Gait reveals an individual’s pattern or manner of walking. It is influenced by a variety of factors, from genetics, personality, mood, and age to even social or cultural factors. Therefore, we can say that pathological gait classification is vital in the diagnosis of diseases related to abnormal walking patterns. Through this paper, we propose a computational technique that employs plantar pressure and 3D skeleton data to classify 6 different gait patterns (namely antalgic gait, lurching, steppage gait, stiff-legged gait, normal gait, and trendelenburg gait). We later feed this pressure data to convolutional neural networks and Vision transformers. We feed the skeleton data to Simple RNN, LSTM, GRU, Bi-LSTM, and Simple RNN+LSTM models.