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

EMNLP 2021 paper The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers.

In this project, we develop a face recognize platform based on MTCNN object-detection netcwork and FaceNet self-supervised network.

Happywhale - Whale and Dolphin Identification Silver🥈 Solution (26/1588)

Official pytorch implementation of "Scaling-up Disentanglement for Image Translation", ICCV 2021.

Certified Patch Robustness via Smoothed Vision Transformers

Calibrated Hyperspectral Image Reconstruction via Graph-based Self-Tuning Network.

classify fashion-mnist dataset with pytorch

Implementation of ML models like Decision tree, Naive Bayes, Logistic Regression and many other

LabelImg is a graphical image annotation tool.

Class-Attentive Diffusion Network for Semi-Supervised Classification [AAAI'21] (official implementation)

Parasite: a tool allowing you to compress and decompress files, to reduce their size

A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning

Kaggle-titanic - A tutorial for Kaggle's Titanic: Machine Learning from Disaster competition. Demonstrates basic data munging, analysis, and visualization techniques. Shows examples of supervised machine learning techniques.

A clean and robust Pytorch implementation of PPO on continuous action space.

A TensorFlow implementation of DeepMind's WaveNet paper

La source de mon module 'pyfade' disponible sur Pypi.

Look Who’s Talking: Active Speaker Detection in the Wild

Neuralnetwork - Basic Multilayer Perceptron Neural Network for deep learning

The code is an implementation of Feedback Convolutional Neural Network for Visual Localization and Segmentation.

This is a collection of our NAS and Vision Transformer work.