A basic Neural Architecture Search using Multi Objective Genetic Algorithms. Hyper-parameter tuning with Genetic Algorithms. Done as part of the Artificial Intelligence course at IIIT-D
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [32, 128]], which is output 0 of ReluBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).