The millimeter-wave (mmWave) radar-based gait recognition technology has attracted significant attention due to its cost-effectiveness and weather resilience. The majority of existing methods are primarily designed for the recognition of gait patterns on the fixed route, and they achieve significant performance. However, fewer advancements have been made in gait pattern recognition for the free route, primarily owing to the challenges posed by data sparsity and route diversity in such contexts. To take those issues into account, we present a novel framework named Gait Spatio-Temporal Network (GSTNet), designed for efficient human gait recognition from spatiotemporal features. The GSTNet is composed of Multi-Temporal Resolution DGCNN (MTRD) and Dynamic Feature Capturing Module (DFCM). The MTDR regroups frames before edge convolution, extracting not only the spatial features of each frame but also the dynamic features from neighboring frames to cope with relative data sparsity. The DFCM adaptively generates weights for each frame through temporal features to handle diverse gait samples. Experiments demonstrate our GSTNet achieves state-of-the-art on the mmGait and STPointGCN datasets. Additionally, we provide results from the ablation study to further validate the efficacy of the proposed framework.