LSTMEncDecAttn.py 文件源码

def setInitAllParameters(self, optimizer, init_type="default",
                             init_scale=0.1):
        sys.stdout.write("############ Current Parameters BEGIN\n")
        self.printAllParameters(optimizer)
        sys.stdout.write("############ Current Parameters END\n")

        if init_type == "uniform":
            sys.stdout.write(
                "# initializer is [uniform] [%f]\n" %
                (init_scale))
            t_initializer = chainer.initializers.Uniform(init_scale)
            named_params = sorted(
                optimizer.target.namedparams(),
                key=lambda x: x[0])
            for n, p in named_params:
                with cuda.get_device(p.data):
                    if args.chainer_version_check[0] == 2:
                        p.copydata(chainer.Parameter(
                            t_initializer, p.data.shape))
                    else:
                        chainer.initializers.init_weight(p.data, t_initializer)
        elif init_type == "normal":
            sys.stdout.write("# initializer is [normal] [%f]\n" % (init_scale))
            t_initializer = chainer.initializers.Normal(init_scale)
            named_params = sorted(
                optimizer.target.namedparams(),
                key=lambda x: x[0])
            for n, p in named_params:
                with cuda.get_device(p.data):
                    if args.chainer_version_check[0] == 2:
                        p.copydata(chainer.Parameter(
                            t_initializer, p.data.shape))
                    else:
                        chainer.initializers.init_weight(p.data, t_initializer)
        else:  # "default"
            sys.stdout.write(
                "# initializer is [defalit] [%f]\n" %
                (init_scale))
            named_params = sorted(
                optimizer.target.namedparams(),
                key=lambda x: x[0])
            for n, p in named_params:
                with cuda.get_device(p.data):
                    p.data *= args.init_scale
        self.printAllParameters(optimizer, init_type, init_scale)
        return 0