-
int the data/OWDETR/VOC2007/ImageSets/ files are:
t1_train.txt t2_train.txt t2_ft.txt
t3_train.txt t3_ft.txt t4_train.txt t4_ft.txt
but int the 'OWOD_new_split.…
-
python tools/train_net.py --num-gpus 1 --eval-only --config-file ./configs/OWOD/t1/t1_test.yaml SOLVER.IMS_PER_BATCH 1 SOLVER.BASE_LR 0.005 OUTPUT_DIR "./output/t1_final"
Command Line Args: Namespace…
-
When running the **"replicate.sh"**, there will be problems. When running **"python tools/train_net.py --num-gpus 4 --dist-url='tcp://127.0.0.1:52133' --config-file ./configs/OWOD/t1/t1_val.yaml SOLVE…
-
What is the upper bound on the iOD mission of PASCAL VOC? Have you tested it?
-
I'm confused that `all_task_test.txt` have 10246（4952+5294）,4952 is voc test split, what is 5294?
coco test split is 5000?
_Originally posted by @JiweiMaster in https://github.com/JosephKJ/OWOD/i…
-
Where in the code do we store 50 samples per known category?
-
Dear @JosephKJ ,
After using the given models run the detection, how can i visualize the results ? I did not found the outputs about where to draw the
bounding boxes and labels.
Thank you very…
-
when I run
python tools/train_net.py --num-gpus 2 --eval-only --config-file ./configs/OWOD/t1/t1_test.yaml SOLVER.IMS_PER_BATCH 8 SOLVER.BASE_LR 0.005 OUTPUT_DIR "./output/t1_final" MODEL.WEIGHTS "/…
-
Hi,
I notice that the performance of Mask-RCNN-P is very similar to the vanilla Mask-RCNN in table 1. Is there any reason why the pseudo label method like OWOD didn't work?
-
first thank for your excellent job
but an error occurred when i tried to reproduce your code:
Traceback (most recent call last):
File "tools/train_net.py", line 172, in
args=(args,),
…