István Sárándi

Do you necessarily need a Keras-style checkpoint for this? It should be possible to backprop through the TF SavedModel as well and get gradients wrt the input image. You may...

For SPEC-SYN, I ended up computing the extrinsic camera matrix from 2D-3D joint correspondences. This is the Perspective-n-Point (PnP) problem, and can be solved using `cv2.solvePnP()` or `cv2.calibrateCamera()` in OpenCV....

Not sure why that is. Meanwhile, you can try pip installing from the repo. But I recommend installing Mayavi with conda.

Set `num_aug=1` for fastest results. The new efficientnetv2-s models can run in real time even on a laptop GPU.

You can check some timing measurements on this poster: https://istvansarandi.com/media/sarandi-eccv2022-demo-poster.pdf It can run in real time even on a laptop GPU.

I faced the same issue and resolved it by rolling my own `map_fn` via `TensorArray`. Here's a rough sketch: ```python def map_fn2(fn, elems, fn_output_signature): batch_size = tf.shape(tf.nest.flatten(elems)[0])[0] arr = tf.TensorArray(...

Thanks for the question! I'm planning to write a how-to, so reports like this are helpful. For writing videos, you need to call new_sequence_output at the start of the desired...

You have to call new_sequence_output with a video file path string (ending in eg. mp4). And you have to do this not at the end but when you want to...

> Hello, i am trying all the aforementioned suggestion but i get the same error. I am using wsl. any suggestions? Thanks in advance. Can you paste the code you're...

The black screen is an issue with Mayavi and VTK and other library version compatibility, unrelated to PoseViz code. I'll try setting better version requirements. Meanwhile you can search github...