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

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning

This repository contains code from the paper "TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network"

Membership Inference Attack against Graph Neural Networks

Reinforcement Learning with Q-Learning Algorithm on gym's frozen lake environment implemented in python

PyTorch implementation of Wide Residual Networks with 1-bit weights by McDonnell (ICLR 2018)

This repository contains the exercises and its solution contained in the book "An Introduction to Statistical Learning" in python.

MixRNet(Using mixup as regularization and tuning hyper-parameters for ResNets)

Code to train models from "Paraphrastic Representations at Scale".

This is the official implementation for the paper "Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization" in NeurIPS 2021.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

Image Completion with Deep Learning in TensorFlow

Awesome Weak-Shot Learning

MAU: A Motion-Aware Unit for Video Prediction and Beyond, NeurIPS2021

Towards Flexible Blind JPEG Artifacts Removal (FBCNN, ICCV 2021)

💛 Code and Dataset for our EMNLP 2021 paper: "Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion Causes"

Black-Box-Tuning - Black-Box Tuning for Language-Model-as-a-Service

Project NII pytorch scripts

A library for low-memory inferencing in PyTorch.

Simple-System-Convert--C--F - Simple System Convert With Python