如何在Tensorflow中創建Inception模塊

Question

查看tensorflow頁面： https : //github.com/tensorflow/models/tree/master/inception

他們顯示了具有其體系結構的圖像，特別是並行包含的“ inception”模塊：

• 1x1的轉換層
• 3x3轉換層
• 5x5的轉換層
• 平均池+ 1x1轉換

隨后是“ concat”層。

我如何在tensorflow中創建這個？

我認為我可以按照這種方式做一些事情來創建並行操作：

start_layer = input_data

filter = tf.Variable(tf.truncated_normal([1,1,channels,filter_count], stddev=0.1)
one_by_one = tf.nn.conv2d(start_layer, filter, strides=[1,1,1,1], padding='SAME')

filter = tf.Variable(tf.truncated_normal([3,3,channels,filter_count], stddev=0.1)
three_by_three = tf.nn.conv2d(start_layer, filter, strides=[1,1,1,1], padding='SAME')

filter = tf.Variable(tf.truncated_normal([5,5,channels,filter_count], stddev=0.1)
five_by_five = tf.nn.conv2d(start_layer, filter, strides=[1,1,1,1], padding='SAME')

filter = tf.Variable(tf.truncated_normal([1,1,channels,filter_count], stddev=0.1)
pooling = tf.nn.avg_pool(start_layer, filter, strides=[1,2,2,1], padding='SAME')

filter = tf.Variable(tf.truncated_normal([1,1,channels,filter_count], stddev=0.1)
pooling = tf.nn.conv2d(pooling, filter, strides=[1,1,1,1], padding='SAME')

#connect one_by_one, three_by_three, five_by_five, pooling into an concat layer

但是，如何將這4個操作組合到concat層中？

Answer 1

我做了與您所做的非常相似的事情，然后使用tf.concat()完成了它。 請注意axis=3 ，它與我的4d張量和連貫匹配到第4維（索引3）。 它的文檔在這里 。

我的最終代碼最終如下所示：

def inception2d(x, in_channels, filter_count):
    # bias dimension = 3*filter_count and then the extra in_channels for the avg pooling
    bias = tf.Variable(tf.truncated_normal([3*filter_count + in_channels], mu, sigma)),

    # 1x1
    one_filter = tf.Variable(tf.truncated_normal([1, 1, in_channels, filter_count], mu, sigma))
    one_by_one = tf.nn.conv2d(x, one_filter, strides=[1, 1, 1, 1], padding='SAME')

    # 3x3
    three_filter = tf.Variable(tf.truncated_normal([3, 3, in_channels, filter_count], mu, sigma))
    three_by_three = tf.nn.conv2d(x, three_filter, strides=[1, 1, 1, 1], padding='SAME')

    # 5x5
    five_filter = tf.Variable(tf.truncated_normal([5, 5, in_channels, filter_count], mu, sigma))
    five_by_five = tf.nn.conv2d(x, five_filter, strides=[1, 1, 1, 1], padding='SAME')

    # avg pooling
    pooling = tf.nn.avg_pool(x, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME')

    x = tf.concat([one_by_one, three_by_three, five_by_five, pooling], axis=3)  # Concat in the 4th dim to stack
    x = tf.nn.bias_add(x, bias)
    return tf.nn.relu(x)