Two phase flow commonly occurs in industrial pipelines, heat exchangers and nuclear power plants. A characteristic feature of two-phase flow is that it can acquire various spatial distribution of phases to form different flow patterns/regimes. The first step to successfully design, analyze, and operate gas-liquid system is flow regime identification. Flow regime identification is of huge importance to the effective operation of facilities for the handling and transportation of multiphase fluids, and it represents one of the most significant challenges in petrochemical and thermonuclear industries today. The objective of this study is to develop a methodology for identification of flow regime using dynamic pressure signals and deep learning techniques. Three different flow regimes were simulated using a Level-Set (LS) method coupled with Volume of Fluid (VOF) method in a 6 m horizontal pipe with 0.050 m inner diameter. Dynamic pressure readings were collected at a strategic location and were converted to scalograms to be used as inputs in deep learning architectures like ResNet-50 and ShuffleNet. Both architectures performed effectively in classifying different flow regime and recorded testing accuracies of 85.7 and 82.9 respectively. According to our knowledge no similar research has been reported in literature, where various Convolutional Neural Networks are used along with dynamic pressure signals to identify flow regime in horizontal pipe. © 2022, Penerbit Akademia Baru. All rights reserved.