Home Explore Help
Sign In
mengxi
/
labelmeWithAI
2
0
Fork 0
Files Issues 0 Pull Requests 0 Wiki
Tree: 6f2e5e49e1
Branches Tags
labelmeWithAI
/
examples
/
semantic_segmentation
Tricolops 6f2e5e49e1 Added BarcodeDecodeModel for enhanced decoding capabilities. Implemented manual intervention for barcode detection by allowing specification of general areas when automatic detection fails. Reorganized code structure to streamline the execution flow and improve maintainability of segmentation and decoding operations. 3 months ago
..
.readme 03d7d365ce Update README images 5 years ago
data_annotated 61f5fee418 Remove lineColor and shapeColor keys from example JSON files 5 years ago
data_dataset_voc aa91168e4c Export original VOC format in labelme2voc.py 1 year ago
README.md 6f2e5e49e1 Added BarcodeDecodeModel for enhanced decoding capabilities. Implemented manual intervention for barcode detection by allowing specification of general areas when automatic detection fails. Reorganized code structure to streamline the execution flow and improve maintainability of segmentation and decoding operations. 3 months ago
labelme2voc.py aa91168e4c Export original VOC format in labelme2voc.py 1 year ago
labels.txt 6f2e5e49e1 Added BarcodeDecodeModel for enhanced decoding capabilities. Implemented manual intervention for barcode detection by allowing specification of general areas when automatic detection fails. Reorganized code structure to streamline the execution flow and improve maintainability of segmentation and decoding operations. 3 months ago

README.md

Semantic Segmentation Example

Annotation

labelme data_annotated --labels labels.txt --nodata --validatelabel exact --config '{shift_auto_shape_color: -2}'

labelme "/media/tricolops/New Volume/Merangue/" --labels labels.txt --nodata --validatelabel exact --config '{shift_auto_shape_color: -2}' --model /home/tricolops/PaddleDetection/Exported_model/openvino_new_50/Detection.xml --segmentation_model /home/tricolops/PaddleSeg/output_bisenetv2/openvino_2023.1_segmentaion/segmentation.xml

Convert to VOC-format Dataset

# It generates:
#   - data_dataset_voc/JPEGImages
#   - data_dataset_voc/SegmentationClass
#   - data_dataset_voc/SegmentationClassNpy
#   - data_dataset_voc/SegmentationClassVisualization
./labelme2voc.py data_annotated data_dataset_voc --labels labels.txt --noobject

Fig 1. JPEG image (left), PNG label (center), JPEG label visualization (right)

Note that the label file contains only very low label values (ex. 0, 4, 14), and 255 indicates the __ignore__ label value (-1 in the npy file).
You can see the label PNG file by following.

labelme_draw_label_png data_dataset_voc/SegmentationClass/2011_000003.png