Pytorch动态调整学习率

poly学习策略

当power＜0，呈现为凸函数，随着epoch增加，学习率下降速率由慢变快

当power >1，呈现为凹函数，随着epoch增加，学习率下降速率由快变慢

def adjust_lr_poly(optimizer, epoch, num_epochs, base_lr, power=0.9)
    lr = base_lr * (1-epoch/num_epochs)**power
    for param_group in optimizer.param_groups:
        param_group['lr'] = lr
    return lr