Vector quantized image modeling with improved vqgan
- In “ Vector-Quantized Image Modeling with Improved VQGAN ”, we propose a two-stage model that reconceives traditional image quantization techniques to yield improved performance on image generation and image understanding tasks. In the first stage, an image quantization model, called VQGAN, encodes an image into lower-dimensional discrete ...Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including unconditional, class-conditioned image generation and unsupervised representation learning. When trained on ImageNet at 256x256 resolution, we achieve Inception Score (IS) of 175.1 and Fr'echet Inception Distance (FID) of 4.17, a dramatic improvement over ...Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively. The... used cars for dollar6000ramsey county recorder Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...论文标题：《Vector-Quantized Image Modeling with Improved VQGAN》—— ICLR 2022 作者信息：Jiahui Yu等 Google Research 这篇论文提出了VQGAN这样的模型不仅可以应用在图像生成中，其预训练模型还可以通过微调迁移到图像分类等任务中去。1 code implementation • 29 May 2023 • Zi Wang , Alexander Ku , Jason Baldridge , Thomas L. Griffiths , Been Kim. Our experiments show it can (1) probe a model's representations of concepts even with a very small number of examples, (2) accurately measure both epistemic uncertainty (how confident the probe is) and aleatory uncertainty (how ...We describe multiple improvements to the image quantizer and show that training a stronger image quantizer is a key component for improving both image generation and image understanding. Vector-Quantized Image Modeling with ViT-VQGAN One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ... boylestraat 15 17 jpghughes and coleman injury lawyers Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Vector-quantized Image Modeling with Improved VQGAN Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alex Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu ICLR 2022 / Google AI Blog. SimVLM: Simple Visual Language Model Pretraining with Weak Supervision Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, Yuan Cao default We describe multiple improvements to the image quantizer and show that training a stronger image quantizer is a key component for improving both image generation and image understanding. Vector-Quantized Image Modeling with ViT-VQGAN One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational ... check mark symbol powerpoint macmakai harrower But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Posted by Jiahui Yu, Senior Research Scientist, and Jing Yu Koh, Research Software Engineer, Google Research In recent years, natural language processing models have dramatically improved their ability to learn general-purpose representations, which has resulted in significant performance gains for a wide range of natural language generation and natural language understanding tasks. In large ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ... does lowe But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ... filippo testa balmain The discrete image tokens are encoded from a learned Vision-Transformer-based VQGAN (ViT-VQGAN). We first propose multiple improvements over vanilla VQGAN from architecture to codebook learning, yielding better efficiency and reconstruction fidelity. The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including ...The Vector-Quantized (VQ) codebook is first introduced in VQVAE , which aims to learn discrete priors to encode images. The following work VQGAN proposes a perceptual codebook by further using perceptual loss and adversarial training objectives . We briefly describe the VQGAN model with its codebook in this section, and more details can be ...Vector-quantized Image Modeling with Improved VQGAN. Pretraining language models with next-token prediction on massive text corpora has delivered phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on both generative and discriminative language tasks.Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis. Vector -Quantized (VQ-based) generative models usually consist of two basic components, i.e., VQ tokenizers and generative transformers. Prior research focuses on improving the reconstruction fidelity of VQ tokenizers but rarely examines how the improvement in ...Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively. The discrete image tokens are encoded from a learned Vision-Transformer-based VQGAN (ViT-VQGAN). megane lopez Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Vector-quantized Image Modeling with Improved VQGAN Yu, Jiahui ; Li, Xin ; Koh, Jing Yu ; Zhang, Han ; Pang, Ruoming ; Qin, James ; Ku, Alexander ; Xu, Yuanzhongand Yonghui Wu. Vector-quantized image modeling with improved vqgan. arXiv preprint arXiv:2110.04627, 2021.3 [10]Chuanxia Zheng, Long Tung Vuong, Jianfei Cai, and Dinh Phung. Movq: Modulating quantized vectors for high-fidelity image generation.arXiv preprint arXiv:2209.09002, 2022.3 Vector-Quantized Image Modeling with ViT-VQGAN One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Posted by Jiahui Yu, Senior Research Scientist, and Jing Yu Koh, Research Software Engineer, Google Research In recent years, natural language processing models have dramatically improved their ability to learn general-purpose representations, which has resulted in significant performance gains for a wide range of natural language generation and natural language understanding tasks. In large ... gandh garbageappellate courts let Oct 9, 2021 · The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including unconditional, class-conditioned image generation and unsupervised representation learning. When trained on ImageNet at 256x256 resolution, we achieve Inception Score (IS) of 175.1 and Fr'echet Inception Distance (FID) of 4.17, a dramatic improvement over ... But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Vector-quantized Image Modeling with Improved VQGAN Yu, Jiahui ; Li, Xin ; Koh, Jing Yu ; Zhang, Han ; Pang, Ruoming ; Qin, James ; Ku, Alexander ; Xu, YuanzhongThis strategy can naturally tap into the rich body of prior work on large language models, which have seen continued advances in capabilities and performance through scaling data and model sizes. Our approach is simple: First, Parti uses a Transformer-based image tokenizer, ViT-VQGAN, to encode images as sequences of discrete tokens.But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Vector-Quantized Image Modeling with Improved VQGAN may 17, 2022 ... Image-Text Pre-training with Contrastive Captioners ... Vector-Quantized Image Modeling with ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ... seamless thong victoria But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...A vector quantization library originally transcribed from Deepmind's tensorflow implementation, made conveniently into a package. It uses exponential moving averages to update the dictionary. VQ has been successfully used by Deepmind and OpenAI for high quality generation of images (VQ-VAE-2) and music (Jukebox). Vector-quantized image modeling with improved vqgan J Yu, X Li, JY Koh, H Zhang, R Pang, J Qin, A Ku, Y Xu, J Baldridge, Y Wu The Tenth International Conference on Learning Representations , 2021Vector-quantized image modeling with improved VQGAN, Oct 2021. This paper uses a 2-stage approach. This first stage uses a Vision transformer-based VQGAN for discrete codebook learning. The second state is an autoregressive transformer whose input is represented by stage 1 encoding.But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ... smz 69 Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization techniques to yield improved performance on image generation and image understanding tasks.and Yonghui Wu. Vector-quantized image modeling with improved vqgan. arXiv preprint arXiv:2110.04627, 2021.3 [10]Chuanxia Zheng, Long Tung Vuong, Jianfei Cai, and Dinh Phung. Movq: Modulating quantized vectors for high-fidelity image generation.arXiv preprint arXiv:2209.09002, 2022.3 swannypercent27s comp gear But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...arXiv.org e-Print archiveImage-Text Pre-training with Contrastive Captioners ... 2022 Vector-Quantized Image Modeling with Improved VQGAN مئی 17, 2022 Contextual Rephrasing in Google ...Image-Text Pre-training with Contrastive Captioners ... 2022 Vector-Quantized Image Modeling with Improved VQGAN مئی 17, 2022 Contextual Rephrasing in Google ...Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing ... percocet 5 325halo 2percent2b collar Vector-quantized Image Modeling with Improved VQGAN Yu, Jiahui ; Li, Xin ; Koh, Jing Yu ; Zhang, Han ; Pang, Ruoming ; Qin, James ; Ku, Alexander ; Xu, YuanzhongVector-quantized Image Modeling with Improved VQGAN Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alex Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu ICLR 2022 / Google AI Blog. SimVLM: Simple Visual Language Model Pretraining with Weak Supervision Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, Yuan CaoBut while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ... prime wheel mexico Overview of the proposed ViT-VQGAN (left) and VIM (right), which, when working together, is capable of both image generation and image understanding…But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...“Vector-Quantized Image Modeling with Improved VQGAN” proposes a two-stage model that reinvents classic image quantization methods to produce better picture generation and image understanding tasks. The first step is to encode an image into discrete latent codes of lesser dimensions using an image quantization model called VQGAN.Image encoders compress an image into smaller dimensions, sometimes even quantized into a discrete space (such as the VQGAN from taming-transformers used in Craiyon). In this article, we try to reproduce the results from ViT-VQGAN (" Vector-quantized Image Modeling with Improved VQGAN ") and experiment with further adaptations. industrial lumber and plywood A vector quantization library originally transcribed from Deepmind's tensorflow implementation, made conveniently into a package. It uses exponential moving averages to update the dictionary. VQ has been successfully used by Deepmind and OpenAI for high quality generation of images (VQ-VAE-2) and music (Jukebox).此篇 ViT-VQGAN 為 VQ-GAN 的改良版本，沒看過的人可以看 The AI Epiphany 介紹的 VQ-GAN 和 VQ-VAE，這種類型的方法主要是要得到一個好的 quantizer，而 VQ-VAE 是透過 CNN-based 的 auto-encoder 把 latent space 變成類似像 dictionary 的 codebook (discrete…Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.We propose Vector-quantized Image Modeling (VIM), which pretrains a Transformer to predict image tokens autoregressively, where discrete image tokens are produced from improved ViT-VQGAN image quantizers. With our proposed improvements on image quantization, we demonstrate superior results on both image generation and understanding. peg 40 hydrogenated castor oilwomenpercent27s ufc fights Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end. install arXiv.org e-Print archiveMotivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively. The discrete image tokens are encoded from a learned Vision-Transformer-based VQGAN (ViT-VQGAN). We first propose multiple improvements over vanilla VQGAN from ...Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.The Vector-Quantized (VQ) codebook is first introduced in VQVAE , which aims to learn discrete priors to encode images. The following work VQGAN proposes a perceptual codebook by further using perceptual loss and adversarial training objectives . We briefly describe the VQGAN model with its codebook in this section, and more details can be ... thepercent20officepercent20bag But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end. pueblo community craigslist Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively. The discrete image tokens are encoded from a learned Vision-Transformer-based VQGAN (ViT-VQGAN). We first propose multiple improvements over vanilla VQGAN from ... microtech utx 70 amazon arXiv.org e-Print archiveVector-Quantized Image Modeling with ViT-VQGAN One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end. VQGAN is an improved version of this that introduces an ...The release weight of ViT-VQGAN small which is trained on ImageNet at here; 16/08. First release weight of ViT-VQGAN base which is trained on ImageNet at here; Add an colab notebook at here; About The Project. This is an unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch. ViT-VQGAN is a simple ViT-based Vector Quantized ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end. sony str dh790 earc updateu haul charleston south carolina But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ... what is the phone number for victoria The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including unconditional, class-conditioned image generation and unsupervised representation learning. When trained on ImageNet at 256x256 resolution, we achieve Inception Score (IS) of 175.1 and Fr'echet Inception Distance (FID) of 4.17, a dramatic improvement over ...The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including unconditional, class-conditioned image generation and unsupervised representation learning. When trained on ImageNet at 256x256 resolution, we achieve Inception Score (IS) of 175.1 and Fr'echet Inception Distance (FID) of 4.17, a dramatic improvement over ... default Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.We first propose multiple improvements over vanilla VQGAN from architecture to codebook learning, yielding better efficiency and reconstruction fidelity. The improved ViT-VQGAN further improves vector-quantized image modeling tasks, including unconditional, class-conditioned image generation and unsupervised representation learning.Vector-quantized Image Modeling with Improved VQGAN Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu ICLR 2022. BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers Zhiliang Peng, Li Dong, Hangbo Bao, Qixiang Ye, Furu Wei arXiv 2022.VQ-Diffusion. Vector Quantized Diffusion (VQ-Diffusion) is a conditional latent diffusion model developed by the University of Science and Technology of China and Microsoft. Unlike most commonly studied diffusion models, VQ-Diffusion's noising and denoising processes operate on a quantized latent space, i.e., the latent space is composed of a ...In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization techniques to yield improved performance on image generation and image understanding tasks. gregory b levett and sons funeral homes and crematory obituaries Vector-Quantized Image Modeling with ViT-VQGAN One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end. VQGAN is an improved version of this that introduces an ...But while such models have achieved strong performance for image generation, few studies have evaluated the learned representation for downstream discriminative tasks (such as image classification). In “Vector-Quantized Image Modeling with Improved VQGAN”, we propose a two-stage model that reconceives traditional image quantization ...This strategy can naturally tap into the rich body of prior work on large language models, which have seen continued advances in capabilities and performance through scaling data and model sizes. Our approach is simple: First, Parti uses a Transformer-based image tokenizer, ViT-VQGAN, to encode images as sequences of discrete tokens.Vector-Quantized Image Modeling with ViT-VQGAN. One recent, commonly used model that quantizes images into integer tokens is the Vector-quantized Variational AutoEncoder (VQVAE), a CNN-based auto-encoder whose latent space is a matrix of discrete learnable variables, trained end-to-end.