glow

glow copied to clipboard

Hi, I have a problem with the 'Loading of the model' part. Here is the error I get when I load this part : _____________________________________________________________________________________________ [](https://3eo8rxxq085-496ff2e9c6d22116-0-colab.googleusercontent.com/outputframe.html?vrz=colab-20220407-060047-RC00_440068893#) in () 96 #...

EAdnds

After I run get_manipulators, I get z_manipulate.npy in shape (40,196608). 196608 means 3*256*256. But I am handling with image of size 3*64*64 = , how can I change z_manipulate.npy to...

viettmab

No matching distribution found for tensorflow-gpu==1.8.0

4

Can't seem to install the requirements - I'm on a mac with CUDA supported GPU, CUDA toolkit, and python 3.5 / 3.7 64 bit architecture (tried both versions) . I...

heaversm

mpiexec hangs on creating pad

1

Hi, quick issue with mpiexec. Without it the program runs fine with 1 gpu (am running Horovod within a Docker container), but mpiexec hangs whenever it's invoked. I ran a...

0xymoro

I find difference between local loss in the download logs (about 3.05 in cifar10) and best result (3.35 in cifar10) in your paper , can anyone explain the diffenence between...

LHB116

Can not download pretrained models, logs and samples

3

Hi, I tried to get the Pretrained models, logs and samples with the following command `wget https://storage.googleapis.com/glow-demo/logs/abl-[reverse/shuffle/1x1]-[add/aff].tar` but I get the following error. Could someone please help me with this?...

mkhoshle

Model producing blank images with dataset of 128x128 or larger images

10

Hello, I have tried training several 256x256 datasets with the Glow model using hyperparameter configurations as similar to the CelebA configuration that your team used, and all I'm getting are...

dpmcgonigle

tensorflow.python.framework.errors_impl.NotFoundError: Key Variable_4633 not found in checkpoint

1

I'm using Tensorflow v1.10 (update : I've also tried on v1.8 and v1.13)and I've been trying to figure out how to use the pre-trained model for testing, but no matter...

Megapotatosan

Which part is encoder ,and which part is decoder?

1

In your paper，which is part belong to encoder, and which part belong to decoder? Is the final 'squeeze + step of flow ' the decoder of Glow? Any help will...

Gpwner

Calculation of scale term

8

Hi guys, In the paper in Table 1, you specify that the NN learns the log of the scale, and thus the scale is calculated as `s = exp(log s)`....

meowcakes