ADADELTA: An Adaptive Learning Rate Method.
- Adam
- To learn about Adam, see Adam: A Method for Stochastic Optimization.
- AdamW
- To learn about AdamW, see Decoupled Weight Decay Regularization.
- RMSprop
- To learn about RMSprop, see Neural Networks for Machine Learning.
- SGD
- H2O Hydrogen Torch uses a stochastic gradient descent optimizer.
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.
- 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
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: If you select Faster R-CNN as the experiment's Model type (setting), the following options are available: If you select FCOS as the experiment's Model type (setting), the following options are available:Image regression | Image classification | Text regression | Text classification | Text token classification | Audio regression | Audio classification
Image object detection
Options
Options
Options
Image semantic segmentation
3D image semantic segmentation | Text sequence to sequence
Image instance segmentation
Image metric learning | Text metric learning
Text regression
Text span prediction
A common strategy is to apply a lower learning rate to the backbone of a model for better convergence and training stability.
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.
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.
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.
- 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.
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.
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.
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.
- 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.
- 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.
- Increasing the number of Evaluation Epochs can speed up an experiment.
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.
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.
- 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.
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).
Export to ONNX
This setting attempts to export the trained model to an open neural network exchange (ONNX) format. If successful, the model in an ONNX format is available in the scoring pipeline.
ONNX target device
This setting defines the target device on which the open neural network exchange (ONNX) model runs. H2O Hydrogen Torch conducts model optimization for either CPU or GPU devices.
Box loss weight
Defines the weight of the box loss in EfficientDet (a type of object detection model); it is used to balance the loss of the bounding box regression and classification.
This setting is available when Efficientdet is selected as the model type for the experiment.
Focal Cls loss alpha
Defines the alpha hyperparameter value in the focal class loss function; for more information, refer to the following paper: Focal Loss for Dense Object Detection.
This setting is available when Efficientdet is selected as the model type for the experiment.
Focal Cls loss gamma
Defines the gamma hyperparameter value in the focal class loss function; for more information, refer to the following paper: Focal Loss for Dense Object Detection.
This setting is available when Efficientdet is selected as the model type for the experiment.
Prediction settings
Metric
This setting defines the metric to evaluate the model's performance.
Options
Image regression | 3D image regression | Text regression | Audio regression
Image classification | 3D image classification | Text classification | Audio classification
Image object detection
Image semantic segmentation | 3D image semantic segmentation
Image instance segmentation
Image metric learning | Text metric learning
Text token classification
Text span prediction
Text sequence to sequence
Speech recognition
Batch size inference
This setting defines the batch size of examples to utilize for inference.
Selecting 0 sets the Batch size inference to the same value used for the Batch size setting.
Metric Iou threshold
Defines the Intersection Over Union (IoU) threshold to calculate the selected metric for image object detection.
When calculating metrics, predicted bounding boxes with an IoU (with the true boxes) above the specified IoU threshold are treated as true positives.
Nms Iou threshold
Defines the Intersection Over Union (IoU) threshold when calculating post-processing non-maximum suppression (NMS).
Non-maximum suppression (NMS) is a post-processing step that reduces the number of bounding boxes predicted by the model. The NMS algorithm removes overlap boxes based on the selected IoU threshold. NMS keeps the higher scoring box.
Max det per image
Defines the maximum number of detections per image that the model returns.
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.
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.
- 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.
If 5 GPUs are available, it is possible to run a 5-fold cross-validation in parallel using a single GPU per fold.
- 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.
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.
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.
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.
This setting is available if you select Neptune in the Logger setting.
Neptune project
This setting defines the Neptune project.
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.
This setting adds a small overhead during the experiment runtime but can help determine if the gradients are exploding or unstable.
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.
Number of images
This setting defines the number of images to show in the experiment Insights tab.
- Submit and view feedback for this page
- Send feedback about H2O Hydrogen Torch to cloud-feedback@h2o.ai