从 softmax 中移除低质量张量预测

Question

我想对张量应用过滤器并删除不符合我条件的值。例如，假设我有一个如下所示的张量：

softmax_tensor = [[ 0.05 , 0.05, 0.2, 0.7], [ 0.25 , 0.25, 0.3, 0.2 ]]

现在，分类器选择 argmax 个张量进行预测：

predictions = [[3],[2]]

但这并不是我想要的，因为我丢失了有关该预测的置信度的信息。我宁愿不做预测，也不愿做出错误的预测。所以我想做的是 return 像这样过滤张量：

new_softmax_tensor = [[ 0.05 , 0.05, 0.2, 0.7]]
new_predictions    = [[3]]

如果这是直截了当的 python，我就没有问题了：

new_softmax_tensor = []
new_predictions    = []

for idx,listItem in enumerate(softmax_tensor):
    # get two highest max values and see if they are far enough apart
    M  = max(listItem)
    M2 = max(n for n in listItem if n!=M)
    if M2 - M > 0.3: # just making up a criteria here
        new_softmax_tensor.append(listItem) 
        new_predictions.append(predictions[idx])

但考虑到 tensorflow 在张量上运行，我不确定如何执行此操作 - 如果我这样做，它会破坏计算图吗？

一个 suggested using tf.gather_nd, but in that scenario they already had a tensor that they wated to filter on. I've also looked at tf.cond还是没看懂。我想很多其他人会从这个完全相同的解决方案中受益。

谢谢大家。

Answer 1

我会做两件事来解决你的问题：

首先，我会 return softmax 张量的值。你在某处寻找对它的引用（你在创建它时保留对它的引用，或者你在适当的张量集合中找到它）然后在 sess.run([softmaxtensor,prediction],feed_dict=..) 中评估它然后你用 python随你喜欢。

其次，如果您想留在图表中，我会使用 build-it tf.where()，其工作方式与 numpy 包 doc there[=13= 中的 np.where 函数非常相似]

Answer 2

好的。我现在已经解决了。这是一个工作示例。

import tensorflow as tf

#Set dummy example tensor
original_softmax_tensor = tf.Variable([
    [0.4,0.2,0.2,0.9,0.1],
    [0.5,0.2,0.2,0.9,0.1],
    [0.6,0.2,0.2,0.1,0.99],
    [0.1,0.8,0.2,0.09,0.99]
    ],name='original_softmax_tensor')

#Set dummy prediction tensor
original_predictions    = tf.Variable([3,3,4,4],name='original_predictions')

#Now create a place to store my new variables
new_softmax_tensor = original_softmax_tensor
new_predictions    = original_predictions


#set my cutoff variable
min_diff = tf.constant(0.3)

#initialize
init_op = tf.global_variables_initializer()


with tf.Session() as sess:
    sess.run(init_op) #execute init_op
    #There's probably a better way to do this, but I had to do this hack to get
    # the difference between the top 2 scores
    tmp_diff1, _ = tf.nn.top_k(original_softmax_tensor,k=2,sorted=True)
    tmp_diff2, _ = tf.nn.top_k(original_softmax_tensor,k=1,sorted=True)
    #subtracting the max scores from both, makes the largest one '0'
    actual_diff = tf.subtract(tmp_diff2,tmp_diff1)
    #The max value for each will be the actual value of interest
    actual_diff = tf.reduce_max(actual_diff,reduction_indices=[1])
    #Create a boolean tensor that says to keep or not
    cond_result = actual_diff  > min_diff
    #Keep only the values I want
    new_predictions = tf.boolean_mask(original_predictions,cond_result)
    new_softmax_tensor = tf.boolean_mask(new_softmax_tensor,cond_result)
    new_predictions.eval()
    new_softmax_tensor.eval()
    # return these if this is in a function

从 softmax 中移除低质量张量预测

Removing low quality tensor predictions from softmax

python

numpy

tensorflow

tensor