Abstract: Two actual rocks drilled from a typical ultra-deep hydrocarbon reservoir in the Tarim Basin are selected to conduct in-situ stress-loading micro-focus CT scanning experiments. The gray images of rock microstructure at different stress loading stages are obtained. The U-Net fully convolutional neural network is utilized to achieve fine semantic segmentation of rock skeleton, pore space, and micro-fractures based on CT slice images of deep rocks. The three-dimensional digital rock models of deformed multiscale fractured-porous media at different stress loading stages are thereafter reconstructed, and the equivalent fracture-pore network models are finally extracted to explore the underlying mechanisms of gas–water two-phase flow at the pore-scale. Results indicate that, in the process of in-situ stress loading, both the deep rocks have experienced three stages: linear elastic deformation, nonlinear plastic deformation, and shear failure. The micro-mechanical behavior greatly affects the dynamic deformation of rock microstructure and gas–water two-phase flow. In the linear elastic deformation stage, with the increase in in-situ stress, both the deep rocks are gradually compacted, leading to decreases in average pore radius, pore throat ratio, tortuosity, and water-phase relative permeability, while the coordination number nearly remains unchanged. In the plastic deformation stage, the synergistic influence of rock compaction and existence of micro-fractures typically exert a great effect on pore-throat topological properties and gas–water relative permeability. In the shear failure stage, due to the generation and propagation of micro-fractures inside the deep rock, the topological connectivity becomes better, fluid flow paths increase, and flow conductivity is promoted, thus leading to sharp increases in average pore radius and coordination number, rapid decreases in pore throat ratio and tortuosity, as well as remarkable improvement in relative permeability of gas phase and water phase.