CPU mode gives wrong 3D pose results about vnect-tensorflow HOT 18 CLOSED

there is a mistake in utils/utils.py

in def extract_3d_joints_from_heatmap x and y is mixed up (line 80 and 81). it should be

coord_2d_x = joints_2d[joint_num][0] 
coord_2d_y = joints_2d[joint_num][1]

After fixing that the 3D plot looks fine (although the axes are messed up)

from vnect-tensorflow.

I think it's not related to cpu or gpu, but there's some problem in 3d pose now.

from vnect-tensorflow.

Has anyone traced the cause of the error?

from vnect-tensorflow.

I am taking same results. Has anyone solved this problem ?

from vnect-tensorflow.

@timctho I think there is some problem in 2d pose results. Joints are not in true localizations.

from vnect-tensorflow.

can any one send me the VNect model file? Thanks!

from vnect-tensorflow.

@timctho How can I get the models/weights/vnect_tf file?

from vnect-tensorflow.

Mabe, it just missed the step of "Kinematic Skeleton Fiting”

from vnect-tensorflow.

@Superlee506 can you tell me more about "Kinematic Skeleton Fiting”? Is it wrote in the paper?

from vnect-tensorflow.

3d pose is also a problem, i test some but cant get a good result, anybody has good idea?

from vnect-tensorflow.

This is my output from above method.
It is quite different from above result.
In my case, 3D skeleton is also wrongly estimated.
How can I get the good estimation?

from vnect-tensorflow.

Well not even your 2D pose is correct and it should be working if you checkout the current repository.
Are sure you changed the correct lines of code?

from vnect-tensorflow.

@cDenius
I had tried this code with these follows.

1. Download weights from the author of paper
2. change weights with using './caffe_weight_to_pickle.py'
3. run '/models/vnect_model.py' to get

   vnect_tf.data-00000-of-00001
   vnect_tf.index
   vnect_tf.meta

4. change the code

   coord_2d_x = joints_2d[joint_num][0] 
   coord_2d_y = joints_2d[joint_num][1]

5. run '/demo_tf.py'

If you can share your parameters, could you send it to my e-mail?

• [email protected]

from vnect-tensorflow.

That is weird. If you don't change the two lines of code do you get the same results as the OP?
I get the desired output without doing or changing anything else besides the 5 steps you have described.

from vnect-tensorflow.

@cDenius
So do you have tensorflow weights without conversion??
Where did you get that weights?
i mean vnect_tf~ files

from vnect-tensorflow.

The messed up axes can be fixed by switching y_pair and x_pair in draw_limbs_3d in utils.py (lines 112+113):

Although there seem to be some scaling issues now haha

from vnect-tensorflow.

@lavage
I can reproduce your results by following your procedures, but it seems like the z coordinates of 3d joint points are incorrect.
Have you observed any similar situations?
Thanks.

from vnect-tensorflow.

@zeroHuang0516
That is what I meant with the scaling issue, you just defined it a bit better ;). Unless you are having different z coordinate issues than shown in my picture above?

As the overall body composition looks ok, it wouldn't be too difficult to normalize the z coordinates however.

from vnect-tensorflow.