New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Body_25b vs. Body_25 caffemodels #3
Comments
Our models are different (and more accurate) than that one, that is why we do not pre-train on it. |
Thank you for your answer. Would it be possible to provide a pre-trained model body_25b which is compatible with the generated by default prototxts by your scripts? |
https://github.com/CMU-Perceptual-Computing-Lab/openpose_train/tree/master/experimental_models The exact d_setLayers might be slightly different, but its own one is included in those models as well. |
Sorry! I've just realized that the d_setLayers was not included in the repo due to some issue with our gitignore file. They are now uploaded! In addition, we have added the scripts for the official body_25 from OpenPose (but we recommend using body_25b for better accuracy while maintaining the same speed). See the updated README from https://github.com/CMU-Perceptual-Computing-Lab/openpose_train/tree/master/experimental_models |
This is great! Thank you so much!
…On Sun, Oct 20, 2019 at 3:12 PM Gines ***@***.***> wrote:
Sorry! I've just realized that the d_setLayers was not included in the
repo due to some issue with our gitignore file. They are now updated!
In addition, we have added the scripts for the official body_25 from
OpenPose (but we recommend using body_25b for better accuracy while
maintaining the same speed).
See the updated README from
https://github.com/CMU-Perceptual-Computing-Lab/openpose_train/tree/master/experimental_models
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#3?email_source=notifications&email_token=ADBE4L6EIFPGPJM3CHYHVEDQPSUTJA5CNFSM4I6XZXPKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEBYROMQ#issuecomment-544282418>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ADBE4L3MFLQGFXYTXYBAG3DQPSUTJANCNFSM4I6XZXPA>
.
|
I have the following question and will really appreciate if you have any insights. |
What is your input resolution? |
The base one, 368x368
…On Wed, Nov 6, 2019 at 2:56 PM Aneri Sheth ***@***.***> wrote:
I have the following question and will really appreciate if you have any
insights.
I trained from scratch body_25b fast model and its mAP is 51.6% on coco
val2017 (17 keypoints) after running the full schedule as generated in
pose_solver.prototxt.
The model you just provided has mAP of 53.2% on the same data set. Do you
have an idea why I am getting a worse result? I noticed some differences in
the OPData layer in the provided train proto in
experimental_models/1_25BBkg/training_results, such as different name for
the rotation angle which would not work with the current openpose code. It
is possible the protos are generated with an older version of openpose?
Also the variable scale_maxs: "1.5" , instead of scale_maxs: "1.5;1.5;2.5".
Is this what you recommend?
What is your input resolution?
—
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#3?email_source=notifications&email_token=ADBE4L7WIECFU2BIZOXO2CLQSMONXA5CNFSM4I6XZXPKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEDHZKDA#issuecomment-550475020>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/ADBE4L46NRRPILE3A25MQEDQSMONXANCNFSM4I6XZXPA>
.
|
Our best resuls are obtained with 4-GPU machines and a batch size of 10, training for about 800k iterations (and picking the model with maximum accuracy amount those). [This line has also been pushed into train/README.md, thanks for the question!] Are you using this setting as well? |
The provided body_25 model is not compatible with the current openpose_caffe_train. It cannot be loaded to be used as a starting point for finetuning. It gives the error: Can't parse message of type "caffe.NetParameter" because it is missing required fields: layer[0].clip_param.min, layer[0].clip_param.max. Is it possible to release a pretrained body_25 model compatible with the d-setLayer.py generated training scripts?
Posting rules
Error
).Posts which do not follow these rules will be ignored, closed, or reported with no further clarification.
Issue Summary
Executed Command (if any)
Note: add
--logging_level 0 --disable_multi_thread
to get higher debug information.OpenPose Output (if any)
Errors (if any)
Type of Issue
You might select multiple topics, delete the rest:
Your System Configuration
Whole console output (if errors appeared), paste the error to PasteBin and then paste the link here: LINK
OpenPose version: Latest GitHub code? Or specific commit (e.g., d52878f)? Or specific version from
Release
section (e.g., 1.2.0)?General configuration:
lsb_release -a
in Ubuntu):gcc --version
in Ubuntu or VS version in Windows): 5.4.0, ... (Ubuntu); VS2015 Enterprise Update 3, VS2017 community, ... (Windows); ...?Non-default settings:
3rd-party software:
cmake --version
in Ubuntu):apt-get install libopencv-dev
(only Ubuntu); OpenPose default (only Windows); compiled from source? If so, 2.4.9, 2.4.12, 3.1, 3.2?; ...?If GPU mode issue:
cat /usr/local/cuda/version.txt
in most cases):nvidia-smi
in Ubuntu):If CPU-only mode issue:
If Python API:
python -c "import numpy; print numpy.version.version"
in Ubuntu):If Windows system:
If speed performance issue:
The text was updated successfully, but these errors were encountered: