About 2D pose

[MilkLoo]

Hello, according to the paper, I can see that the image has 2Dpose input, but in the code, I don't see where the 2Dpose input comes from. Could you please help me understand the following code?

[hongsukchoi]

Hi!

In the demo code, you can find the source here: https://github.com/hongsukchoi/3DCrowdNet_RELEASE/blob/79284d533cd88515aec08fa04ee0eb50f847c6af/demo/demo.py#L119

In the dataloader code,

you can look at the def load_data(self): function.

[MilkLoo]

Hello, I want to ask, I use your trained weight files and pictures, demo.py, but the effect is not so good, is what I did wrong?

[hongsukchoi]

Could you visualize your 2D pose input and full error log?

[MilkLoo]

I follow the operation of Redame.md step by step, and input is also downloaded from the link.

[hongsukchoi]

I see. Which link did you use?

And I think you can solve this problem by tuning the parameter here: https://github.com/hongsukchoi/3DCrowdNet_RELEASE/blob/79284d533cd88515aec08fa04ee0eb50f847c6af/demo/demo.py#L142

The input 2D pose has an inaccurate lower body pose. You can filter those joints by increasing the threshold.

[MilkLoo]

Hello, I have adjusted the parameters and tried many times, but the effect is still not very good. What is to be done?

[hongsukchoi]

This looks definitively wrong. Can you show me the code that you changed? Or did you run without any modification?

Best regards, Hongsuk Choi https://hongsukchoi.github.io

On Fri, Mar 15, 2024 at 3:57 AM YI XINCHANG @.***> wrote:

90566cbe2ca20c30bd953d6d245cd4d.jpg (view on web) https://github.com/hongsukchoi/3DCrowdNet_RELEASE/assets/134379440/4d7c39c4-2620-42ae-a017-995bcc5d79bc b5133ae1af2b8269265b40899291c14.jpg (view on web) https://github.com/hongsukchoi/3DCrowdNet_RELEASE/assets/134379440/b7fb57fc-0ad3-4603-a402-0f13eb28639a Hello, I have adjusted the parameters and tried many times, but the effect is still not very good. What is to be done?

— Reply to this email directly, view it on GitHub https://github.com/hongsukchoi/3DCrowdNet_RELEASE/issues/34#issuecomment-1999115901, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHNGKW7G6AXTRUAHANXTGJLYYKSVPAVCNFSM6AAAAABETPKRNGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSOJZGEYTKOJQGE . You are receiving this because you commented.Message ID: @.***>

[MilkLoo]

I have not modified the code, is directly configured after the running code

[hongsukchoi]

I see. Then, I feel like the model checkpoint is actually not loaded. Could you change the model load code to use ‘strict=True’ and see if there’s any error?

Best regards, Hongsuk Choi https://hongsukchoi.github.io

On Fri, Mar 15, 2024 at 11:06 PM YI XINCHANG @.***> wrote:

I have not modified the code, is directly configured after the running code

— Reply to this email directly, view it on GitHub https://github.com/hongsukchoi/3DCrowdNet_RELEASE/issues/34#issuecomment-2001344748, or unsubscribe https://github.com/notifications/unsubscribe-auth/AHNGKW2XVVZYZ4TXQC3G56LYYOZNBAVCNFSM6AAAAABETPKRNGVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDAMBRGM2DINZUHA . You are receiving this because you commented.Message ID: @.***>

[MilkLoo]

Hello, I changed your parameter to True, but the effect is still the same.

[hongsukchoi]

Hi! It seems the code is giving random results. But I can't find a reason if you didn't change the code... I hope others people can try the current code and discuss. Unfortunately, I have no resource to run the code. Maybe you can check the inference code on 3DPW benchmark first.

[MilkLoo]

Hello, I have solved this problem with the network after retraining, thank you!

[hongsukchoi]

@MilkLoo That sounds great! Maybe there's problem in the uploaded weight? I will check it out once I get resource again.

[MilkLoo]

@hongsukchoi

I'm really sorry, I still need to trouble you, now I have the 2D pose data of Human3.6M test set, I want to use the model to evaluate the results, but the code of the evaluation part is not good at writing, can you share it? Thank you.

[hongsukchoi]

Hi!

I am not sure I understood your question. You could change the testing dataset here: https://github.com/hongsukchoi/3DCrowdNet_RELEASE/blob/main/assets/yaml/3dpw.yml

and run the command here: https://github.com/hongsukchoi/3DCrowdNet_RELEASE/blob/main/assets/running.md