Tensorflowfully_connected 在单元测试用例中不起作用? [英] Tensorflow fully_connected not working in unit test cases?

问题描述

我一定错过了一些基本的东西.这是我的测试用例 -

I must missed something basic. Here is my test case -

    def test_silly(self):
        with self.test_session() as sess:
            init_op = tf.global_variables_initializer()
            out = tf.contrib.layers.fully_connected(
                inputs=tf.zeros([self.batch_size, 10]),
                num_outputs=20,
                activation_fn=None,
                scope="hmmm")
            sess.run(init_op)
            print(out.eval())

我不明白为什么我总是收到如下错误.

I do not understand why I kept getting error like below.

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value hmmm/weights
 [[Node: hmmm/weights/read = Identity[T=DT_FLOAT, _class=["loc:@hmmm/weights"], _device="/job:localhost/replica:0/task:0/cpu:0"](hmmm/weights)]]

推荐答案

hmmm/weights 未初始化.

def test_silly(self):
    with self.test_session() as sess:
        out = tf.contrib.layers.fully_connected(
            inputs=tf.zeros([self.batch_size, 10]),
            num_outputs=20,
            activation_fn=None,
            scope="hmmm")
        init_op = tf.global_variables_initializer()
        sess.run(init_op)
        print(out.eval())

交换init_op 的位置就可以了.参考 What did tf.global_variables_initializer() 在引擎盖?了解更多见解.

Swapping the position of init_op will make it work. Refer to What does tf.global_variables_initializer() do under the hood? for more insights.

这篇关于Tensorflowfully_connected 在单元测试用例中不起作用?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！