Hongkun Liu

I tried to restore model_c, and finetune glintasia dataset use train_net.py , but loss stopped at about 3 ,it didn't decrease about 10thousand steps.

nvcc fatal : Unsupported gpu architecture 'compute_86'

1

When I setup deformable multi head attention, report the error as below: > nvcc fatal : Unsupported gpu architecture 'compute_86' > Traceback (most recent call last): > File "/data/queenie_liu/anaconda3/envs/mmTrans/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line...

I have three question: 1、I guess you only use target without other agents in calculating loss and propagating backward because you only generate one theta value in a sample scene,...

How you modify the code to reach the real-time performance?

2

I use mask-rcnn(backbone resnet-101) to train and predict my image, when I predict the image, only model.detect spends 250ms-300ms. I want to reduce the time in model.detect to 200-250ms, I...

Can't find model 'en_core_web_sm'

2

python scripts/main.py --data=image_20230408/ --out_dir output --world_size=1 --save_img Traceback (most recent call last): File "scripts/main.py", line 4, in from pipeline import semantic_annotation_pipeline File "/data2/queenie_2023/Semantic-Segment-Anything/scripts/pipeline.py", line 13, in from blip import open_vocabulary_classification_blip...