首页 文章

CNN结果在keras和tensorflow中是不同的

提问于
浏览 次
0

我最近正在学习机器学习 . 所以我在keras和tensorflow（不使用keras）中制作一些cnn模型来练习技能 . 但keras和tensorflow的cnn结果并不相同 . 这很令人困惑 .

keras结果为68％，tensorflow为66.6％

这里是tensorflow代码：

def convolution(self, inputs_fw):

    inputs_fw = tf.nn.dropout(inputs_fw, keep_prob=self.dropout_keep_prob)

    with tf.name_scope('forward_conv'):
        fil1 = 2
        fil2 = 3

        conv1_fw = tf.layers.conv1d(inputs_fw,filters=100,kernel_size=fil1,padding="VALID",activation=tf.nn.tanh)#tanh
        print "print conv1"
        print conv1_fw
        conv1_fw = conv1_fw + self.cbiases['convolution1']
        pool_fw = tf.layers.max_pooling1d(inputs=conv1_fw,pool_size=self.max_sentence_len-fil1+1,strides=self.max_sentence_len-fil1+1)
        print pool_fw

        pool_fw_flat =tf.reshape(pool_fw, [-1,1*100])

        conv1_fw2 = tf.layers.conv1d(inputs_fw,filters=100,kernel_size=fil2,padding="VALID",activation=tf.nn.tanh)#tanh
        print "print conv12"
        conv1_fw2 = conv1_fw2 + self.cbiases['convolution2']
        print conv1_fw2
        pool_fw2 = tf.layers.max_pooling1d(inputs=conv1_fw2,pool_size=self.max_sentence_len-fil2+1,strides=self.max_sentence_len-fil2+1)
        print pool_fw2

        pool_fw_flat2 =tf.reshape(pool_fw2, [-1,1*100])


    output = tf.concat([pool_fw_flat,pool_fw_flat2],1)

    predict = tf.matmul(output, self.weights['softmax_conv']) + self.biases['softmax_conv']

    print predict.get_shape()
    return predict

损失和准确性由：

with tf.name_scope('loss'):
        cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prob, labels=self.y))

    with tf.name_scope('train'):
        global_step = tf.Variable(0, name="tr_global_step", trainable=False)
        optimizer = tf.train.AdadeltaOptimizer(learning_rate=self.learning_rate).minimize(cost, global_step=global_step)

    with tf.name_scope('predict'):
        correct_pred = tf.equal(tf.argmax(prob, 1), tf.argmax(self.y, 1))
        # accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
        accuracy = tf.reduce_sum(tf.cast(correct_pred, tf.int32))

我犯了一些错误吗？非常感谢 .

tensorflow keras conv-neural-network

2 回答

  • 0

    原因可能是代码中的dropout层，它将随机对图层输出进行采样，尝试重新运行两次tensorflow代码，您也会得到不同的结果 .

    inputs_fw = tf.nn.dropout(inputs_fw, keep_prob=self.dropout_keep_prob)
    回复于
  • 0

    看来你是nopt使用 softmax 来获取概率

    logits = tf.matmul(output, self.weights['softmax_conv']) + self.biases['softmax_conv']
predict = tf.nn.softmax(tf.matmul(output, self.weights['softmax_conv']) + self.biases['softmax_conv'])
# is training True/False
inputs_fw = tf.nn.dropout(inputs_fw, keep_prob=self.dropout_keep_prob, is_training=is_training)
    回复于

相关问题