Loads a deep learning model and prepares its execution on a specific target device.
const fil::DetectFeaturesModelDirectory& inModelDirectory,
const ftl::Optional<fil::DeviceType::Type>& inTargetDevice,
const ftl::Optional<fil::Size>& inInputSizeHint,
||A Detect Features model stored in a specific disk directory
||A device selected for deploying and executing the model. If not set, device depending on version (CPU/GPU) of installed Deep Learning Add-on is selected.
||Prepares the model for an execution with a given maximum input size (image size or a size of a roi bounding box) in advance
||Identifier of the deployed model
- In most cases, this filter should be placed in the INITIALIZE section.
- Executing this filter may take several seconds.
- This filter should be connected to DL_DetectFeatures through the ModelId ports.
- You can edit the model directly through the inModelDirectory. Another option is to use the Deep Learning Editor application and just copy the path to the created model.
- inInputSizeHint should be set to the maximum expected size of analysed area (in following DL_DetectFeatures filters, using deployed model), which is an image size or a bounding box of a roi. By default (if this input is set to NIL), a size of one of the training image is used (please note, that it does not take roi into account). Following this guideline should ensure an optimal memory usage and no performance hit on first call to DL_DetectFeatures.
- Passing NIL as inTargetDevice (which is default), is identical to passing DeviceType::CUDA on GPU version of Deep Learning Addon and DeviceType::CPU on CPU version on Deep Learning Addon.
- GPU version of Deep Learning Addon supports DeviceType::CUDA and DeviceType::CPU as inTargetDevice value.
- CPU version of Deep Learning Addon supports only DeviceType::CPU as inTargetDevice value.