precision-sustainable-ag/Field-AnnotationPipeline
This repo automates semantic labels and bounding boxes for Field imagery, within the broader Ag Image Repository, focusing on real-world agricultural conditions essential for training deep learning models.
PythonMIT
Issues
- 1
- 2
Revisit for data cleaning and reformatting
#32 opened by navjot-nangia - 0
- 0
- 0
- 0
bgr to rgb for cropouts
#34 opened by mkutu - 0
prep training Field data for yolo segmenter
#33 opened by mkutu - 0
merge train_model_weed_detection to develop
#22 opened by mkutu - 0
setup data ingestion for the processing pipeline
#19 opened by mkutu - 10
create metadata file for empty detection results
#23 opened by mkutu - 0
- 0
add data_upload/transfer process to move the processed data products to the longterm storage locker
#31 opened by mkutu - 4
move broad_sparse config from json to hydra yaml
#21 opened by mkutu - 2
species_info update
#25 opened by navjot-nangia - 0
- 0
- 3
- 0
update species_info.json with new species
#8 opened by mkutu - 2
testing for segment_weeds.py
#12 opened by mkutu - 1
- 0
- 1
breakup _clean_mask in segment_weeds.py
#15 opened by mkutu - 1
- 0
config data download and parsing using hydra
#7 opened by mkutu - 0
Explore HQ SAM
#9 opened by mkutu - 1
vit_b vs vit_h for segment_weeds
#10 opened by navjot-nangia - 2
- 1
train target-WEED detection model
#3 opened by mkutu - 0
implement classifier model in pipeline
#5 opened by mkutu - 0
train detection model to detect target plant
#2 opened by mkutu