com.intel.analytics.bigdl.transform.vision.image
Get input in this MiniBatch.
Get target in this MiniBatch
Replace the original content of the miniBatch with a set of Sample.
Replace the original content of the miniBatch with a set of Sample.
a set of Sample
self
Get the number of samples in this MiniBatch
Get the number of samples in this MiniBatch
size How many samples in this MiniBatch
Slice this MiniBatch to a smaller MiniBatch with offset and length
Slice this MiniBatch to a smaller MiniBatch with offset and length
offset, counted from 1
length
A smaller MiniBatch
An deprecated function for single-input/single-target MiniBatch.
An deprecated function for single-input/single-target MiniBatch. You don't need to override this, because we have add a default implement to throw exception.
(Since version 0.2.0) Old interface, use getInput instead
An deprecated function for single-input/single-target MiniBatch.
An deprecated function for single-input/single-target MiniBatch. You don't need to override this, because we have add a default implement to throw exception.
(Since version 0.2.0) Old interface, use getTarget instead
A batch of images with flattened RoiLabels the getTarget() returns a Table with key from 1 to batchSize. Each key in the table is mapped to a Table for the annotation of an image in the batch. The annotation table holds the annotation info for one image (assume the image has N detections). The annotation table has
Key Value RoiImageInfo.CLASSES the categories for each detections (see RoiLabel.clasees field) (1 x N), or (2 x N) Tensor[Float] RoiImageInfo.BBOXES the bboxes, (N x 4) Tensor[Float] RoiImageInfo.MASKS (Optional) the mask data, Array[Tensor[Float]\]. The outer array has N elements. The inner tensor holds the data for segmentation RoiImageInfo.ISCROWD Whether each detection is crowd. (1 x N) Tensor[Float]. -1: unknown, 0: not crowd, 1: is crowd RoiImageInfo.IMGINFO with shape (batchSize, 4), contains all images info (height, width, original height, original width)