Konpat comments

Results 61 comments of


                                            Konpat

Linking of bin/vizdoom fails

I have a similar problem with this during `pip install vizdoom`. (with anaconda) The error was: ``` /home/ta/anaconda3/lib/libharfbuzz.so.0: undefined reference to `FT_Done_MM_Var' /home/ta/anaconda3/lib/libharfbuzz.so.0: undefined reference to `FT_Get_Var_Blend_Coordinates' ``` It is...

Uncaught Exception: Cannot read property "moeditorWindow" of null

I already mentioned the version number to be 0.2.0. So, if it is to be the latest it is the latest. By the way, I can simply solve this problem...

AttributeError: 'CIFAR10' object has no attribute 'num_inputs'

+1 happened to me as well.

Nice work! About "Predictive power of the semantic subcode".

We didn't plan to release it at first. I'm now reconsidering it. I'll try to make time for this. Hang tight!

no dconditional dim model for ffhq 256?

Could you please clarify the question?

reconstruct blur/noise image

DiffAE has a part that does denoising, of course, like any other diffusion model, but it's not designed specifically to do this. Turning a noisy image into a clean image...

socket.error: [Errno 99] Cannot assign requested address

@Jane333 Addition to that, I can also use `--ip=*`

socket.error: [Errno 99] Cannot assign requested address

@EvgeniaAR honestly, no idea - -" you might need to dig deeper to what "address" it is trying to allocate.

How many epochs required for training?

Your understanding is correct. Note that the number of "samples" here is comparable to other DDPM on the same dataset. Maybe, the number of epochs is not interpreted the same...

Training autoenc and Training latent DDM

They are not trained at the same time. You can train the autoencoder alone with only images (and you will only get the autoencoder). Since it is still an autoencoder,...