Open MilkLoo opened 5 months ago
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.
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?
Could you visualize your 2D pose input and full error log?
I follow the operation of Redame.md step by step, and input is also downloaded from the link.
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.
Hello, I have adjusted the parameters and tried many times, but the effect is still not very good. What is to be done?
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: @.***>
I have not modified the code, is directly configured after the running code
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: @.***>
Hello, I changed your parameter to True, but the effect is still the same.
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.
Hello, I have solved this problem with the network after retraining, thank you!
@MilkLoo That sounds great! Maybe there's problem in the uploaded weight? I will check it out once I get resource again.
@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.
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
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?