Releases: airctic/icevision
Releases · airctic/icevision
0.12.0: added files for 0.12 release (#1064)
Co-authored-by: Francesco Pochetti <[email protected]>
0.11.0
updated CHANGELOG.md to the last PR (#974)
0.9.0a1
0.8.1
bumped version to 0.8.1 (#881)
0.8.0
Supports pytorch 1.8
Added
iou_thresholds
parameter toCOCOMetric
SimpleConfusionMatrix
Metric- Negative samples support for yolov5
- Negative samples support for mmdetection object detection models
Changed
- Breaking: Albumentations
aug_tfms
defaults.- rotate_limit changed from 45 to 15
- rgb_shift_limit changed from 20 to 10
- VOC parser uses image sizes from annotation file instead of image
- bumps fastai to latest version (<2.4)
0.8.0rc1
0.7.1a1
0.7.0
[0.7.0]
BREAKING: API Refactor
Added
- Metrics for mmdetection models
Changed
- Breaking: Renamed tasks
default,detect,classif
tocommon,detection,classification
- Breaking: Renamed
imageid
torecord_id
- Breaking: Added parameter
is_new
toParser.parse_fields
- Removed all dependencies on
cv2
for visualisation - Use new composite API for visualisation - covers user defined task names & multiple tasks
- Added a ton of visualisation goodies to
icevision.visualize.draw_data.draw_sample
- user can now- use custom fonts
- control mask thickness
- control mask blending
- prettify labels -- show confidence score & capitalise label
- plot specific and/or exclude specific labels
- pass in a dictionary mapping labels to specific colors
- control label height & width padding from bbox edge
- add border around label for legibility (color is a parameter)
Breaking:: Rename labels->label_ids
, labels_names->labels
in LabelsRecordComponent
- Renamed torchvision resnet backbones:
- resnet_fpn.resnet18 -> resnet18_fpn
- resnest_fpn.resnest18 -> resnest18_fpn
Breaking: Added parameters sample
and keep_image
to convert_raw_prediction
Breaking: Renamed VocXmlParser
to VOCBBoxParser
and VocMaskParser
to VOCMaskParser
Breaking: Renamed predict_dl
to predict_from_dl