Tensorflow，多标签精度计算 [英] Tensorflow, multi label accuracy calculation

问题描述

我正在处理一个多标签问题，我正在尝试确定我的模型的准确性.

I am working on a multi label problem and i am trying to determine the accuracy of my model.

我的模型:

NUM_CLASSES = 361

x = tf.placeholder(tf.float32, [None, IMAGE_PIXELS])
y_ = tf.placeholder(tf.float32, [None, NUM_CLASSES])

# create the network
pred = conv_net( x )

# loss
cost = tf.reduce_mean( tf.nn.sigmoid_cross_entropy_with_logits( pred, y_) )

# train step
train_step   = tf.train.AdamOptimizer().minimize( cost )

我想以两种不同的方式计算准确度
- 正确预测的所有标签的百分比- 正确预测所有标签的图像百分比

i want to calculate the accuracy in two different ways
- % of all labels that are predicted correctly - % of images where ALL labels are predicted correctly

不幸的是，我只能计算正确预测的所有标签的百分比.

unfortunately i am only able to calculate the % of all labels that are predicted correctly.

我认为这段代码会计算正确预测所有标签的图像百分比

I thought this code would calculate % of images where ALL labels are predicted correctly

correct_prediction = tf.equal( tf.round( pred ), tf.round( y_ ) )

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

以及此代码占正确预测的所有标签的百分比

and this code % of all labels that are predicted correctly

pred_reshape = tf.reshape( pred, [ BATCH_SIZE * NUM_CLASSES, 1 ] )
y_reshape = tf.reshape( y_, [ BATCH_SIZE * NUM_CLASSES, 1 ] )

correct_prediction_all = tf.equal( tf.round( pred_reshape ), tf.round( y_reshape ) )

accuracy_all = tf.reduce_mean( tf.cast(correct_prediction_all, tf.float32 ) )

不知何故，属于一张图像的标签的一致性丢失了，我不知道为什么.

somehow the coherency of the labels belonging to one image is lost and i am not sure why.

推荐答案

我相信您代码中的错误在于:correct_prediction = tf.equal( tf.round( pred ), tf.round( y_ ) ).

I believe the bug in your code is in: correct_prediction = tf.equal( tf.round( pred ), tf.round( y_ ) ).

pred 应该是未缩放的 logits(即没有最终的 sigmoid).

pred should be unscaled logits (i.e. without a final sigmoid).

这里你想比较 sigmoid(pred) 和 y_ 的输出(都在区间 [0, 1] 中)所以你必须写:

Here you want to compare the output of sigmoid(pred) and y_ (both in the interval [0, 1]) so you have to write:

correct_prediction = tf.equal(tf.round(tf.nn.sigmoid(pred)), tf.round(y_))

<小时>

然后计算:

---

Then to compute:

• 所有标签的平均准确率:

accuracy1 = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

• 所有标签都需要正确的准确性:

all_labels_true = tf.reduce_min(tf.cast(correct_prediction), tf.float32), 1)
accuracy2 = tf.reduce_mean(all_labels_true)

这篇关于Tensorflow，多标签精度计算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！