kk

Results 19 issues of kk

Now I have a number of images stored in numpy file. I want to use FLIF to compress them losslessly and count the length? Does this library provide API to...

question

I find that in the training and testing phase, the dataset is standardized as a whole batch, including computing the mean and variance in a per channel style. However, when...

I clone the repository and run cifar10 densenet. The accuracy reaches 87% at epoch 150 and does not increase anymore. I don't know why. Should I change some hyperparameters?

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...

My cpu support avx and avx2, but not avx512f. I build tensorflow myself. And tensorflow works well, but tensorboard still report the following error: 2019-02-04 07:39:40.286677: F tensorflow/core/platform/cpu_feature_guard.cc:37] The TensorFlow...

awaiting reply

I find that in the training and testing phase, the dataset is standardized as a whole batch, including computing the mean and variance from the entire cifar10 dataset. However, when...

In the top layer, the prior distribution here use h=conv(0) + embedding as the mean and std in the case of 'ycond=True'. It seems that the conv layer is unnecessary.

Hi, I am trying Glow on my computer. But it is too gpu hungry. Could you please upload pretrained model on CelebA 32x32? Thanks a lot!

I have an issue with the PropagateOnto strategy. If I use the default PropagateOver strategy, my typestate code works well. But when using PropagateOnto strategy, some dataflow facts vanish after...

bug

In `LLVMModuleSet::buildSVFModule`, `extapi.bc` is inserted before the real main module. So `LLVMModuleSet::getLLVMModuleSet()->getMainLLVMModule()` returns `extapi.bc`.