glow
glow copied to clipboard
Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"
Welcome to [WhiteSource for GitHub.com](https://github.com/apps/whitesource-for-github-com)! This is an onboarding PR to help you understand and configure settings before WhiteSource starts scanning your repository for security vulnerabilities. :vertical_traffic_light: WhiteSource for GitHub.com...
Bumps [tensorflow-gpu](https://github.com/tensorflow/tensorflow) from 1.8.0 to 2.3.1. Release notes Sourced from tensorflow-gpu's releases. TensorFlow 2.3.1 Release 2.3.1 Bug Fixes and Other Changes Fixes an undefined behavior causing a segfault in tf.raw_ops.Switch...
I am trying to train a GLOW mapping on a custom dataset. However while training, I frequently receive a `tensorflow.python.framework.errors_impl.InvalidArgumentError: Input is not invertible` error. Upon seeing the logs, I...
I tried to use MS-COCO dataset for training. After i serialize the MS-COCO image using ``` img = tf.gfile.FastGFile(img_path, 'rb').read() or img = open(img_path, 'rb').read() ``` and save tfrecords, i...
I can i train glow model with my custom dataset (actually, i want to train the model on MS-COCO). Is anybody who has tried to use her/his own dataset?
The flow based model is very very interesting. But it is too GPU hungry. I see that some pretrained models are uploaded. Now I have a question about the pretrained...
Hi, When training with CUDA_VISIBLE_DEVICES="0,1,2" mpiexec -n 3 python3 train.py --data_dir celeba-tfr --problem 'celeba' on 3GPUs I get the following warning: **[[51353,1],1]: A high-performance Open MPI point-to-point messaging module was...
Hi!guys, when i run `pip install -r requirements.txt` The following error : Building wheels for collected packages: horovod Building wheel for horovod (setup.py) ... error ERROR: Command errored out with...
I`m downloading dataset files but it takes long time. Could you upload pretrained model files?
https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/tfops.py#L256 In this line of code, after conv2d, another actnorm is used. I'm not quite clear why logdet is not computed for this actnorm, this actnorm also changed the distribution...