neogyk
neogyk
@exook @psteinb , I have not. I will take a look.
I can benchmark the CMS data with perun, so we will check how it works.
Currently, the baler can be executed only with full precision numbers. The mixed precision is not working due to the error of mismatch of the data types during the matrix...
Dear @TaliCohn, I am still working, the code is not yet finalised.
@TaliCohn, tomorrow it's will be ready
Dear @TaliCohn . I have finished the implementation of the QVT, trained it using MNIST dataset. The backpropagation is very slow, it's very hard to achieve the results with the...
@BALJAPALLIANSHUL, there are already implemented [workflow](https://github.com/neogyk/baler/commit/728362487e7cb2e4bbd0e2be5636c6531bf57913#diff-ffbc8e48c2c993cd23502298f9820bda3f144c8a867f6943290e61dba6a6bf3e) in my fork of this repo
@chMoussa, does this feature need to be supported without using Embedding?
@chMoussa. The case without embedding will be: ``` import torch import pyqtorch as pyq from pyqtorch.utils import DiffMode from pyqtorch.embed import ConcretizedCallable x = torch.rand(1, requires_grad=True) sin_x_fn = pyq.ConcretizedCallable(call_name =...
Helo, @ayushb03. Can we add additional test cases for this pr?