Detectron: how can I downloads the weights.pkl for rpn_person_only_R-101-FPN_1x.yaml

Created on 25 Feb 2019 · 3Comments · Source: facebookresearch/Detectron

PLEASE FOLLOW THESE INSTRUCTIONS BEFORE POSTING

Please thoroughly read README.md, INSTALL.md, GETTING_STARTED.md, and FAQ.md
Please search existing open and closed issues in case your issue has already been reported
Please try to debug the issue in case you can solve it on your own before posting

After following steps 1-3 above and agreeing to provide the detailed information requested below, you may continue with posting your issue

(Delete this line and the text above it.)

Expected results

What did you expect to see?

Actual results

What did you observe instead?

Detailed steps to reproduce

E.g.:

The command that you ran

System information

Operating system: ?
Compiler version: ?
CUDA version: ?
cuDNN version: ?
NVIDIA driver version: ?
GPU models (for all devices if they are not all the same): ?
PYTHONPATH environment variable: ?
python --version output: ?
Anything else that seems relevant: ?

Source

Adhders

Most helpful comment

@Adhders ，i got the same problem in docker，but is was solved by changing _DETECTRON_S3_BASE_URL = 'https://dl.fbaipublicfiles.com/detectron' in line 40 in
/detectron/lib/utils/io.py， i help it work to u

xiang-zhe on 12 Mar 2019

👍3

All 3 comments

when i enter "python3 tools/infer_simple.py --cfg configs/12_2017_baselines/rpn_person_only_R-101-FPN_1x.yaml --output-dir /tmp/detectron-visualizations --image-ext jpg --wts https://dl.fbaipublicfiles.com/detectron/35861858/12_2017_baselines/rpn_person_only_R-101-FPN_1x.yaml.02_32_51.SgT4y1cO/output/train/coco_2014_train:coco_2014_valminusminival/generalized_rcnn/model_final.pkl demo"

there is AssertionError: Detectron only automatically caches URLs in the Detectron S3 bucket: https://s3-us-west-2.amazonaws.com/detectron

Adhders on 25 Feb 2019

xiang-zhe on 12 Mar 2019

👍3

Hi @Adhders, you can find the up-to-date download links for person only RPN models here. Thanks for the suggestion @xiang-zhe. We updated the URLs in 5ed75f9d672b3c78b7da92d9b2321d04f33a7ccc so you may need to rebase on master or apply the corresponding code changes if your fork diverged from this repo (see #781 for more info).