• Stars
    star
    986
  • Rank 46,429 (Top 1.0 %)
  • Language
    Python
  • License
    MIT License
  • Created over 5 years ago
  • Updated almost 4 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.

PyTorch pretrained BigGAN

An op-for-op PyTorch reimplementation of DeepMind's BigGAN model with the pre-trained weights from DeepMind.

Introduction

This repository contains an op-for-op PyTorch reimplementation of DeepMind's BigGAN that was released with the paper Large Scale GAN Training for High Fidelity Natural Image Synthesis by Andrew Brock, Jeff Donahue and Karen Simonyan.

This PyTorch implementation of BigGAN is provided with the pretrained 128x128, 256x256 and 512x512 models by DeepMind. We also provide the scripts used to download and convert these models from the TensorFlow Hub models.

This reimplementation was done from the raw computation graph of the Tensorflow version and behave similarly to the TensorFlow version (variance of the output difference of the order of 1e-5).

This implementation currently only contains the generator as the weights of the discriminator were not released (although the structure of the discriminator is very similar to the generator so it could be added pretty easily. Tell me if you want to do a PR on that, I would be happy to help.)

Installation

This repo was tested on Python 3.6 and PyTorch 1.0.1

PyTorch pretrained BigGAN can be installed from pip as follows:

pip install pytorch-pretrained-biggan

If you simply want to play with the GAN this should be enough.

If you want to use the conversion scripts and the imagenet utilities, additional requirements are needed, in particular TensorFlow and NLTK. To install all the requirements please use the full_requirements.txt file:

git clone https://github.com/huggingface/pytorch-pretrained-BigGAN.git
cd pytorch-pretrained-BigGAN
pip install -r full_requirements.txt

Models

This repository provide direct and simple access to the pretrained "deep" versions of BigGAN for 128, 256 and 512 pixels resolutions as described in the associated publication. Here are some details on the models:

  • BigGAN-deep-128: a 50.4M parameters model generating 128x128 pixels images, the model dump weights 201 MB,
  • BigGAN-deep-256: a 55.9M parameters model generating 256x256 pixels images, the model dump weights 224 MB,
  • BigGAN-deep-512: a 56.2M parameters model generating 512x512 pixels images, the model dump weights 225 MB.

Please refer to Appendix B of the paper for details on the architectures.

All models comprise pre-computed batch norm statistics for 51 truncation values between 0 and 1 (see Appendix C.1 in the paper for details).

Usage

Here is a quick-start example using BigGAN with a pre-trained model.

See the doc section below for details on these classes and methods.

import torch
from pytorch_pretrained_biggan import (BigGAN, one_hot_from_names, truncated_noise_sample,
                                       save_as_images, display_in_terminal)

# OPTIONAL: if you want to have more information on what's happening, activate the logger as follows
import logging
logging.basicConfig(level=logging.INFO)

# Load pre-trained model tokenizer (vocabulary)
model = BigGAN.from_pretrained('biggan-deep-256')

# Prepare a input
truncation = 0.4
class_vector = one_hot_from_names(['soap bubble', 'coffee', 'mushroom'], batch_size=3)
noise_vector = truncated_noise_sample(truncation=truncation, batch_size=3)

# All in tensors
noise_vector = torch.from_numpy(noise_vector)
class_vector = torch.from_numpy(class_vector)

# If you have a GPU, put everything on cuda
noise_vector = noise_vector.to('cuda')
class_vector = class_vector.to('cuda')
model.to('cuda')

# Generate an image
with torch.no_grad():
    output = model(noise_vector, class_vector, truncation)

# If you have a GPU put back on CPU
output = output.to('cpu')

# If you have a sixtel compatible terminal you can display the images in the terminal
# (see https://github.com/saitoha/libsixel for details)
display_in_terminal(output)

# Save results as png images
save_as_images(output)

output_0 output_1 output_2

Doc

Loading DeepMind's pre-trained weights

To load one of DeepMind's pre-trained models, instantiate a BigGAN model with from_pretrained() as:

model = BigGAN.from_pretrained(PRE_TRAINED_MODEL_NAME_OR_PATH, cache_dir=None)

where

  • PRE_TRAINED_MODEL_NAME_OR_PATH is either:

    • the shortcut name of a Google AI's or OpenAI's pre-trained model selected in the list:

      • biggan-deep-128: 12-layer, 768-hidden, 12-heads, 110M parameters
      • biggan-deep-256: 24-layer, 1024-hidden, 16-heads, 340M parameters
      • biggan-deep-512: 12-layer, 768-hidden, 12-heads , 110M parameters
    • a path or url to a pretrained model archive containing:

      • config.json: a configuration file for the model, and
      • pytorch_model.bin a PyTorch dump of a pre-trained instance of BigGAN (saved with the usual torch.save()).

    If PRE_TRAINED_MODEL_NAME_OR_PATH is a shortcut name, the pre-trained weights will be downloaded from AWS S3 (see the links here) and stored in a cache folder to avoid future download (the cache folder can be found at ~/.pytorch_pretrained_biggan/).

  • cache_dir can be an optional path to a specific directory to download and cache the pre-trained model weights.

Configuration

BigGANConfig is a class to store and load BigGAN configurations. It's defined in config.py.

Here are some details on the attributes:

  • output_dim: output resolution of the GAN (128, 256 or 512) for the pre-trained models,
  • z_dim: size of the noise vector (128 for the pre-trained models).
  • class_embed_dim: size of the class embedding vectors (128 for the pre-trained models).
  • channel_width: size of each channel (128 for the pre-trained models).
  • num_classes: number of classes in the training dataset, like imagenet (1000 for the pre-trained models).
  • layers: A list of layers definition. Each definition for a layer is a triple of [up-sample in the layer ? (bool), number of input channels (int), number of output channels (int)]
  • attention_layer_position: Position of the self-attention layer in the layer hierarchy (8 for the pre-trained models).
  • eps: epsilon value to use for spectral and batch normalization layers (1e-4 for the pre-trained models).
  • n_stats: number of pre-computed statistics for the batch normalization layers associated to various truncation values between 0 and 1 (51 for the pre-trained models).

Model

BigGAN is a PyTorch model (torch.nn.Module) of BigGAN defined in model.py. This model comprises the class embeddings (a linear layer) and the generator with a series of convolutions and conditional batch norms. The discriminator is currently not implemented since pre-trained weights have not been released for it.

The inputs and output are identical to the TensorFlow model inputs and outputs.

We detail them here.

BigGAN takes as inputs:

  • z: a torch.FloatTensor of shape [batch_size, config.z_dim] with noise sampled from a truncated normal distribution, and
  • class_label: an optional torch.LongTensor of shape [batch_size, sequence_length] with the token types indices selected in [0, 1]. Type 0 corresponds to a sentence A and type 1 corresponds to a sentence B token (see BERT paper for more details).
  • truncation: a float between 0 (not comprised) and 1. The truncation of the truncated normal used for creating the noise vector. This truncation value is used to selecte between a set of pre-computed statistics (means and variances) for the batch norm layers.

BigGAN outputs an array of shape [batch_size, 3, resolution, resolution] where resolution is 128, 256 or 512 depending of the model:

Utilities: Images, Noise, Imagenet classes

We provide a few utility method to use the model. They are defined in utils.py.

Here are some details on these methods:

  • truncated_noise_sample(batch_size=1, dim_z=128, truncation=1., seed=None):

    Create a truncated noise vector.

    • Params:
      • batch_size: batch size.
      • dim_z: dimension of z
      • truncation: truncation value to use
      • seed: seed for the random generator
    • Output: array of shape (batch_size, dim_z)
  • convert_to_images(obj):

    Convert an output tensor from BigGAN in a list of images.

    • Params:
      • obj: tensor or numpy array of shape (batch_size, channels, height, width)
    • Output:
      • list of Pillow Images of size (height, width)
  • save_as_images(obj, file_name='output'):

    Convert and save an output tensor from BigGAN in a list of saved images.

    • Params:
      • obj: tensor or numpy array of shape (batch_size, channels, height, width)
      • file_name: path and beggingin of filename to save. Images will be saved as file_name_{image_number}.png
  • display_in_terminal(obj):

    Convert and display an output tensor from BigGAN in the terminal. This function use libsixel and will only work in a libsixel-compatible terminal. Please refer to https://github.com/saitoha/libsixel for more details.

    • Params:
      • obj: tensor or numpy array of shape (batch_size, channels, height, width)
      • file_name: path and beggingin of filename to save. Images will be saved as file_name_{image_number}.png
  • one_hot_from_int(int_or_list, batch_size=1):

    Create a one-hot vector from a class index or a list of class indices.

    • Params:
      • int_or_list: int, or list of int, of the imagenet classes (between 0 and 999)
      • batch_size: batch size.
        • If int_or_list is an int create a batch of identical classes.
        • If int_or_list is a list, we should have len(int_or_list) == batch_size
    • Output:
      • array of shape (batch_size, 1000)
  • one_hot_from_names(class_name, batch_size=1):

    Create a one-hot vector from the name of an imagenet class ('tennis ball', 'daisy', ...). We use NLTK's wordnet search to try to find the relevant synset of ImageNet and take the first one. If we can't find it direcly, we look at the hyponyms and hypernyms of the class name.

    • Params:
      • class_name: string containing the name of an imagenet object.
    • Output:
      • array of shape (batch_size, 1000)

Download and conversion scripts

Scripts to download and convert the TensorFlow models from TensorFlow Hub are provided in ./scripts.

The scripts can be used directly as:

./scripts/download_tf_hub_models.sh
./scripts/convert_tf_hub_models.sh

More Repositories

1

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Python
133,705
star
2

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Python
28,073
star
3

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Python
25,619
star
4

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
Python
17,530
star
5

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python
15,663
star
6

candle

Minimalist ML framework for Rust
Rust
15,011
star
7

trl

Train transformer language models with reinforcement learning.
Python
9,850
star
8

text-generation-inference

Large Language Model Text Generation Inference
Python
8,939
star
9

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
Rust
8,885
star
10

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Python
7,854
star
11

chat-ui

Open source codebase powering the HuggingChat app
TypeScript
7,113
star
12

lerobot

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Python
6,522
star
13

alignment-handbook

Robust recipes to align language models with human and AI preferences
Python
4,474
star
14

parler-tts

Inference and training library for high-quality TTS models.
Python
4,027
star
15

autotrain-advanced

🤗 AutoTrain Advanced
Python
3,925
star
16

deep-rl-class

This repo contains the syllabus of the Hugging Face Deep Reinforcement Learning Course.
MDX
3,680
star
17

diffusion-models-class

Materials for the Hugging Face Diffusion Models Course
Jupyter Notebook
3,508
star
18

notebooks

Notebooks using the Hugging Face libraries 🤗
Jupyter Notebook
3,492
star
19

distil-whisper

Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
Python
3,455
star
20

neuralcoref

✨Fast Coreference Resolution in spaCy with Neural Networks
C
2,842
star
21

safetensors

Simple, safe way to store and distribute tensors
Python
2,754
star
22

text-embeddings-inference

A blazing fast inference solution for text embeddings models
Rust
2,746
star
23

knockknock

🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code
Python
2,682
star
24

speech-to-speech

Speech To Speech: an effort for an open-sourced and modular GPT4-o
Python
2,540
star
25

swift-coreml-diffusers

Swift app demonstrating Core ML Stable Diffusion
Swift
2,506
star
26

optimum

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools
Python
2,469
star
27

blog

Public repo for HF blog posts
Jupyter Notebook
2,303
star
28

setfit

Efficient few-shot learning with Sentence Transformers
Jupyter Notebook
2,142
star
29

course

The Hugging Face course on Transformers
MDX
2,005
star
30

awesome-papers

Papers & presentation materials from Hugging Face's internal science day
1,996
star
31

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Python
1,909
star
32

evaluate

🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
Python
1,825
star
33

cookbook

Open-source AI cookbook
Jupyter Notebook
1,660
star
34

transfer-learning-conv-ai

🦄 State-of-the-Art Conversational AI with Transfer Learning
Python
1,654
star
35

swift-coreml-transformers

Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!
Swift
1,543
star
36

pytorch-openai-transformer-lm

🐥A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI
Python
1,464
star
37

huggingface.js

Utilities to use the Hugging Face Hub API
TypeScript
1,368
star
38

Mongoku

🔥The Web-scale GUI for MongoDB
TypeScript
1,313
star
39

huggingface_hub

All the open source things related to the Hugging Face Hub.
Python
1,311
star
40

gsplat.js

JavaScript Gaussian Splatting library.
TypeScript
1,302
star
41

llm-vscode

LLM powered development for VSCode
TypeScript
1,206
star
42

hmtl

🌊HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP
Python
1,185
star
43

nanotron

Minimalistic large language model 3D-parallelism training
Python
1,071
star
44

optimum-nvidia

Python
888
star
45

torchMoji

😇A pyTorch implementation of the DeepMoji model: state-of-the-art deep learning model for analyzing sentiment, emotion, sarcasm etc
Python
880
star
46

awesome-huggingface

🤗 A list of wonderful open-source projects & applications integrated with Hugging Face libraries.
853
star
47

optimum-quanto

A pytorch quantization backend for optimum
Python
738
star
48

llm.nvim

LLM powered development for Neovim
Lua
728
star
49

naacl_transfer_learning_tutorial

Repository of code for the tutorial on Transfer Learning in NLP held at NAACL 2019 in Minneapolis, MN, USA
Python
718
star
50

dataset-viewer

Backend that powers the dataset viewer on Hugging Face dataset pages through a public API.
Python
689
star
51

swift-transformers

Swift Package to implement a transformers-like API in Swift
Swift
647
star
52

exporters

Export Hugging Face models to Core ML and TensorFlow Lite
Python
587
star
53

llm-ls

LSP server leveraging LLMs for code completion (and more?)
Rust
586
star
54

ratchet

A cross-platform browser ML framework.
Rust
574
star
55

transformers-bloom-inference

Fast Inference Solutions for BLOOM
Python
557
star
56

lighteval

LightEval is a lightweight LLM evaluation suite that Hugging Face has been using internally with the recently released LLM data processing library datatrove and LLM training library nanotron.
Python
554
star
57

pytorch_block_sparse

Fast Block Sparse Matrices for Pytorch
C++
523
star
58

node-question-answering

Fast and production-ready question answering in Node.js
TypeScript
459
star
59

large_language_model_training_playbook

An open collection of implementation tips, tricks and resources for training large language models
Python
452
star
60

swift-chat

Mac app to demonstrate swift-transformers
Swift
444
star
61

llm_training_handbook

An open collection of methodologies to help with successful training of large language models.
Python
437
star
62

text-clustering

Easily embed, cluster and semantically label text datasets
Python
422
star
63

cosmopedia

Python
416
star
64

optimum-intel

🤗 Optimum Intel: Accelerate inference with Intel optimization tools
Jupyter Notebook
393
star
65

controlnet_aux

Python
386
star
66

community-events

Place where folks can contribute to 🤗 community events
Jupyter Notebook
368
star
67

tflite-android-transformers

DistilBERT / GPT-2 for on-device inference thanks to TensorFlow Lite with Android demo apps
Java
368
star
68

nn_pruning

Prune a model while finetuning or training.
Jupyter Notebook
360
star
69

speechbox

Python
341
star
70

100-times-faster-nlp

🚀100 Times Faster Natural Language Processing in Python - iPython notebook
HTML
325
star
71

education-toolkit

Educational materials for universities
Jupyter Notebook
324
star
72

transformers.js-examples

A collection of 🤗 Transformers.js demos and example applications
JavaScript
323
star
73

open-muse

Open reproduction of MUSE for fast text2image generation.
Python
320
star
74

local-gemma

Gemma 2 optimized for your local machine.
Python
317
star
75

unity-api

C#
313
star
76

audio-transformers-course

The Hugging Face Course on Transformers for Audio
MDX
308
star
77

datablations

Scaling Data-Constrained Language Models
Jupyter Notebook
305
star
78

hf_transfer

Rust
287
star
79

dataspeech

Python
262
star
80

huggingface-llama-recipes

Jupyter Notebook
259
star
81

optimum-benchmark

🏋️ A unified multi-backend utility for benchmarking Transformers, Timm, PEFT, Diffusers and Sentence-Transformers with full support of Optimum's hardware optimizations & quantization schemes.
Python
245
star
82

diarizers

Python
238
star
83

hub-docs

Docs of the Hugging Face Hub
221
star
84

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters
Python
216
star
85

sam2-studio

Swift
196
star
86

optimum-neuron

Easy, fast and very cheap training and inference on AWS Trainium and Inferentia chips.
Jupyter Notebook
193
star
87

data-is-better-together

Let's build better datasets, together!
Jupyter Notebook
192
star
88

instruction-tuned-sd

Code for instruction-tuning Stable Diffusion.
Python
189
star
89

simulate

🎢 Creating and sharing simulation environments for embodied and synthetic data research
Python
185
star
90

OBELICS

Code used for the creation of OBELICS, an open, massive and curated collection of interleaved image-text web documents, containing 141M documents, 115B text tokens and 353M images.
Python
184
star
91

diffusion-fast

Faster generation with text-to-image diffusion models.
Python
179
star
92

olm-datasets

Pipeline for pulling and processing online language model pretraining data from the web
Python
173
star
93

api-inference-community

Python
161
star
94

jat

General multi-task deep RL Agent
Python
154
star
95

workshops

Materials for workshops on the Hugging Face ecosystem
Jupyter Notebook
148
star
96

coreml-examples

Swift Core ML Examples
Jupyter Notebook
147
star
97

optimum-habana

Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)
Python
147
star
98

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.
Python
140
star
99

sharp-transformers

A Unity plugin for using Transformers models in Unity.
C#
139
star
100

hf-hub

Rust client for the huggingface hub aiming for minimal subset of features over `huggingface-hub` python package
Rust
132
star