可以用

scope.find_var(name)

请问有具体的例子吗？
假定我要输出FC1的参数

import paddle.fluid as fluid
x = fluid.layers.data(name='x', shape=[5], dtype='float32'),
fc1 = fluid.layers.fc(input=x, size=128, act='relu')
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())

https://github.com/PaddlePaddle/Paddle/blob/develop/python/paddle/fluid/tests/unittests/test_beam_search_op.py#L49
参考这个例子，需要对fc的参数指定一个名字，然后用名字获取值

import paddle.fluid as fluid
from paddle.fluid.param_attr import ParamAttr
x = fluid.layers.data(name='x', shape=[5], dtype='float32'),                         
param_attr = ParamAttr(name='target_fc')
bias_attr = ParamAttr(name='target_fc_b')
fc1 = fluid.layers.fc(input=x, size=128, act='relu', param_attr=param_attr, bias_attr=bias_attr)
scope = fluid.executor.global_scope()
 
# get tensor
ret = scope.find_var("target_fc").get_tensor()
print(ret)           
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
错误提示

Traceback (most recent call last):
  File "test.py", line 12, in
    ret = scope.find_var("target_fc").get_tensor()
AttributeError:
'NoneType' object has no attribute 'get_tensor'

program还没run的时候，数据是没有初始化的

问题搞定～我补充一下完整的代码，谢谢解答：）

import paddle.fluid as fluid
from paddle.fluid.param_attr import ParamAttr
x = fluid.layers.data(name='x', shape=[5], dtype='float32'),                         
param_attr = ParamAttr(name='target_fc')
bias_attr = ParamAttr(name='target_fc_b')
fc1 = fluid.layers.fc(input=x, size=128, act='relu', param_attr=param_attr, bias_attr=bias_attr)
 
# get tensor
place = fluid.CPUPlace()
exe = fluid.Executor(place)
exe.run(fluid.default_startup_program())
ret = fluid.global_scope().find_var("target_fc").get_tensor()
import numpy as np
ret = np.array(ret)
print (ret.shape)
print(ret)