All Projects → makora9143 → pytorch-convcnp

makora9143 / pytorch-convcnp

Licence: other
A PyTorch Implementation of Convolutional Conditional Neural Process.

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to pytorch-convcnp

Restoring-Extremely-Dark-Images-In-Real-Time
The project is the official implementation of our CVPR 2021 paper, "Restoring Extremely Dark Images in Real Time"
Stars: ✭ 79 (+92.68%)
Mutual labels:  pytorch-implementation
Pytorch Vae
A Collection of Variational Autoencoders (VAE) in PyTorch.
Stars: ✭ 2,704 (+6495.12%)
Mutual labels:  pytorch-implementation
TransMorph Transformer for Medical Image Registration
TransMorph: Transformer for Unsupervised Medical Image Registration (PyTorch)
Stars: ✭ 130 (+217.07%)
Mutual labels:  bayesian-deep-learning
pytorch-serving
[UNMAINTAINED] A starter pack for creating a lightweight responsive web app for Fast.AI PyTorch models.
Stars: ✭ 16 (-60.98%)
Mutual labels:  pytorch-implementation
Pytorch Seq2seq
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
Stars: ✭ 3,418 (+8236.59%)
Mutual labels:  pytorch-implementation
Dropout BBalpha
Implementations of the ICML 2017 paper (with Yarin Gal)
Stars: ✭ 40 (-2.44%)
Mutual labels:  bayesian-deep-learning
lowshot-shapebias
Learning low-shot object classification with explicit shape bias learned from point clouds
Stars: ✭ 37 (-9.76%)
Mutual labels:  pytorch-implementation
ocbnn-public
General purpose library for BNNs, and implementation of OC-BNNs in our 2020 NeurIPS paper.
Stars: ✭ 31 (-24.39%)
Mutual labels:  bayesian-deep-learning
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+7651.22%)
Mutual labels:  pytorch-implementation
DUN
Code for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)
Stars: ✭ 65 (+58.54%)
Mutual labels:  bayesian-deep-learning
neural-question-generation
Pytorch implementation of Paragraph-level Neural Question Generation with Maxout Pointer and Gated Self-attention Networks
Stars: ✭ 126 (+207.32%)
Mutual labels:  pytorch-implementation
saliency
Pytorch Implementation of the paper - "Tidying Deep Saliency Prediction Architectures"
Stars: ✭ 27 (-34.15%)
Mutual labels:  pytorch-implementation
deep-weight-prior
The Deep Weight Prior, ICLR 2019
Stars: ✭ 42 (+2.44%)
Mutual labels:  bayesian-deep-learning
subjectiveqe-esrgan
PyTorch implementation of ESRGAN (ECCVW 2018) for compressed image subjective quality enhancement.
Stars: ✭ 12 (-70.73%)
Mutual labels:  pytorch-implementation
CADA
Attending to Discriminative Certainty for Domain Adaptation
Stars: ✭ 17 (-58.54%)
Mutual labels:  bayesian-deep-learning
abae-pytorch
PyTorch implementation of 'An Unsupervised Neural Attention Model for Aspect Extraction' by He et al. ACL2017'
Stars: ✭ 52 (+26.83%)
Mutual labels:  pytorch-implementation
spatial-smoothing
(ICML 2022) Official PyTorch implementation of “Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness”.
Stars: ✭ 68 (+65.85%)
Mutual labels:  bayesian-deep-learning
SuperNNova
Open Source Photometric classification https://supernnova.readthedocs.io
Stars: ✭ 18 (-56.1%)
Mutual labels:  bayesian-deep-learning
INFO320
Neural Networks and Bayesian Learning
Stars: ✭ 24 (-41.46%)
Mutual labels:  bayesian-deep-learning
Structured-Bayesian-Pruning-pytorch
pytorch implementation of Structured Bayesian Pruning
Stars: ✭ 18 (-56.1%)
Mutual labels:  bayesian-deep-learning

ConvCNP: Convolutional Conditional Neural Process, in PyTorch

A PyTorch implementation of Convolutional Conditional Neural Process from the 2019 paper (arXiv, ICLR2020) by Jonathan Gordon, Wessel P. Bruinsma, Andrew Y. K. Foong, James Requeima, Yann Dubois, and Richard E. Turner.

(The original code is not published as of 2019/12/28)

Table of Contents

Dependencies

  1. Python 3.7+
  2. PyTorch 1.3
  3. GPyTorch 1.0
  4. Numpy 1.16+
  5. Scikit-learn 0.21
  6. Fastprogress 0.1.21

Datasets

1D Regression

We provide several kernels to generate datasets for syntethic 1D regression:

  • EQ Kernel
  • Matern-5/2 Kernel
  • Periodic Kernel

2D Regression

  • MNIST
  • CIFAR10

Train

1D Regression

$ python main1d.py --kernel [eq | matern | periodic]

2D Regression

$ python main2d.py --dataset [mnist | cifar10] # Highly recommend to run this code in your GPU environment!

Demonstration

CIFAR10 Prediction

If you want some more demo (1D reg.), please see our jupyter notebooks.

Reference

  • Jonathan Gordon et al. "Convolutional Conditional Neural Processes" ICLR2020 (accepted)
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].