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

STYLER: Style Factor Modeling with Rapidity and Robustness via Speech Decomposition for Expressive and Controllable Neural Text to Speech

Robotics environments

MaRS - a recursive filtering framework that allows for truly modular multi-sensor integration

Topic Discovery via Latent Space Clustering of Pretrained Language Model Representations

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation.

Author: Wenhao Yu ([email protected]). ACL 2022. Commonsense Reasoning on Knowledge Graph for Text Generation

Point-NeRF: Point-based Neural Radiance Fields

Learning Logic Rules for Document-Level Relation Extraction

CTF challenges and write-ups for MicroCTF 2021.

Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)

PyTorch implementation of ARM-Net: Adaptive Relation Modeling Network for Structured Data.

Supervised forecasting of sequential data in Python.

PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

JFB: Jacobian-Free Backpropagation for Implicit Models

An Open-Source Tool for Automatic Disease Diagnosis..

Deep motion transfer

Facilitates implementing deep neural-network backbones, data augmentations

Implementations of CNNs, RNNs, GANs, etc

IMBENS: class-imbalanced ensemble learning in Python.

A computational optimization project towards the goal of gerrymandering the results of a hypothetical election in the UK.