unsupported operand type(s) for *: 'function' and 'float'

2019/12/07 下午 04:50

機器學習共學討論版

Leo Siu

觀看數：124

回答數：1

收藏數：0

ml100-3

ml100-3-d89

不清楚這個寫法是在哪裡出錯...基本上是依照範例寫的

得到的error message為: unsupported operand type(s) for *: 'function' and 'float'

請各位專家指教，謝謝!

import tensorflow as tf

import keras.backend as K

"""Code Here

撰寫一個 loss function, 使其可以結合 focal loss 與 crossentropy loss

"""

def combined_loss(gamma=2., alpha=4.):

"""Define the customized loss."""

gamma = float(gamma)

alpha = float(alpha)

def focal_loss_fixed(y_true, y_pred):

"""Focal loss for multi-classification

FL(p_t)=-alpha(1-p_t)^{gamma}ln(p_t)

"""

epsilon = 1e-8

y_true = tf.convert_to_tensor(y_true, tf.float32)

y_pred = tf.convert_to_tensor(y_pred, tf.float32)

model_out = tf.add(y_pred, epsilon)

ce = tf.multiply(y_true, -tf.log(model_out))

weight = tf.multiply(y_true, tf.pow(tf.subtract(1., model_out), gamma))

fl = tf.multiply(alpha, tf.multiply(weight, ce))

reduced_fl = tf.reduce_max(fl, axis=1)

return tf.reduce_mean(reduced_fl)

return focal_loss_fixed*(1-ce_w)+keras.losses.categorical_crossentropy(y_true, y_pred)*ce_w

ce_weights_list = [0., 0.3, 0.5, 0.7, 1]