Codebase for Diffusion Models Beat GANS on Image Synthesis.

Related tags

Deep Learningguided-diffusion
Overview

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.

Download pre-trained models

We have released checkpoints for the main models in the paper. Before using these models, please review the corresponding model card to understand the intended use and limitations of these models.

Here are the download links for each model checkpoint:

Sampling from pre-trained models

To sample from these models, you can use the classifier_sample.py, image_sample.py, and super_res_sample.py scripts. Here, we provide flags for sampling from all of these models. We assume that you have downloaded the relevant model checkpoints into a folder called models/.

For these examples, we will generate 100 samples with batch size 4. Feel free to change these values.

SAMPLE_FLAGS="--batch_size 4 --num_samples 100 --timestep_respacing 250"

Classifier guidance

Note for these sampling runs that you can set --classifier_scale 0 to sample from the base diffusion model. You may also use the image_sample.py script instead of classifier_sample.py in that case.

  • 64x64 model:
MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond True --diffusion_steps 1000 --dropout 0.1 --image_size 64 --learn_sigma True --noise_schedule cosine --num_channels 192 --num_head_channels 64 --num_res_blocks 3 --resblock_updown True --use_new_attention_order True --use_fp16 True --use_scale_shift_norm True"
python classifier_sample.py $MODEL_FLAGS --classifier_scale 1.0 --classifier_path models/64x64_classifier.pt --model_path models/64x64_diffusion.pt $SAMPLE_FLAGS
  • 128x128 model:
MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond True --diffusion_steps 1000 --image_size 128 --learn_sigma True --noise_schedule linear --num_channels 256 --num_heads 4 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
python classifier_sample.py $MODEL_FLAGS --classifier_scale 0.5 --classifier_path models/128x128_classifier.pt --model_path models/128x128_diffusion.pt $SAMPLE_FLAGS
  • 256x256 model:
MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond True --diffusion_steps 1000 --image_size 256 --learn_sigma True --noise_schedule linear --num_channels 256 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
python classifier_sample.py $MODEL_FLAGS --classifier_scale 1.0 --classifier_path models/256x256_classifier.pt --model_path models/256x256_diffusion.pt $SAMPLE_FLAGS
  • 256x256 model (unconditional):
MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond False --diffusion_steps 1000 --image_size 256 --learn_sigma True --noise_schedule linear --num_channels 256 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
python classifier_sample.py $MODEL_FLAGS --classifier_scale 10.0 --classifier_path models/256x256_classifier.pt --model_path models/256x256_diffusion.pt $SAMPLE_FLAGS
  • 512x512 model:
MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond True --diffusion_steps 1000 --image_size 512 --learn_sigma True --noise_schedule linear --num_channels 256 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 False --use_scale_shift_norm True"
python classifier_sample.py $MODEL_FLAGS --classifier_scale 4.0 --classifier_path models/512x512_classifier.pt --model_path models/512x512_diffusion.pt $SAMPLE_FLAGS

Upsampling

For these runs, we assume you have some base samples in a file 64_samples.npz or 128_samples.npz for the two respective models.

  • 64 -> 256:
MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond True --diffusion_steps 1000 --large_size 256  --small_size 64 --learn_sigma True --noise_schedule linear --num_channels 192 --num_heads 4 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
python super_res_sample.py $MODEL_FLAGS --model_path models/64_256_upsampler.pt --base_samples 64_samples.npz $SAMPLE_FLAGS
  • 128 -> 512:
MODEL_FLAGS="--attention_resolutions 32,16 --class_cond True --diffusion_steps 1000 --large_size 512 --small_size 128 --learn_sigma True --noise_schedule linear --num_channels 192 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
python super_res_sample.py $MODEL_FLAGS --model_path models/128_512_upsampler.pt $SAMPLE_FLAGS --base_samples 128_samples.npz

LSUN models

These models are class-unconditional and correspond to a single LSUN class. Here, we show how to sample from lsun_bedroom.pt, but the other two LSUN checkpoints should work as well:

MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond False --diffusion_steps 1000 --dropout 0.1 --image_size 256 --learn_sigma True --noise_schedule linear --num_channels 256 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
python image_sample.py $MODEL_FLAGS --model_path models/lsun_bedroom.pt $SAMPLE_FLAGS

You can sample from lsun_horse_nodropout.pt by changing the dropout flag:

MODEL_FLAGS="--attention_resolutions 32,16,8 --class_cond False --diffusion_steps 1000 --dropout 0.0 --image_size 256 --learn_sigma True --noise_schedule linear --num_channels 256 --num_head_channels 64 --num_res_blocks 2 --resblock_updown True --use_fp16 True --use_scale_shift_norm True"
python image_sample.py $MODEL_FLAGS --model_path models/lsun_horse_nodropout.pt $SAMPLE_FLAGS

Note that for these models, the best samples result from using 1000 timesteps:

SAMPLE_FLAGS="--batch_size 4 --num_samples 100 --timestep_respacing 1000"

Results

This table summarizes our ImageNet results for pure guided diffusion models:

Dataset FID Precision Recall
ImageNet 64x64 2.07 0.74 0.63
ImageNet 128x128 2.97 0.78 0.59
ImageNet 256x256 4.59 0.82 0.52
ImageNet 512x512 7.72 0.87 0.42

This table shows the best results for high resolutions when using upsampling and guidance together:

Dataset FID Precision Recall
ImageNet 256x256 3.94 0.83 0.53
ImageNet 512x512 3.85 0.84 0.53

Finally, here are the unguided results on individual LSUN classes:

Dataset FID Precision Recall
LSUN Bedroom 1.90 0.66 0.51
LSUN Cat 5.57 0.63 0.52
LSUN Horse 2.57 0.71 0.55

Training models

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.

Owner
Katherine Crowson
AI/generative artist.
Katherine Crowson
GitHub Repository
Malware Env for OpenAI Gym

Malware Env for OpenAI Gym Citing If you use this code in a publication please cite the following paper: Hyrum S. Anderson, Anant Kharkar, Bobby Fila

ENDGAME 563 Dec 29, 2022
This's an implementation of deepmind Visual Interaction Networks paper using pytorch

Visual-Interaction-Networks An implementation of Deepmind visual interaction networks in Pytorch. Introduction For the purpose of understanding the ch

Mahmoud Gamal Salem 166 Dec 06, 2022
Procedural 3D data generation pipeline for architecture

Synthetic Dataset Generator Authors: Stanislava Fedorova Alberto Tono Meher Shashwat Nigam Jiayao Zhang Amirhossein Ahmadnia Cecilia bolognesi Dominik

Computational Design Institute 49 Nov 25, 2022
[NeurIPS 2021] "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators"

G-PATE This is the official code base for our NeurIPS 2021 paper: "G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of T

AI Secure 14 Oct 12, 2022
PyTorch implementation of paper A Fast Knowledge Distillation Framework for Visual Recognition.

FKD: A Fast Knowledge Distillation Framework for Visual Recognition Official PyTorch implementation of paper A Fast Knowledge Distillation Framework f

Zhiqiang Shen 129 Dec 24, 2022
Python PID Tuner - Makes a model of the System from a Process Reaction Curve and calculates PID Gains

PythonPID_Tuner_SOPDT Step 1: Takes a Process Reaction Curve in csv format - assumes data at 100ms interval (column names CV and PV) Step 2: Makes a r

1 Jan 18, 2022
My coursework for Machine Learning (2021 Spring) at National Taiwan University (NTU)

Machine Learning 2021 Machine Learning (NTU EE 5184, Spring 2021) Instructor: Hung-yi Lee Course Website : (https://speech.ee.ntu.edu.tw/~hylee/ml/202

100 Dec 26, 2022
Official implementation of Monocular Quasi-Dense 3D Object Tracking

Monocular Quasi-Dense 3D Object Tracking Monocular Quasi-Dense 3D Object Tracking (QD-3DT) is an online framework detects and tracks objects in 3D usi

Visual Intelligence and Systems Group 441 Dec 20, 2022
DTCN SMP Challenge - Sequential prediction learning framework and algorithm

DTCN This is the implementation of our paper "Sequential Prediction of Social Me

Bobby 2 Jan 24, 2022
a practicable framework used in Deep Learning. So far UDL only provide DCFNet implementation for the ICCV paper (Dynamic Cross Feature Fusion for Remote Sensing Pansharpening)

UDL UDL is a practicable framework used in Deep Learning (computer vision). Benchmark codes, results and models are available in UDL, please contact @

Xiao Wu 11 Sep 30, 2022
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation

[ICCV2021] TransReID: Transformer-based Object Re-Identification [pdf] The official repository for TransReID: Transformer-based Object Re-Identificati

DamoCV 569 Dec 30, 2022
Learning Logic Rules for Document-Level Relation Extraction

LogiRE Learning Logic Rules for Document-Level Relation Extraction We propose to introduce logic rules to tackle the challenges of doc-level RE. Equip

41 Dec 26, 2022
Codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing

Contrast and Mix (CoMix) The repository contains the codes for the paper Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Backgroun

Computer Vision and Intelligence Research (CVIR) 13 Dec 10, 2022
Unofficial implementation of Google "CutPaste: Self-Supervised Learning for Anomaly Detection and Localization" in PyTorch

CutPaste CutPaste: image from paper Unofficial implementation of Google's "CutPaste: Self-Supervised Learning for Anomaly Detection and Localization"

Lilit Yolyan 59 Nov 27, 2022
Transformers provides thousands of pretrained models to perform tasks on different modalities such as text, vision, and audio.

English | 简体中文 | 繁體中文 | 한국어 State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow 🤗 Transformers provides thousands of pretrained models

Clara Meister 50 Nov 12, 2022
When in Doubt: Improving Classification Performance with Alternating Normalization

When in Doubt: Improving Classification Performance with Alternating Normalization Findings of EMNLP 2021 Menglin Jia, Austin Reiter, Ser-Nam Lim, Yoa

Menglin Jia 13 Nov 06, 2022
A New Approach to Overgenerating and Scoring Abstractive Summaries

We provide the source code for the paper "A New Approach to Overgenerating and Scoring Abstractive Summaries" accepted at NAACL'21. If you find the code useful, please cite the following paper.

Kaiqiang Song 4 Apr 03, 2022
Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'

Re-implementation of the paper 'Grokking: Generalization beyond overfitting on small algorithmic datasets' Paper Original paper can be found here Data

Tom Lieberum 38 Aug 09, 2022
Official Pytorch implementation of MixMo framework

MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks Official PyTorch implementation of the MixMo framework | paper | docs Alexandr

79 Nov 07, 2022
QTool: A Low-bit Quantization Toolbox for Deep Neural Networks in Computer Vision

This project provides abundant choices of quantization strategies (such as the quantization algorithms, training schedules and empirical tricks) for quantizing the deep neural networks into low-bit c

Monash Green AI Lab 51 Dec 10, 2022