The inverse mapping of GANs'(Generative Adversarial Nets) generator has a great potential value. Hence, some works have been developed to construct the inverse function of generator by directly learning or adversarial learning. While the results are encouraging, the problem is highly challenging and the existing ways of training inverse models of GANs have many disadvantages, such as hard to train or poor performance. Due to these reasons, we propose a new approach based on using inverse generator (IG) model as encoder and pre-trained generator (G) as decoder of an AutoEncoder network to train the IG model. In the proposed model, the difference between the input and output, which are both the generated image of pre-trained GAN's generator, of Au-toEncoder is directly minimized. The optimizing method can overcome the difficulty in training and inverse model of an non one-to-one function. We also applied the inverse model of GANs' generators to image searching and translation. The experimental results prove that the proposed approach works better than the traditional approaches in image searching.
The ternary system of K 2 SO 4 + KH 2 PO 4 + H 2 O at (298.15 and 333.15) K was investigated by the method of isothermal solution saturation and moist residues. Thus the solubility data of the system were obtained, and phase diagrams of K 2 SO 4 + KH 2 PO 4 + H 2 O at (298.15 and 333.15) K were constructed on the basis of the solubility data. The solid phase in the system mentioned above was also identified. The crystallization field of potassium sulfate and potassium dihydrogen phosphate (KDP) were determined, and the crystallization field of potassium sulfate was larger than that of potassium dihydrogen phosphate. The density of saturated solutions for the systems studied at (298.15 and 333.15) K was also measured. The solubility data, density, and the phase equilibrium diagrams for the ternary system can provide the fundamental basis for the preparation of potassium dihydrogen phosphate in potassium sulfate and potassium dihydrogen phosphate aqueous mixtures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.