-
## 一言でいうと
離散潜在表現を学習するVQ-VAEを利用して音楽生成を行った研究。VQ-VAE-2のように潜在表現を階層状にしているが(音声の圧縮度に応じたEncoderを用意)、各階層の表現が壊れないよう全結合して出力せず個別のDecoderをでそれぞれ復元・学習する。歌詞とAttentionで対応付けた学習も行っている。
, last revised 25 Feb 2018 (this version, v7)
TMats updated
6 years ago
-
Pose your (and uprank 5 others') questions here for [Ashton Anderson](https://www.cs.toronto.edu/~ashton/) about his 2024 ICLR paper ["Designing Skill-Compatible AI: Methodologies and Frameworks in Ch…
-
# Simple AI-Chatbot
This is very easy to build and deploy generative chatbot that makes use of of streamlit for ui and is based on python. It uses the API calling method to invoke the llm and can b…
-
Hi, I'm trying to train examples using the configurations in `configs/example_training`.
When I use yaml files such as imagenet-f8_cond.yaml or txt2img-clipl.yaml, there are no issues.
However, wh…
-
## Goal
The goal of this issue is to lockdown how we want `EpiAware` to ingest observed data, especially in light of #107 .
## Current API
The data `y_t` is an argument to `make_epi_aware` co…
-
### Version
latest
### On which installation method(s) does this occur?
_No response_
### Describe the issue
See log output below
### Minimum reproducible example
_No response_
### Relevant lo…
-
For now im running in python 3.10.9 since thats what the community has been running in the past and iv had no reason to update, and it could break things.
XFormers is saying that it cant load becau…
-
whenever context is passed to a block like in:
h, res_samples = downsample_block(hidden_states=h, temb=emb, context=context)
the forward function uses "del context"
so it is not really impleme…
-
After using this in a project, I've found that the following additional properties would be helpful to have in the structured declaration.
| Property | Value …