Question

我最大限度地积累了张量。但是我不必使用内置的tf.nn.max_pool（），而是使用tf.reduce_max（）。但它给出了错误：

ValueError: Shape must be rank 4 but is rank 5 for 'conv2_1/Conv2D' (op: 'Conv2D') with input shapes: [1,?,1,224,64], [3,3,64,128].

以下是代码：

 with tf.name_scope('conv1_2') as scope:
        kernel = tf.Variable(tf.truncated_normal([3, 3, 64, 64], dtype=tf.float32,
                                                 stddev=1e-1), name='weights')
        conv = tf.nn.conv2d(self.conv1_1, kernel, [1, 1, 1, 1], padding='SAME')
        biases = tf.Variable(tf.constant(0.0, shape=[64], dtype=tf.float32),
                             trainable=True, name='biases')
        out = tf.nn.bias_add(conv, biases)
        self.conv1_2 = tf.nn.relu(out, name=scope)
        self.parameters += [kernel, biases]

 self.pool1=tf.reduce_max(self.conv1_2,reduction_indices=[1], keep_dims=True)


        # conv2_1
        with tf.name_scope('conv2_1') as scope:
            kernel = tf.Variable(tf.truncated_normal([3, 3, 64, 128], dtype=tf.float32,
                                                     stddev=1e-1), name='weights')
        sess = tf.InteractiveSession()
        tf.Print(self.pool1,[self.pool1],message="hellow fatima")
            conv = tf.nn.conv2d([self.pool1], kernel, [1, 1, 1, 1], padding='SAME')
            biases = tf.Variable(tf.constant(0.0, shape=[128], dtype=tf.float32),
                                 trainable=True, name='biases')
            out = tf.nn.bias_add(conv, biases)
            self.conv2_1 = tf.nn.relu(out, name=scope)
            self.parameters += [kernel, biases]

Answer 1

您可以尝试删除传递到[]的第一个参数中的tf.nn.conv2d。因此，您应该尝试以下方式而不是conv = tf.nn.conv2d([self.pool1], kernel, [1, 1, 1, 1], padding='SAME')：conv = tf.nn.conv2d(self.pool1, kernel, [1, 1, 1, 1], padding='SAME')

形状必须是等级4但是等级5

1 个答案: