guided-diffusion

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

This repository is based on openai/improved-diffusion, with modifications for classifier conditioning and architecture improvements.

Usage

Training diffusion models is described in the parent repository. Training a classifier is similar. We assume you have put training hyperparameters into a TRAIN_FLAGS variable, and classifier hyperparameters into a CLASSIFIER_FLAGS variable. Then you can run:

mpiexec -n N python scripts/classifier_train.py --data_dir path/to/imagenet $TRAIN_FLAGS $CLASSIFIER_FLAGS

Make sure to divide the batch size in TRAIN_FLAGS by the number of MPI processes you are using.

Here are flags for training the 128x128 classifier. You can modify these for training classifiers at other resolutions:

TRAIN_FLAGS="--iterations 300000 --anneal_lr True --batch_size 256 --lr 3e-4 --save_interval 10000 --weight_decay 0.05"
CLASSIFIER_FLAGS="--image_size 128 --classifier_attention_resolutions 32,16,8 --classifier_depth 2 --classifier_width 128 --classifier_pool attention --classifier_resblock_updown True --classifier_use_scale_shift_norm True"

For sampling from a 128x128 classifier-guided model, 25 step DDIM:

MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond True --image_size 128 --learn_sigma True --num_channels 256 --num_heads 4 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
CLASSIFIER_FLAGS="--image_size 128 --classifier_attention_resolutions 32,16,8 --classifier_depth 2 --classifier_width 128 --classifier_pool attention --classifier_resblock_updown True --classifier_use_scale_shift_norm True --classifier_scale 1.0 --classifier_use_fp16 True"
SAMPLE_FLAGS="--batch_size 4 --num_samples 50000 --timestep_respacing ddim25 --use_ddim True"
mpiexec -n N python scripts/classifier_sample.py \
    --model_path /path/to/model.pt \
    --classifier_path path/to/classifier.pt \
    $MODEL_FLAGS $CLASSIFIER_FLAGS $SAMPLE_FLAGS

To sample for 250 timesteps without DDIM, replace --timestep_respacing ddim25 to --timestep_respacing 250, and replace --use_ddim True with --use_ddim False.

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

Related tags

Overview

guided-diffusion

Usage

Owner

OpenAI

This is the source code for generating the ASL-Skeleton3D and ASL-Phono datasets. Check out the README.md for more details.

PIXIE: Collaborative Regression of Expressive Bodies

DeceFL: A Principled Decentralized Federated Learning Framework

The codes and related files to reproduce the results for Image Similarity Challenge Track 1.

Unsupervised Image Generation with Infinite Generative Adversarial Networks

Code accompanying the paper on "An Empirical Investigation of Domain Generalization with Empirical Risk Minimizers" published at NeurIPS, 2021

Implementations for the ICLR-2021 paper: SEED: Self-supervised Distillation For Visual Representation.

A developer interface for creating Chat AIs for the Chai app.

Learning Continuous Signed Distance Functions for Shape Representation

Surrogate-Assisted Genetic Algorithm for Wrapper Feature Selection

Keras Image Embeddings using Contrastive Loss

Transformer part of 12th place solution in Riiid! Answer Correctness Prediction

Cours d'Algorithmique Appliquée avec Python pour BTS SIO SISR

An open source implementation of CLIP.

Finite-temperature variational Monte Carlo calculation of uniform electron gas using neural canonical transformation.

Improving the robustness and performance of biomedical NLP models through adversarial training

A module for solving and visualizing Schrödinger equation.

Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch

Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical analysis and state-of-the-art performance.