Olivia comments

Results 9 comments of


                                            Olivia

AttributeError: Cannot convert ConvTranspose2d with output_padding != 0

Any updates on this? Thanks in advance.

QAT (quantization aware training) Support quantizing models recursively

Any tips on quantizing the Pix2Pix generator? I've used [this official tutorial](https://www.tensorflow.org/tutorials/generative/pix2pix) as a guide, and have attempted the following to no avail: ``` def downsample(filters, size, apply_batchnorm=True): initializer =...

QAT (quantization aware training) Support quantizing models recursively

Thanks for the quick response! That doesn't throw an error, but it doesn't look like it quantizes the layers created within the `upsample` and `downsample` functions. Is there any way...

QAT (quantization aware training) Support quantizing models recursively

I did manage to get that working for me with some additional layers in the _apply_quantization_ function (I'm still learning here!). But, I receive the following error, I think due...

QAT (quantization aware training) Support quantizing models recursively

Wonderful! Thanks again!

Attempt to add hyper-phunk theme

Who gives a ** about an oxford comma?? 😉

ONNX Conversion fails due to unsupported ops: LinSpace and MatrixInverse

Hi @chiragsamal -- thanks for sharing your code! Did you ultimately figure out how to register your custom linspace op? I'm hoping to do the same thing and exporting with...

compilation terminated

I managed to get the install to succeed with Pytorch 1.10 (which requires Python

pipenv injects secrets into Pipfile and lock file

I can confirm that installation of a private package with an environment var works: ``` export GH_PAT=some-secret-token pipenv install https://${GH_PAT}@github.com/user/repo.git#egg=foo ``` However, the un-masked variable is written both to stdout...