saeedizadi

def main():
    print("hello world!")


if __name__ == "__main__":
    main()

saeedizadi

model = dict()
        optimizer = dict()
        criterion = dict()
        model['gen'] = UncertaintyNet(ndense=12, nconvs=8, growth_rate=8, scale=scale).cuda()
        optimizer['gen'] = optim.Adam(model['gen'].parameters(), lr=lr, weight_decay=weight_decay)
        criterion['gen'] = nn.L1Loss().cuda()

        model['disc'] = Discriminator().cuda()
        optimizer['disc'] = optim.Adam(model['disc'].parameters(), lr=lr, weight_decay=weight_decay)
        criterion['disc'] = nn.BCELoss().cuda()

saeedizadi

def binary_jaccard_index(predictions,targets):
    """Computes the binary (generalized) Jaccard index between predictions and targets.
    .. math:: L_i  = \\sum_i{\\min(p_i,t_i} / \\sum_i{\\max(p_i,t_i}
    Parameters
    ----------
    predictions : Theano tensor
        Predictions in [0, 1], such as a sigmoidal output of a neural network,
        giving the probability of the positive class
    targets : Theano tensor
        Targets in {0, 1}, such as ground truth labels.