shenhanqian / kgdet Goto Github PK
View Code? Open in Web Editor NEW[AAAI 2021] The official repo for the paper "KGDet: Keypoint-Guided Fashion Detection".
License: MIT License
[AAAI 2021] The official repo for the paper "KGDet: Keypoint-Guided Fashion Detection".
License: MIT License
I was going through the visual script in the repo but not able to understand how exactly should I visualise the bounding boxes.
不好意思,请问一下,测试数据的json文件里为什么还包含keypoints, segementation等数据,如果我想用自己的数据测试的话,具体说的话 我需要怎么制作json文件呢? 有什么资料可以参考吗?
谢谢。
输出的json文件里 同一张图片的同一种类型的衣服的keypoints也输出了几个,如果我只想输出score最高的那一个keypoints,我需要改哪里呢?
谢谢!
Following your steps exactly, why is each key point in the generated JSON file 1.0? As shown in the figure:
Will the visualization result in all the key points appearing because I haven't set them? Is there a problem with the prediction model?
There is no problem with the test, but it is strange to see 294 key points in the output file with all v being 1!!!
Thank you for sharing such an amazing repo. I'm testing it but having trouble installing dependencies because Colab and also my own laptop have Cuda 11.2 or higher so I cannot install pytorch and mmcv like your README instruction. Do you have plan for it?
Thank you for great research. I have a question about field keypoints in dataset. Why number keypoint very large 882 while max keypoint in deepfastion is 38 .
Hello.
Thanks you for the great work.
I used your checkpoints to test the deepfashon2 images, but I encountered some problems. I tried the following modifications:
Finally, I can run the demo. However, the output is not correct. Can you give some advises so that I can run the demo experiment successfully? Thanks.
Hi,
I am getting the following error: RuntimeError: Error compiling objects for extension
Getting this error when trying to run this command: !python3 setup.py develop
请问如果想要可视化测试结果的keypoints 跟 bbox,需要怎么弄?
没用过mmdetection,这个结构有点不熟悉
当我运行 ./mmdetection/tools/dist_test.sh configs/kgdet_moment_r50_fpn_1x-demo.py checkpoints/KGDet_epoch-12.pth 1 --json_out work_dirs/demo_KGDet.json --eval bbox keypoints
会出现下面的报错
bash: ./mmdetection/tools/dist_test.sh: /usr/bin/env: bad interpreter: Permission denied
请问这个可能是什么原因?
I Followed all the instructions to install this repo but when i run Test with 1 gpu demo, follow error occurs.
Traceback (most recent call last): File "./mmdetection/tools/test.py", line 13, in from mmdet.apis import init_dist File "/home/revolveai/projects/KGDet/mmdetection/mmdet/apis/init.py", line 2, in from .inference import (inference_detector, init_detector, show_result, File "/home/revolveai/projects/KGDet/mmdetection/mmdet/apis/inference.py", line 10, in from mmdet.core import get_classes File "/home/revolveai/projects/KGDet/mmdetection/mmdet/core/init.py", line 3, in from .evaluation import * # noqa: F401, F403 File "/home/revolveai/projects/KGDet/mmdetection/mmdet/core/evaluation/init.py", line 5, in from .eval_hooks import (CocoDistEvalmAPHook, CocoDistEvalRecallHook, File "/home/revolveai/projects/KGDet/mmdetection/mmdet/core/evaluation/eval_hooks.py", line 13, in from mmdet import datasets File "/home/revolveai/projects/KGDet/mmdetection/mmdet/datasets/init.py", line 7, in from .loader import DistributedGroupSampler, GroupSampler, build_dataloader File "/home/revolveai/projects/KGDet/mmdetection/mmdet/datasets/loader/init.py", line 1, in from .build_loader import build_dataloader File "/home/revolveai/projects/KGDet/mmdetection/mmdet/datasets/loader/build_loader.py", line 8, in from .sampler import DistributedGroupSampler, DistributedSampler, GroupSampler File "/home/revolveai/projects/KGDet/mmdetection/mmdet/datasets/loader/sampler.py", line 6, in from mmcv.runner.utils import get_dist_info ImportError: cannot import name 'get_dist_info' Traceback (most recent call last): File "/home/revolveai/miniconda3/envs/pft_test/lib/python3.6/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/home/revolveai/miniconda3/envs/pft_test/lib/python3.6/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/revolveai/miniconda3/envs/pft_test/lib/python3.6/site-packages/torch/distributed/launch.py", line 263, in main() File "/home/revolveai/miniconda3/envs/pft_test/lib/python3.6/site-packages/torch/distributed/launch.py", line 259, in main cmd=cmd) subprocess.CalledProcessError: Command '['/home/revolveai/miniconda3/envs/pft_test/bin/python', '-u', './mmdetection/tools/test.py', '--local_rank=0', 'configs/kgdet_moment_r50_fpn_1x-demo.py', 'checkpoints/KGDet_epoch-12.pth', '--launcher', 'pytorch', '--json_out', 'work_dirs/demo_KGDet.json', '--eval', 'bbox', 'keypoints']' returned non-zero exit status 1.
So I am trying to run this notebook on colab and I tried to run the line for demo on test images
# single-gpu testing !python tools/test.py /content/drive/MyDrive/KGDet/KGDet/configs/kgdet_moment_r50_fpn_1x-demo.py /content/drive/MyDrive/KGDet/KGDet/checkpoints/KGDet_epoch-12.pth --json_out work_dirs/demo_KGDet.json --eval bbox keypoints
and got the error test.py: error: unrecognized arguments: --json_out work_dirs/demo_KGDet.json
If I remove json from json_out then it raises a pkl file error
! ./tools/dist_test.sh /content/drive/MyDrive/KGDet/KGDet/configs/kgdet_moment_r50_fpn_1x-demo.py /content/drive/MyDrive/KGDet/KGDet/checkpoints/KGDet_epoch-12.pth 1 --json_out work_dirs/demo_KGDet.json --eval bbox keypoints
and got /bin/bash: ./tools/dist_test.sh: /usr/bin/env: bad interpreter: Permission denied
Is there a tutorial to run this on colab ?
I also tried following mmdetection's colab notebook tutorial and tried this
from mmdet.apis import inference_detector, init_detector, show_result_pyplot config = '/content/drive/MyDrive/KGDet/KGDet/configs/kgdet_moment_r50_fpn_1x-demo.py' checkpoint = '/content/drive/MyDrive/KGDet/KGDet/checkpoints/KGDet_epoch-12.pth' model = init_detector(config, checkpoint, device='cuda:0')
but ended up getting KeyError: 'RepPointsDetectorKp is not in the models registry'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.