-
Dear Ling-Pan,
I am writing to request an update to the OMAR benchmark code to include implementation for the discrete action space. Despite our best efforts, we have been unable to locate the nece…
-
Hi
Thank you for your amazing work
As mentioned that the code is build on the GroupViT repo, I see grouping block is same as what is coined as slot attention here. Is there any difference betwee…
-
TFD: https://www.tensorflow.org/probability/oryx/api_docs/python/oryx/distributions/RelaxedOneHotCategorical
-
do I see it correctly that the code fragments provided by OpenAI and the way you binded it in the vae.py file means that there is no actual codebook in the form of an explicit nn.Paramter or nn.Embedd…
-
**Describe the bug:**
The updated RotaryEncoder implementation introduced in [this PR](https://github.com/facebookresearch/fairseq2/pull/66) changes the dtype of `freqs` to `torch.complex64`. However…
-
In your work, discrete variables are implemented in latent variables. May I ask whether this method is feasible for discrete variables to be directly used as network output?
-
These functions can be found in [`mindspore.ops`](https://jax.readthedocs.io/en/latest/jax.numpy.html) namespace.
\_
>Please keep in mind that the proper way to link an issue to this list is t…
-
作者您好,请问您是复现出了VP2P-Match这项工作吗
-
I understand from #258 that there is randomness in the generated VQGAN code sequences because of Gumbel Softmax, but the different sequences nevertheless reconstruct to similar looking images. However…
-
Hi @YongfeiYan, thanks for sharing your project with us.
I would like to know how do I modify the implementation to use Bernoulli variables. I need the network to generate codes consisting of 0s an…