2

查看 tfa.metrics.CohenKappa的文档，我试图弄清楚如何将它与一个简单的模型一起使用。

我编写了以下代码：

  num_features = 10
  inp = Input(shape=( num_features))
  out = Dense(5, activation='softmax')(inp)
  model = tf.keras.models.Model(inp, out)
  # model.add_metric(tfa.metrics.CohenKappa(num_classes=5)(out)) <-- problematic line
  model.compile('sgd', loss='mse')

这会产生以下模型：

Model: "model_16"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_18 (InputLayer)        [(None, 1)]               0         
_________________________________________________________________
dense_51 (Dense)             (None, 5)                 10        
=================================================================
Total params: 10
Trainable params: 10
Non-trainable params: 0
_________________________________________________________________

如果我取消注释 cohenKappa 行，我会收到以下错误：

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-165-d0ef1187e052> in <module>()
----> 1 get_model().summary()

4 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/metrics_utils.py in decorated(metric_obj, *args, **kwargs)
     88 
     89     with tf_utils.graph_context_for_symbolic_tensors(*args, **kwargs):
---> 90       update_op = update_state_fn(*args, **kwargs)
     91     if update_op is not None:  # update_op will be None in eager execution.
     92       metric_obj.add_update(update_op)

TypeError: update_state() missing 1 required positional argument: 'y_pred'

我错过了什么？

4

0 回答 0