TensorFlow中具有稀疏标签的多标签图像分类？ [英] Multilabel image classification with sparse labels in TensorFlow?
问题描述
我想对n个类执行多标签图像分类任务。
我为每个图像都得到了稀疏的标签向量，并且每个标签向量的每个维当前都以这种方式编码：
I want to perform a multilabel image classification task for n classes. I've got sparse label vectors for each image and each dimension of each label vector is currently encoded in this way:
1.0->标签为真/图像属于此类
1.0 ->Label true / Image belongs to this class
-1.0->标签错误/图片不包含此类。
-1.0 ->Label false / Image does not contain to this class.
0.0 ->缺失值/标签
0.0 ->missing value/label
例如：V = {1.0，-1.0,1.0，0.0}
E.g.: V= {1.0,-1.0,1.0, 0.0}
对于此示例V，模型应学习到，相应的图像应分类为第一类和第三类。
For this example V the model should learn, that the corresponding image should be classified in the first and third class.
我目前的问题是如何处理缺失的值/标签。我搜索了所有问题并发现了这个问题：
tensorflow / skflow＃113 在这里找到
My problem is currently how to handle the missing values/labels. I've searched through the issues and found this issue: tensorflow/skflow#113 found here
因此可以使用以下方法进行多重图像分类：
tf.nn.sigmoid_cross_entropy_with_logits（logits，target，name = None）
So could do multilable image classification with: tf.nn.sigmoid_cross_entropy_with_logits(logits, targets, name=None)
但是TensorFlow具有针对稀疏softmax的此错误函数，用于专有分类：
tf.nn.sparse_softmax_cross_entropy_with_logits（logits，labels，name = None）
but TensorFlow has this error function for sparse softmax, which is used for exclusive classification: tf.nn.sparse_softmax_cross_entropy_with_logits(logits, labels, name=None)
那么有稀疏的S型交叉熵吗？ （找不到任何东西）或任何建议，如何处理稀疏标签的多标签分类问题。
So is there something like sparse sigmoid cross entropy? (Couldn't find something) or any suggestions how can I handle my multilabel classification problem with sparse labels.
推荐答案
我使用了 weighted_cross_entropy_with_logits 作为损失函数，权重为正数1s。
I used weighted_cross_entropy_with_logits as the loss function with positive weights for 1s.
在我来说，所有标签都同样重要。但是0出现在任何标签上的可能性是1的十倍。
In my case, all the labels are equally important. But 0 was ten times more likely to be appeared as the value of any label than 1.
所以我通过调用 pos_weight权衡了所有1。前述损失函数的 参数。我使用的pos_weight（=正值的权重）为10。顺便说一句，我不建议使用任何策略来计算pos_weight。我认为这将明确取决于手中的数据。
So I weighed all the 1s by calling the pos_weight parameter of the aforementioned loss function. I used a pos_weight (= weight on positive values) of 10. By the way, I do not recommend any strategy to calculate the pos_weight. I think it will depend explicitly on the data in hand.
如果实数标签= 1，则
weighted_cross_entropy = pos_weight * sigmoid_cross_entropy
具有logits的加权交叉熵与具有
Weighted cross entropy with logits is same as the Sigmoid cross entropy with logits, except for the extra weight value multiplied to all the targets with a positive real value i.e.; 1.
从理论上讲，它应该可以完成工作。我仍在调整其他参数以优化性能。稍后会更新性能统计信息。
Theoretically, it should do the job. I am still tuning other parameters to optimize the performance. Will update with performance statistics later.
这篇关于TensorFlow中具有稀疏标签的多标签图像分类？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
