Question

我已将server { listen 443 ssl default_server; listen [::]:443 ssl default_server; location / { # proxy pass to your app proxy_pass http://localhost:7070; proxy_http_version 1.1; proxy_set_header Upgrade $http_upgrade; proxy_set_header Connection 'upgrade'; proxy_set_header Host $host; proxy_cache_bypass $http_upgrade; }子类化为我的RNN的构建块。我将此对象的实例放入RNNCell，然后在tf.dynamic_rnn类中定义预测函数：

Agent

一切正常，但我现在如何为图层添加直方图？我试图在class Agent(): def __init__(self): ... def predictions(self): cell = RNNCell() output, last_state = tf.dynamic_rnn(cell, inputs = ...) return output中进行此操作，但它不起作用：

RNNCell

然后

class RNNCell(tf.nn.rnn_cell.RNNCell):
    def __init__(self):
        super(RNNCell, self).__init__()
        self._output_size = 15
        self._state_size = 15
        self._histogram1 = None

    def __call__(self, X, state):
        network = tflearn.layers.conv_2d(X, 5, [1, 3], activation='relu', weights_init=tflearn.initializations.variance_scaling(), padding="valid")
        self._histogram1 = tf.summary.histogram("layer1_hist_summary", network)
        ...

    @property
    def histogram1(self):
    return self._histogram1

稍后当我运行class Agent(): def __init__(self): ... def predictions(self): cell = RNNCell() self.histogram1 = cell.histogram1 output, last_state = tf.dynamic_rnn(cell, inputs = ...) return output时，我收到错误sess.run(agent.histogram1, feed_dict=...)

Answer 1

我认为问题是Agent的self.histogram1的价值从未更新，以反映RNNCell中分配的摘要。

您的Agent predictions（）方法的代码在此处将Agent的histogram1值初始化为None：

cell = RNNCell()  #invoks __init__() so RNNCELL's histogram1 is now None
self.histogram1 = cell.histogram1

当调用RNNCell的__call__()方法时，它会更新RNNCell的histogram1值

self._histogram1 = tf.summary.histogram("layer1_hist_summary", network)

但是代理商的histogram1副本显然没有更新，所以当打电话时：

sess.run(agent.histogram1, feed_dict=...)

agent.histogram1仍然是无。

我没有在发布的代码中看到摘要在培训之前合并的情况，因此缺少的步骤很可能是在某处未发布的代码中。

如何在张量板中可视化RNN层的直方图？

1 个答案: