Generative Adversarial Text to Image Synthesis

Overview

Text To Image Synthesis

This is a tensorflow implementation of synthesizing images. The images are synthesized using the GAN-CLS Algorithm from the paper Generative Adversarial Text-to-Image Synthesis. This implementation is built on top of the excellent DCGAN in Tensorflow.

Plese star https://github.com/tensorlayer/tensorlayer

Model architecture

Image Source : Generative Adversarial Text-to-Image Synthesis Paper

Requirements

Datasets

  • The model is currently trained on the flowers dataset. Download the images from here and save them in 102flowers/102flowers/*.jpg. Also download the captions from this link. Extract the archive, copy the text_c10 folder and paste it in 102flowers/text_c10/class_*.

N.B You can downloads all data files needed manually or simply run the downloads.py and put the correct files to the right directories.

python downloads.py

Codes

  • downloads.py download Oxford-102 flower dataset and caption files(run this first).
  • data_loader.py load data for further processing.
  • train_txt2im.py train a text to image model.
  • utils.py helper functions.
  • model.py models.

References

Results

  • the flower shown has yellow anther red pistil and bright red petals.
  • this flower has petals that are yellow, white and purple and has dark lines
  • the petals on this flower are white with a yellow center
  • this flower has a lot of small round pink petals.
  • this flower is orange in color, and has petals that are ruffled and rounded.
  • the flower has yellow petals and the center of it is brown
  • this flower has petals that are blue and white.
  • these white flowers have petals that start off white in color and end in a white towards the tips.

License

Apache 2.0

Comments
  • ValueError: Object arrays cannot be loaded when allow_pickle=False

    ValueError: Object arrays cannot be loaded when allow_pickle=False

    File "train_txt2im.py", line 458, in main_train() File "train_txt2im.py", line 133, in main_train load_and_assign_npz(sess=sess, name=net_rnn_name, model=net_rnn) File "train_txt2im.py", line 458, in main_train() File "train_txt2im.py", line 133, in main_train load_and_assign_npz(sess=sess, name=net_rnn_name, model=net_rnn) File "/home/siddanath/importantforprojects/text-to-image/utils.py", line 20, in load_and_assign_npz params = tl.files.load_npz(name=name) File "/home/siddanath/importantforprojects/text-to-image/tensorlayer/files.py", line 600, in load_npz return d['params'] File "/home/siddanath/anaconda3/lib/python3.7/site-packages/numpy/lib/npyio.py", line 262, in getitem pickle_kwargs=self.pickle_kwargs) File "/home/siddanath/anaconda3/lib/python3.7/site-packages/numpy/lib/format.py", line 722, in read_array raise ValueError("Object arrays cannot be loaded when " ValueError: Object arrays cannot be loaded when allow_pickle=False

    opened by Siddanth-pai 2
  • Attempt to have a second RNNCell use the weights of a variable scope that already has weights

    Attempt to have a second RNNCell use the weights of a variable scope that already has weights

    I got a problem, how can I solve it?

    Attempt to have a second RNNCell use the weights of a variable scope that already has weights: 'rnnftxt/rnn/dynamic/rnn/basic_lstm_cell'; and the cell was not constructed as BasicLSTMCell(..., reuse=True). To share the weights of an RNNCell, simply reuse it in your second calculation, or create a new one with the argument reuse=True.

    opened by flsd201983 1
  • Next step after download.py

    Next step after download.py

    What is the next step to do after download.py? I tried python data_loader.py, but it has FileNotFoundError: FileNotFoundError: [Errno 2] No such file or directory: '/home/ly/src/lib/text-to-image/102flowers/text_c10'

    opened by arisliang 0
  • ValueError: invalid literal for int() with base 10: 'e' - when making inference

    ValueError: invalid literal for int() with base 10: 'e' - when making inference

    code -

    sample_sentence = ["a"] * int(sample_size/ni) + ["e"] * int(sample_size/ni) + ["i"] * int(sample_size/ni) + ["o"] * int(sample_size/ni) + ["u"] * int(sample_size/ni)

    for i, sentence in enumerate(sample_sentence): print("seed: %s" % sentence) sentence = preprocess_caption(sentence) sample_sentence[i] = [vocab.word_to_id(word) for word in nltk.tokenize.word_tokenize( sentence)] + [vocab.end_id] # add END_ID

    sample_sentence = tl.prepro.pad_sequences(sample_sentence, padding='post')
    
    img_gen, rnn_out = sess.run([net_g_res.outputs, net_rnn_res.outputs], feed_dict={
        t_real_caption: sample_sentence,
        t_z: sample_seed})
    
    save_images(img_gen, [ni, ni], 'samples/gen_samples/gen.png')
    
    opened by Akinleyejoshua 0
  • Excuse me, why is the flower dataset I test the result is very different from result.png

    Excuse me, why is the flower dataset I test the result is very different from result.png

    import tensorflow as tf import tensorlayer as tl from tensorlayer.layers import * from tensorlayer.prepro import * from tensorlayer.cost import * import numpy as np import scipy from scipy.io import loadmat import time, os, re, nltk

    from utils import * from model import * import model import pickle

    ###======================== PREPARE DATA ====================================### print("Loading data from pickle ...") import pickle with open("_vocab.pickle", 'rb') as f: vocab = pickle.load(f) with open("_image_train.pickle", 'rb') as f: _, images_train = pickle.load(f) with open("_image_test.pickle", 'rb') as f: _, images_test = pickle.load(f) with open("_n.pickle", 'rb') as f: n_captions_train, n_captions_test, n_captions_per_image, n_images_train, n_images_test = pickle.load(f) with open("_caption.pickle", 'rb') as f: captions_ids_train, captions_ids_test = pickle.load(f)

    images_train_256 = np.array(images_train_256)

    images_test_256 = np.array(images_test_256)

    images_train = np.array(images_train) images_test = np.array(images_test)

    ni = int(np.ceil(np.sqrt(batch_size))) save_dir = "checkpoint"

    t_real_image = tf.placeholder('float32', [batch_size, image_size, image_size, 3], name = 'real_image')

    t_real_caption = tf.placeholder(dtype=tf.int64, shape=[batch_size, None], name='real_caption_input')

    t_z = tf.placeholder(tf.float32, [batch_size, z_dim], name='z_noise') generator_txt2img = model.generator_txt2img_resnet

    net_rnn = rnn_embed(t_real_caption, is_train=False, reuse=False) net_g, _ = generator_txt2img(t_z, net_rnn.outputs, is_train=False, reuse=False, batch_size=batch_size)

    sess = tf.Session(config=tf.ConfigProto(allow_soft_placement=True)) tl.layers.initialize_global_variables(sess)

    net_rnn_name = os.path.join(save_dir, 'net_rnn.npz400.npz') net_cnn_name = os.path.join(save_dir, 'net_cnn.npz400.npz') net_g_name = os.path.join(save_dir, 'net_g.npz400.npz') net_d_name = os.path.join(save_dir, 'net_d.npz400.npz')

    net_rnn_res = tl.files.load_and_assign_npz(sess=sess, name=net_rnn_name, network=net_rnn)

    net_g_res = tl.files.load_and_assign_npz(sess=sess, name=net_g_name, network=net_g)

    sample_size = batch_size sample_seed = np.random.normal(loc=0.0, scale=1.0, size=(sample_size, z_dim)).astype(np.float32)

    n = int(sample_size / ni) sample_sentence = ["the flower shown has yellow anther red pistil and bright red petals."] * n +
    ["this flower has petals that are yellow, white and purple and has dark lines"] * n +
    ["the petals on this flower are white with a yellow center"] * n +
    ["this flower has a lot of small round pink petals."] * n +
    ["this flower is orange in color, and has petals that are ruffled and rounded."] * n +
    ["the flower has yellow petals and the center of it is brown."] * n +
    ["this flower has petals that are blue and white."] * n +
    ["these white flowers have petals that start off white in color and end in a white towards the tips."] * n

    for i, sentence in enumerate(sample_sentence): print("seed: %s" % sentence) sentence = preprocess_caption(sentence) sample_sentence[i] = [vocab.word_to_id(word) for word in nltk.tokenize.word_tokenize(sentence)] + [vocab.end_id] # add END_ID

    sample_sentence = tl.prepro.pad_sequences(sample_sentence, padding='post')

    img_gen, rnn_out = sess.run([net_g_res.outputs, net_rnn_res.outputs], feed_dict={ t_real_caption : sample_sentence, t_z : sample_seed})

    save_images(img_gen, [ni, ni], 'samples/gen_samples/gen.png')

    opened by keqkeq 0
  • Tensorflow 2.1, Tensorlayer 2.2 update

    Tensorflow 2.1, Tensorlayer 2.2 update

    Hello,

    are there any plans in the near future to update this git to the latest Tensorflow and Tensorlayer versions? I've been trying making the code run with backwards compat (compat.tf1. ...) but I've keep bumping on errors which are a bit too big of mouth full for me.

    Fyi: I've succesfully run the DCGAN Tensorlayer implementation with Tensorlayer 2.2 and a self build Tensorflow 2.1 (with 3.0 compute compatibility) from source in Python 3.7.

    So, an update would be greatly appreciated!

    opened by SadRebel1000 0
Releases(0.2)
Owner
Hao
Assistant Professor @ Peking University
Hao
StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation Demo video: CVPR 2021 Oral: Single Channel Manipulation: Localized or attribu

Zongze Wu 267 Dec 30, 2022
The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

Deep High-Resolution Representation Learning for Human Pose Estimation (CVPR 2019) News [2020/07/05] A very nice blog from Towards Data Science introd

Leo Xiao 3.9k Jan 05, 2023
Pytorch Implementation of Interaction Networks for Learning about Objects, Relations and Physics

Interaction-Network-Pytorch Pytorch Implementraion of Interaction Networks for Learning about Objects, Relations and Physics. Interaction Network is a

117 Nov 05, 2022
An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise Weight Sharing) by Sensetime Research.

An integration of several popular automatic augmentation methods, including OHL (Online Hyper-Parameter Learning for Auto-Augmentation Strategy) and AWS (Improving Auto Augment via Augmentation Wise

45 Dec 08, 2022
CT-Net: Channel Tensorization Network for Video Classification

[ICLR2021] CT-Net: Channel Tensorization Network for Video Classification @inproceedings{ li2021ctnet, title={{\{}CT{\}}-Net: Channel Tensorization Ne

33 Nov 15, 2022
Code for paper Novel View Synthesis via Depth-guided Skip Connections

Novel View Synthesis via Depth-guided Skip Connections Code for paper Novel View Synthesis via Depth-guided Skip Connections @InProceedings{Hou_2021_W

8 Mar 14, 2022
Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(2021) paper

ImageNet-21K Pretraining for the Masses Paper | Pretrained models Official PyTorch Implementation Tal Ridnik, Emanuel Ben-Baruch, Asaf Noy, Lihi Zelni

574 Jan 02, 2023
VR Viewport Pose Model for Quantifying and Exploiting Frame Correlations

This repository contains the introduction to the collected VRViewportPose dataset and the code for the IEEE INFOCOM 2022 paper: "VR Viewport Pose Model for Quantifying and Exploiting Frame Correlatio

0 Aug 10, 2022
This repository is a series of notebooks that show solutions for the projects at Dataquest.io.

Dataquest Project Solutions This repository is a series of notebooks that show solutions for the projects at Dataquest.io. Of course, there are always

Dataquest 1.1k Dec 30, 2022
Compares various time-series feature sets on computational performance, within-set structure, and between-set relationships.

feature-set-comp Compares various time-series feature sets on computational performance, within-set structure, and between-set relationships. Reposito

Trent Henderson 7 May 25, 2022
Install alphafold on the local machine, get out of docker.

AlphaFold This package provides an implementation of the inference pipeline of AlphaFold v2.0. This is a completely new model that was entered in CASP

Kui Xu 73 Dec 13, 2022
WatermarkRemoval-WDNet-WACV2021

WatermarkRemoval-WDNet-WACV2021 Thank you for your attention. Citation Please cite the related works in your publications if it helps your research: @

LUYI 63 Dec 05, 2022
Py4fi2nd - Jupyter Notebooks and code for Python for Finance (2nd ed., O'Reilly) by Yves Hilpisch.

Python for Finance (2nd ed., O'Reilly) This repository provides all Python codes and Jupyter Notebooks of the book Python for Finance -- Mastering Dat

Yves Hilpisch 1k Jan 05, 2023
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

face.evoLVe: High-Performance Face Recognition Library based on PaddlePaddle & PyTorch Evolve to be more comprehensive, effective and efficient for fa

Zhao Jian 3.1k Jan 02, 2023
This script scrapes and stores the availability of timeslots for Car Driving Test at all RTA Serivce NSW centres in the state.

This script scrapes and stores the availability of timeslots for Car Driving Test at all RTA Serivce NSW centres in the state. Dependencies Account wi

Balamurugan Soundararaj 21 Dec 14, 2022
This repository contains the code for the paper in EMNLP 2021: "HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression".

HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression This repository contains the code for the paper in EM

Chenhe Dong 2 Mar 24, 2022
Code repo for EMNLP21 paper "Zero-Shot Information Extraction as a Unified Text-to-Triple Translation"

Zero-Shot Information Extraction as a Unified Text-to-Triple Translation Source code repo for paper Zero-Shot Information Extraction as a Unified Text

cgraywang 88 Dec 31, 2022
Campsite Reservation Finder

yellowstone-camping UPDATE: yellowstone-camping is being expanded and renamed to camply. The updated tool now interfaces with the Recreation.gov API a

Justin Flannery 233 Jan 08, 2023
classification task on dataset-CIFAR10,by using Tensorflow/keras

CIFAR10-Tensorflow classification task on dataset-CIFAR10,by using Tensorflow/keras 在这一个库中,我使用Tensorflow与keras框架搭建了几个卷积神经网络模型,针对CIFAR10数据集进行了训练与测试。分别使

3 Oct 17, 2021
This repo is to be freely used by ML devs to check the GAN performances without coding from scratch.

GANs for Fun Created because I can! GOAL The goal of this repo is to be freely used by ML devs to check the GAN performances without coding from scrat

Sagnik Roy 13 Jan 26, 2022