EClassifier Class
EClassifier allows to train a classifier using an EClassificationDataset object and classify new images.
As required by Deep Learning techniques, the input image of EClassifier must be of the same format (width, height, number of channels). By default, this format will be the one of the first image added to the dataset used for training unless its width and height is smaller than the minimum width and height supported by the classifier (See EClassifier::MinimumWidth and EClassifier::MinimumHeight). In this case, the input resolution will be the minimum resolution supported by the classifier. The format can also be specified by the EClassifier::Width, EClassifier::Height and EClassifier::Channels. methods.
By default, images that don't satisfy the image format of the classifier are automatically reformatted. This behavior can be controlled through the EClassifier::EnableAutomaticImageReformat method. When the automatic image reformatting is disabled, training or classifying an image that doesn't satisfy the input image format will result in an exception.
Once trained, the input image format cannot be changed.
Base Class:EDeepLearningTool
Namespace: Euresys::Open_eVision::EasyDeepLearning
Methods
Classifies images and returns the complete results as an
EClassificationResult object.
The method throws an exception if the input image does not fulfill the input specification.
DEPRECATED. Use
EClassifier::ModelType instead. Capacity of classifier to use. Be aware that changing the classifier capacity will delete the effect of any previous training. The capacity will be translated to the corresponding type (Small, Normal, or Large).
Number of channels for input images of the classifier. The number of channels can be either 1 (monochrome image) or 3 (RGB image). By default, this value will be set from the format of the first image added to the training dataset.
Colorized heatmap with transparency.
When the minimum and maximum alpha values are different from each other, the transparency value for a pixel will depend on the value of the heatmap at that pixel. The range of heatmap values [0, 255] will be mapped to the range [minAlpha, maxAlpha].
Whether to always compute the heatmap along the result when applying the tool. If true, the heatmap is available through
EClassificationResult::Heatmap.
Enable automatic image reformat (true by default).
Enable histogram equalization of all images passing through the classifier. (false by default)
Gets a heatmap associated with the given label. A heatmap is an image that indicates which pixels in the original image best explain the given label.
Height for input images of the classifier. By default, this value will be set from the format of the first image of the dataset used for training.
Minimum height for input images of the classifier. This value is equal to 1 for standard networks.
Minimum width for input images of the classifier. This value is equal to 1 for standard networks.
Model type for training. Default: "Normal".
The list of available models is available through
EClassifier.
Number of available models for training an EasyClassify tool.
Type of the deep learning tool.
Whether to use a pretrained model when training.
Default: true if the pretrained model are found on the disk.
Width for input images of the classifier. By default, this value will be set from the format of the first image of the dataset used for training.
Whether a pretrained model for the current configuration can be found.
Loads the classifier and use it as a pretrained model.
Serializes the classifier settings.
DEPRECATED. Use
EClassifier::ModelType instead. Capacity of classifier to use. Be aware that changing the classifier capacity will delete the effect of any previous training. The capacity will be translated to the corresponding type (Small, Normal, or Large).
Number of channels for input images of the classifier. The number of channels can be either 1 (monochrome image) or 3 (RGB image). By default, this value will be set from the format of the first image added to the training dataset.
Whether to always compute the heatmap along the result when applying the tool. If true, the heatmap is available through
EClassificationResult::Heatmap.
Enable automatic image reformat (true by default).
Enable histogram equalization of all images passing through the classifier. (false by default)
Height for input images of the classifier. By default, this value will be set from the format of the first image of the dataset used for training.
Model type for training. Default: "Normal".
The list of available models is available through
EClassifier.
Whether to use a pretrained model when training.
Default: true if the pretrained model are found on the disk.
Width for input images of the classifier. By default, this value will be set from the format of the first image of the dataset used for training.
EClassifier Class
EClassifier allows to train a classifier using an EClassificationDataset object and classify new images.
As required by Deep Learning techniques, the input image of EClassifier must be of the same format (width, height, number of channels). By default, this format will be the one of the first image added to the dataset used for training unless its width and height is smaller than the minimum width and height supported by the classifier (See EClassifier::MinimumWidth and EClassifier::MinimumHeight). In this case, the input resolution will be the minimum resolution supported by the classifier. The format can also be specified by the EClassifier::Width, EClassifier::Height and EClassifier::Channels. methods.
By default, images that don't satisfy the image format of the classifier are automatically reformatted. This behavior can be controlled through the EClassifier::EnableAutomaticImageReformat method. When the automatic image reformatting is disabled, training or classifying an image that doesn't satisfy the input image format will result in an exception.
Once trained, the input image format cannot be changed.
Base Class:EDeepLearningTool
Namespace: Euresys.Open_eVision.EasyDeepLearning
Properties
DEPRECATED. Use
EClassifier::ModelType instead. Capacity of classifier to use. Be aware that changing the classifier capacity will delete the effect of any previous training. The capacity will be translated to the corresponding type (Small, Normal, or Large).
Number of channels for input images of the classifier. The number of channels can be either 1 (monochrome image) or 3 (RGB image). By default, this value will be set from the format of the first image added to the training dataset.
Whether to always compute the heatmap along the result when applying the tool. If true, the heatmap is available through
EClassificationResult::Heatmap.
Enable automatic image reformat (true by default).
Enable histogram equalization of all images passing through the classifier. (false by default)
Height for input images of the classifier. By default, this value will be set from the format of the first image of the dataset used for training.
Minimum height for input images of the classifier. This value is equal to 1 for standard networks.
Minimum width for input images of the classifier. This value is equal to 1 for standard networks.
Model type for training. Default: "Normal".
The list of available models is available through
EClassifier.
Number of available models for training an EasyClassify tool.
Type of the deep learning tool.
Whether to use a pretrained model when training.
Default: true if the pretrained model are found on the disk.
Width for input images of the classifier. By default, this value will be set from the format of the first image of the dataset used for training.
Methods
Classifies images and returns the complete results as an
EClassificationResult object.
The method throws an exception if the input image does not fulfill the input specification.
Colorized heatmap with transparency.
When the minimum and maximum alpha values are different from each other, the transparency value for a pixel will depend on the value of the heatmap at that pixel. The range of heatmap values [0, 255] will be mapped to the range [minAlpha, maxAlpha].
Gets a heatmap associated with the given label. A heatmap is an image that indicates which pixels in the original image best explain the given label.
Whether a pretrained model for the current configuration can be found.
Loads the classifier and use it as a pretrained model.
Serializes the classifier settings.