回答此问题可获得 20 贡献值,回答如果被采纳可获得 50 分。
<p>我用Keras来训练深层神经网络。我使用<strong>train_on_batch</strong>功能来训练我的模型。我的模型有两个输出。我要做的是,修改每个样本的损失,每个样本的特定值。因此,由于Keras文档<a href="https://keras.io/models/sequential/#train_on_batch" rel="nofollow noreferrer">here</a></p>
<p>我需要为<strong>示例权重</strong>参数分配两个不同的权重。
下面是我的代码,其中每一批,我有四个培训示例:</p>
<pre><code>wights=[12,10,31,1];
mod_loss = mymodel.train_on_batch([X_train], [Y1, Y2],sample_weight=[wights,[1.0,1.0,1.0,1.0]])
</code></pre>
<p>我使用<strong>sample_weight</strong>只对第一个输出进行加权,而不是对第二个输出进行加权。运行代码时,出现以下错误:</p>
^{pr2}$
<p>它给了我一个想法,如果我把赋值改为<strong>sample_weight</strong>为一个numpy数组,问题就会迎刃而解。所以我把代码改成了这个:</p>
<pre><code>wights=[12,10,31,1];
mod_loss = mymodel.train_on_batch([X_train], [Y1, Y2],sample_weight=numpy.array([wights,[1.0,1.0,1.0,1.0]]))
</code></pre>
<p>我有个错误:</p>
<pre><code> File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training.py", line 1211, in train_on_batch
class_weight=class_weight)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training.py", line 794, in _standardize_user_data
sample_weight, feed_output_names)
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training_utils.py", line 200, in standardize_sample_weights
'sample_weight')
File "/Library/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/keras/engine/training_utils.py", line 188, in standardize_sample_or_class_weights
str(x_weight))
TypeError: The model has multiple outputs, so `sample_weight` should be either a list or a dict. Provided `sample_weight` type not understood: [[12.0 10.0 31.0 1.0]
[ 1. 1. 1. 1. ]]
</code></pre>
<p>我有点困惑,我不确定这是否是Keras实现中的一个bug。我在网上几乎找不到任何与此相关的工作或问题。有什么想法吗?在</p>