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
How to predict my own image? #26
Comments
Please follow our validation code. |
Hi @zyoohv, However, I am still not able to get correctly predict my own image. Were you able to figure it out? The validation uses the function Hi @leoxiaobin Can you please elaborate the use of center and scale arguments? Do we need to tag our images with these in order to use your trained model? |
@ahwaleed But unfortunately, I meet the same problem with you. I can not get correctly result on most of my images. I think it mainly because the model has overfit to the special dataset, so you'd better train your own model. good luck. |
@zyoohv Hi, I also want to predict my own images using the pre-trained model. However, the results are not satisfactory. I'm afraid I have to train my own model but not use the pre-trained model. BTW, have you figured out the use of center and scale? I did not use these two terms and I wonder wheter they are necessary to improve the results. |
@ahwaleed Hi, do you figure out how to predict own images with satisfactory performance? I wonder whether we can use the pre-trained models on my own images. |
@ybpaopao I tested the pre-trained model with my own image, the result is good in my case. This is how I run it with center and scale arguments:
|
Hi Qichao! Could you share your full code for testing the pretrained model with one single image? I'd really appreciate that. I ran what you have in this last block and get see some import statement errors. Thank you! |
Hi @williamrodz, I filled the left code, but the result is not good for the mpii images
the command to run it is create a .py file in pose_estimation folder and use command |
@jiaxue1993 |
@JunJieAI |
@jiaxue1993 |
@KaiserLew Load an image
|
@jiaxue1993
Can you elaborate on this? When you say "follow their validation code" do you mean you use the valid.py script as-is by creating your own person detection JSON and then create a dummy annotations file? Or have you modified the codebase in some meaningful way? For example, are you still using a config file and having the DATASET set to coco? |
@Godatplay |
Thanks for your reply. It seems like there is more to it to get results comparable to the original test, though. @jiaxue1993 and @leoxiaobin both mentioned using the validation code (sorry, I mis-tagged) |
@QichaoXu It is useful ,thanks, some low confidence points should be filtered out |
Hi @JunJieAI @QichaoXu @shehel or anyone who has tried this and got satisfied results |
@jiaxue1993 When I try to run the code you filled it gives me key error self.stage2_cfg = cfg['MODEL']['EXTRA']['STAGE2'] Do you have any idea how to solve it |
I didn't work on this for a while, just briefly looked through the code, I guess that might because model loading error? Just recommend you go through the authors tutorial first before working on your own images. |
Hello @jiaxue1993 , Thank you for the reply I have mailed you the thing which I tried, Thank You |
Thank You @jiaxue1993 I got a good output for my data. |
@zyoohv could you elaborate the use of pixel_std and this instruction in
|
@jiaxue1993 i think that:
should be
|
box = [450, 160, 350, 560] |
@jiaxue1993 Thanks for the code. But I'm wondering is the affine transform necessary? |
Code for visualizing is available in my fork https://github.com/BadMachine/human-pose-estimation.pytorch |
Faster-rcnn, Key points detection is available now. Besides, I added the function of social distance detection as well. https://github.com/finnickniu/Pytorch_keypoint_Socialdistance |
I guess this implementation is suitable for single person pose estimation only, at least it works fine for me this way. |
@AndriiHura Definitely, it needs an human detection first! |
@jiaxue1993, I find that your codes lack of something like nms? Because, I try validate in COCO dataset via your inference code, the result is worse than using code validation code of this repo. |
@BadMachine, could you show how to define width and height when visualizating? |
I read your code carefully, and implement with following code.
But I still get the wrong result.
Could you help me?
LoadNet.pdf
The text was updated successfully, but these errors were encountered: