PROB

PROB copied to clipboard

Hi Orr, I have a couple thoughts on the final prediction and would love to hear your thoughts. If I understand things correctly the C+1 logit of the classification head...

luckylukez

Codebase writes malformed `learned*ft.json` files

8

Dear orr, Thanks for your opening code again, but when I use this code, I found a question about exemplar_replay_prev_file. When I finish the code PY_ARGS=${@:1} python -u main_open_world.py \...

yangengineering

OSError: [Errno 8] Exec format error: 'configs/EVAL_M_OWOD_BENCHMARK.sh'

1

Objective: I am trying to perform direct inference without training the model After setting up the environment and installing all dependencies,also I had made some changes required to run this...

simranbajaj06

Dear orrzohar, hello: First of all, thank you for making the model open source and other work. I encountered some issues while reproducing the PROB model. I configured the environment...

Taoxiaohei

diff between 'ProbObjectnessHead' and 'FullProbObjectnessHead'

1

In the PROB model, I noticed two modules, 'ProbObjectnessHead' and 'FullProbObjectnessHead'. I have two questions: 1. Only the former is used, but I believe the latter is more in line...

ezyzzy

About the number of images and annotations in the dataset

1

Hello author, thank you for your work. When I was downloading and processing the VOC and COCO datasets, I ended up with a final number of images: 150,375, and the...

2462954048