utils#
SSD 300 utils adapted from MLCommons.
Based on MLCommons Reference Implementation here
Functions
|
Module |
Classes
Inspired by https://github.com/kuangliu/pytorch-ssd Transform between (bboxes, lables) <-> SSD output. |
|
SSD Data Augumentation, according to original paper Composed by several steps: |
- class composer.models.ssd.utils.Encoder(dboxes)[source]#
Inspired by https://github.com/kuangliu/pytorch-ssd Transform between (bboxes, lables) <-> SSD output.
- dboxes: default boxes in size 8732 x 4,
encoder: input ltrb format, output xywh format decoder: input xywh format, output ltrb format
- encode:
input : bboxes_in (Tensor nboxes x 4), labels_in (Tensor nboxes) output : bboxes_out (Tensor 8732 x 4), labels_out (Tensor 8732) criteria : IoU threshold of bboexes
- decode:
input : bboxes_in (Tensor 8732 x 4), scores_in (Tensor 8732 x nitems) output : bboxes_out (Tensor nboxes x 4), labels_out (Tensor nboxes) criteria : IoU threshold of bboexes max_output : maximum number of output bboxes
- class composer.models.ssd.utils.SSDCropping(num_cropping_iterations=1)[source]#
Cropping for SSD, according to original paper Choose between following 3 conditions:
Preserve the original image
Random crop minimum IoU is among 0.1, 0.3, 0.5, 0.7, 0.9
Random crop
Reference to https://github.com/chauhan-utk/ssd.DomainAdaptation
- class composer.models.ssd.utils.SSDTransformer(dboxes, size=(300, 300), val=False, num_cropping_iterations=1)[source]#
SSD Data Augumentation, according to original paper Composed by several steps:
Cropping Resize Flipping Jittering
- composer.models.ssd.utils.calc_iou_tensor(box1, box2)[source]#
Calculation of IoU based on two boxes tensor, Reference to https://github.com/kuangliu/pytorch-ssd.