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

LeetCode Solutions https://t.me/tenvlad

NAACL2021 - COIL Contextualized Lexical Retriever

unet-family: Ultimate version

Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)

Source code release of the paper: Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation.

Repository aimed at compiling code, papers, demos etc.. related to my PhD on 3D vision and machine learning for fruit detection and shape estimation at the university of Lincoln

Parametric Contrastive Learning (ICCV2021)

The Submission for SIMMC 2.0 Challenge 2021

DeepFaceLab fork which provides IPython Notebook to use DFL with Google Colab

Narya API allows you track soccer player from camera inputs, and evaluate them with an Expected Discounted Goal (EDG) Agent

Torch-mutable-modules - Use in-place and assignment operations on PyTorch module parameters with support for autograd

Multi-Scale Aligned Distillation for Low-Resolution Detection (CVPR2021)

Using PyTorch Perform intent classification using three different models to see which one is better for this task

Social Fabric: Tubelet Compositions for Video Relation Detection

[CVPR2021 Oral] UP-DETR: Unsupervised Pre-training for Object Detection with Transformers

Flaxformer: transformer architectures in JAX/Flax

BitPack is a practical tool to efficiently save ultra-low precision/mixed-precision quantized models.

This repository is the code of the paper "Sparse Spatial Transformers for Few-Shot Learning".

[NeurIPS 2021] A weak-shot object detection approach by transferring semantic similarity and mask prior.

Face Synthetics dataset is a collection of diverse synthetic face images with ground truth labels.