The research of virtual face based on Deep Convolutional Generative Adversarial Networks using TensorFlow

Abstract Since Generative Adversarial Nets (GANs) has been proposed in 2014, it has become one of the most popular hot topics. Deep Convolutional Generative Adversarial Networks (DCGAN) is greatly promoted the development and application of GANs. In this paper, we have made an in-depth exploration for the most popular DCGAN at present via utilizing TensorFlow deep learning framework, using the open CelebA face dataset of The Chinese University of Hong Kong as the data source. By comparing DCGAN unconstrained and DCGAN constrained, the experimental results show that the DCGAN model significantly improves the virtual face generation model after adding constraints in the training phase, which enhance the ability of the generator to deceive the discriminator. Finally, we have evaluated the proposed model from the perspective of TensorBoard and achieved the desired experimental results.

[1]  Frédéric Jurie,et al.  An Adversarial Regularisation for Semi-Supervised Training of Structured Output Neural Networks , 2017, NIPS 2017.

[2]  Anmin Mao,et al.  Kirchhoff type problems in RN with radial potentials and locally Lipschitz functional , 2016, Appl. Math. Lett..

[3]  Jianwen Feng,et al.  Event-triggered communication for synchronization of Markovian jump delayed complex networks with partially unknown transition rates , 2017, Appl. Math. Comput..

[4]  Wen Tan,et al.  On the pullback attractor for the non-autonomous SIR equations with diffusion ☆ , 2017 .

[5]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[6]  Zhi-Min Chen,et al.  Equilibrium states of the Charney-DeVore quasi-geostrophic equation in mid-latitude atmosphere , 2016 .

[7]  Hengcai Tang,et al.  Quantitative versions of the joint distributions of Hecke eigenvalues , 2016 .

[8]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[9]  Minh N. Do,et al.  Semantic Image Inpainting with Perceptual and Contextual Losses , 2016, ArXiv.

[10]  Qiang Liu,et al.  EXISTENCE OF WEAK SOLUTIONS FOR SOME SINGULAR PARABOLIC EQUATION , 2016 .

[11]  Peirong Xu,et al.  Generalized varying coefficient partially linear measurement errors models , 2017 .

[12]  Shengyuan Xu,et al.  New insight into reachable set estimation for uncertain singular time-delay systems , 2018, Appl. Math. Comput..

[13]  Yumeng Li,et al.  A moderate deviation principle for stochastic Volterra equation , 2017 .

[14]  Qian Zhang,et al.  Mathematical modeling and numerical study of carbonation in porous concrete materials , 2016, Appl. Math. Comput..

[15]  Ian Goodfellow,et al.  Generative adversarial networks , 2020, Commun. ACM.

[16]  Bin Wang,et al.  Trigonometric collocation methods based on Lagrange basis polynomials for multi-frequency oscillatory second-order differential equations , 2016, J. Comput. Appl. Math..

[17]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[18]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Wensheng Chen,et al.  A novel adaptive partial differential equation model for image segmentation , 2014 .

[20]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[21]  Shudi Yang,et al.  The weight distributions of two classes of p-ary cyclic codes with few weights , 2015, Finite Fields Their Appl..

[22]  Fushan Li,et al.  Global existence and blow-up phenomena for p-Laplacian heat equation with inhomogeneous Neumann boundary conditions , 2014, Boundary Value Problems.

[23]  Huajun Gong,et al.  Local well-posedness of strong solutions to density-dependent liquid crystal system , 2015 .

[24]  Fushan Li,et al.  Blow-up of solution for a nonlinear Petrovsky type equation with memory , 2016, Appl. Math. Comput..

[25]  Bin Wang,et al.  Arbitrary-Order Trigonometric Fourier Collocation Methods for Multi-Frequency Oscillatory Systems , 2016, Found. Comput. Math..

[26]  Fanwei Meng,et al.  Some new weakly singular integral inequalities and their applications to fractional differential equations , 2016 .

[27]  Dongdai Lin,et al.  Complete weight enumerators of two classes of linear codes , 2017, Discret. Math..

[28]  Lihua Liu,et al.  New oscillation criteria for second-order nonlinear neutral delay differential equations , 2009, J. Comput. Appl. Math..

[29]  Jun Zhang,et al.  Correlation analysis with additive distortion measurement errors , 2017 .

[30]  Martín Abadi,et al.  Learning to Protect Communications with Adversarial Neural Cryptography , 2016, ArXiv.

[31]  Xi-Nan Ma,et al.  Constant mean curvature surfaces and mean curvature flow with non-zero Neumann boundary conditions on strictly convex domains , 2018 .

[32]  Peihe Wang,et al.  Some geometrical properties of convex level sets of minimal graph on 2-dimensional Riemannian manifolds , 2016 .

[33]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Stefan Scherer,et al.  Learning representations of emotional speech with deep convolutional generative adversarial networks , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[35]  Hongyong Zhao,et al.  Strong and weak properties of travelling waves for degenerate diffusion/aggregation-diffusion models with non-smooth reaction term , 2018, Appl. Math. Lett..

[36]  Bin Wang,et al.  Sixth-order symplectic and symmetric explicit ERKN schemes for solving multi-frequency oscillatory nonlinear Hamiltonian equations , 2017 .

[37]  Fushan Li,et al.  Global existence and blow-up phenomena for nonlinear divergence form parabolic equations with inhomogeneous Neumann boundary conditions , 2012 .

[38]  Camille Couprie,et al.  Semantic Segmentation using Adversarial Networks , 2016, NIPS 2016.

[39]  Bo Chen,et al.  Noisy image segmentation based on wavelet transform and active contour model , 2011 .

[40]  Soumith Chintala,et al.  Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks , 2015, ICLR.

[41]  Chuangqiang Hu,et al.  Pure Weierstrass gaps from a quotient of the Hermitian curve , 2018, Finite Fields Their Appl..

[42]  Yuru Zou,et al.  On small bases which admit points with two expansions , 2017 .

[43]  Chuangqiang Hu,et al.  Weierstrass semigroups from Kummer extensions , 2017, Finite Fields Their Appl..

[44]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[45]  Bing Xu,et al.  On the Number of Periodic Solutions of Delay Differential Equations , 2018, Int. J. Bifurc. Chaos.

[46]  Peihe Wang,et al.  The convexity of the level sets of maximal strictly space-like hypersurfaces defined on 2-dimensional space forms , 2018, Nonlinear Analysis.

[47]  Zengqin Zhao,et al.  Iterative technique for third-order differential equation with three-point nonlinear boundary value conditions , 2016 .

[48]  Pingrun Li,et al.  Some classes of equations of discrete type with harmonic singular operator and convolution , 2016, Appl. Math. Comput..

[49]  Qiang Ji,et al.  A joint cascaded framework for simultaneous eye detection and eye state estimation , 2017, Pattern Recognit..

[50]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[51]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[52]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[53]  Xiaoming Peng,et al.  Lower bounds for the blow-up time to a nonlinear viscoelastic wave equation with strong damping , 2018, Appl. Math. Lett..

[54]  Peihe Wang,et al.  Convexity of Level Sets of Minimal Graph on Space Form with Nonnegative Curvature , 2016, 1607.05991.