A PyTorch implementation of the paper "Semantic Image Synthesis via Adversarial Learning" in ICCV 2017

Last update: Nov 25, 2022

Related tags

Deep Learning dong_iccv_2017

Overview

Semantic Image Synthesis via Adversarial Learning

This is a PyTorch implementation of the paper Semantic Image Synthesis via Adversarial Learning.

Requirements

PyTorch 0.2
Torchvision
Pillow
fastText.py (Note: if you have a problem when loading a pretrained model, try my fixed code)
NLTK

Pretrained word vectors for fastText

Download a pretrained English word vectors. You can see the list of pretrained vectors on this page.

Datasets

Oxford-102 flowers: images and captions
Caltech-200 birds: images and captions

The caption data is from this repository. After downloading, modify CONFIG file so that all paths of the datasets point to the data you downloaded.

Run

scripts/train_text_embedding_[birds/flowers].sh
Train a visual-semantic embedding model using the method of Kiros et al..
scripts/train_[birds/flowers].sh
Train a GAN using a pretrained text embedding model.
scripts/test_[birds/flowers].sh
Generate some examples using original images and semantically relevant texts.

Results

Acknowledgements

We would like to thank Hao Dong, who is one of the first authors of the paper Semantic Image Synthesis via Adversarial Learning, for providing helpful advice for the implementation.

A PyTorch implementation of the paper "Semantic Image Synthesis via Adversarial Learning" in ICCV 2017

Related tags

Overview

Semantic Image Synthesis via Adversarial Learning

Requirements

Pretrained word vectors for fastText

Datasets

Run

Results

Acknowledgements

Owner

Seonghyeon Nam

An original implementation of "Noisy Channel Language Model Prompting for Few-Shot Text Classification"

Aydin is a user-friendly, feature-rich, and fast image denoising tool

Codebase for the paper titled "Continual learning with local module selection"

DRLib：A concise deep reinforcement learning library, integrating HER and PER for almost off policy RL algos.

TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision

A python library for time-series smoothing and outlier detection in a vectorized way.

An optimization and data collection toolbox for convenient and fast prototyping of computationally expensive models.

CUDA Python Low-level Bindings

[Arxiv preprint] Causality-inspired Single-source Domain Generalization for Medical Image Segmentation (code&data-processing pipeline)

This is a tensorflow-based rotation detection benchmark, also called AlphaRotate.

Codes and Data Processing Files for our paper.

Nested cross-validation is necessary to avoid biased model performance in embedded feature selection in high-dimensional data with tiny sample sizes

Sign Language is detected in realtime using video sequences. Our approach involves MediaPipe Holistic for keypoints extraction and LSTM Model for prediction.

Code for Graph-to-Tree Learning for Solving Math Word Problems (ACL 2020)

Bayesian Generative Adversarial Networks in Tensorflow

Train a state-of-the-art yolov3 object detector from scratch!

Tensorflow Implementation of Pixel Transposed Convolutional Networks (PixelTCN and PixelTCL)

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

Simulating an AI playing 2048 using the Expectimax algorithm

StarGAN v2-Tensorflow - Simple Tensorflow implementation of StarGAN v2