Mayank Kumar

I am very new to these kinds of models so please help me understand where where in the code the output of ReferenceNet's spatial attention and cross-attention going in the...

Why does VPoser encoder take 63 parametres and not 72?

2

SMPL-X has 72 parameters which would provide much more detailed rendering. Is there a way to use VPoser encoder-decoder with 72 parameters instead of only 63. Thanks

Getting weird Rendering !

3

 I ran SMPLifyX today and got the above result. When I ran it yesterday, I got the following result:  I didn't changed any parametres, even tried reinstalling smplifyx.

## Question Why is my encrypted Linear Classifier slower than encrypted ConvNet classifier ? ## Further Information I am trying to evaluate an encrypted Linear and an encrypted CNN classifier...

The fedml-he example as implemented [here](https://github.com/FedML-AI/FedML/tree/master/python/examples/federate/cross_silo/mqtt_s3_fedavg_fhe_mnist_lr_example) does not seem to encrypt the model weights (torch tensors are communicated instead of ciphertext) even when the `enable_fhe` flag is `true` in the...