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
bilinear sampler #15
Comments
Hello @yangsenius and thanks for your interest. Regarding (1), the offsets are the small_offsets around each keypoint, and the base is either the midrange-offsets or the long-range offsets which need to be refined. We sample the offsets by the locations specified by the base and add them back into the base. I hope this is clear. I'm not sure what your question is in (2). We are indeed trying to gather values from the destinations of the offsets. If your question is in regard to the sampling implementation, note that this implementation is borrowed, as I mentioned in the readme, and I only lightly modified it to deal with border issues. Now, with tensorflow 1.14, you can use instead |
Hello @jricheimer, thanks for your helpful answer ! I think i have understood it :
|
Grateful for your implementation! I have some questions about the bilinear sampler.
KerasPersonLab/model.py
Line 49 in 32d44dd
Why
base = base + bilinear_sampler(offsets, base)
instead ofbase = base + bilinear_sampler(base, offsets)
? Does this mean that we interpolate theoffset
according to thebase
?KerasPersonLab/bilinear.py
Line 43 in 32d44dd
If we
iy0 = vy0 + h
, then theiy0
will represent the destination position of offsets. Why using these positions wheniy0 = tf.where(mask, tf.zeros_like(iy0), iy0)
?In this condition,
will gather values from the destination positions of predicted offsets, shouldn't we gather values from the start positions of offsets?
The text was updated successfully, but these errors were encountered: