module TensorflowLite::Image::Common
Direct including types
- TensorflowLite::Image::AgeEstimationExact
- TensorflowLite::Image::AgeEstimationRange
- TensorflowLite::Image::Classification
- TensorflowLite::Image::FaceDetection
- TensorflowLite::Image::GenderEstimation
- TensorflowLite::Image::ObjectDetection
- TensorflowLite::Image::PoseEstimation
- TensorflowLite::Image::Segmentation
Defined in:
tflite_image.crConstructors
Instance Method Summary
-
#client : Client
the tensorflow lite client
-
#detection_adjustments(image : Canvas, scale_mode : Scale = @scaling_mode)
this will calculate the adjustments required to the detections for overlaying on the original image (or a scaled image in the same aspect ratio)
-
#detection_adjustments(image_width : Int32, image_height : Int32, scale_mode : Scale = @scaling_mode)
this will calculate the adjustments required to the detections for overlaying on the original image (or a scaled image in the same aspect ratio)
-
#input_format : Format
the detected tensor format (can be set manually, but not recommended)
-
#labels : Array(String)
the labels extracted from the model or provided in the initializer
-
#resolution : Tuple(Int32, Int32)
returns width x height that the models requires
-
#run(canvas : Canvas, scale_mode : Scale = @scaling_mode, resize_method : StumpyResize::InterpolationMethod = :bilinear)
scales the image before invoking the tflite model
-
#scaling_mode : Scale
the scaling mode to use when preparing images for analysis
-
#scaling_mode=(scaling_mode : Scale)
the scaling mode to use when preparing images for analysis
Constructor Detail
Instance Method Detail
this will calculate the adjustments required to the detections for overlaying on the original image (or a scaled image in the same aspect ratio)
this will calculate the adjustments required to the detections for overlaying on the original image (or a scaled image in the same aspect ratio)
the detected tensor format (can be set manually, but not recommended)
scales the image before invoking the tflite model
the scaling mode to use when preparing images for analysis
- Use fit if you would like the whole image to be processed, however letter boxing means the image is smaller which may effect detections
- Use cover if you would like to crop the image, only the middle of the image will be used for detection unless the aspect ratio matches the model input
the scaling mode to use when preparing images for analysis
- Use fit if you would like the whole image to be processed, however letter boxing means the image is smaller which may effect detections
- Use cover if you would like to crop the image, only the middle of the image will be used for detection unless the aspect ratio matches the model input