我正在尝试根据以下内容创建损失函数：
但在Tensorflow 2.0中：
tf.contrib.metrics.cohen_kappa已不再存在。有替代方案吗？
回答：
def kappa_loss(y_pred, y_true, y_pow=2, eps=1e-10, N=4, bsize=256, name='kappa'):
"""离散卡帕损失的连续可微近似。
Args:
y_pred: 2D张量或数组，[batch_size, num_classes]
y_true: 2D张量或数组，[batch_size, num_classes]
y_pow: int，例如y_pow=2
N: 通常是模型的类别数
bsize: 训练或验证操作的批次大小
eps: 浮点数，防止除以零
name: 可选的操作范围/名称。
Returns:
包含卡帕损失的张量。"""
with tf.name_scope(name):
y_true = tf.cast(y_true, dtype='float')
repeat_op = tf.cast(tf.tile(tf.reshape(tf.range(0, N), [N, 1]), [1, N]), dtype='float')
repeat_op_sq = tf.square((repeat_op - tf.transpose(repeat_op)))
weights = repeat_op_sq / tf.cast((N - 1) ** 2, dtype='float')
pred_ = y_pred ** y_pow
try:
pred_norm = pred_ / (eps + tf.reshape(tf.reduce_sum(pred_, 1), [-1, 1]))
except Exception:
pred_norm = pred_ / (eps + tf.reshape(tf.reduce_sum(pred_, 1), [bsize, 1]))
hist_rater_a = tf.reduce_sum(pred_norm, 0)
hist_rater_b = tf.reduce_sum(y_true, 0)
conf_mat = tf.matmul(tf.transpose(pred_norm), y_true)
nom = tf.reduce_sum(weights * conf_mat)
denom = tf.reduce_sum(weights * tf.matmul(
tf.reshape(hist_rater_a, [N, 1]), tf.reshape(hist_rater_b, [1, N])) /
tf.cast(bsize, dtype='float'))
return nom / (denom + eps)并使用
lossMetric = kappa_loss
model.compile(optimizer=optimizer, loss=lossMetric, metrics=metricsToWatch)并事先将值转换为浮点数：
tf.cast(nn_x_train.values, dtype='float')我还使用了一个numpy验证版本：
def qwk3(a1, a2, max_rat=3):
assert(len(a1) == len(a2))
a1 = np.asarray(a1, dtype=int)
a2 = np.asarray(a2, dtype=int)
hist1 = np.zeros((max_rat + 1, ))
hist2 = np.zeros((max_rat + 1, ))
o = 0
for k in range(a1.shape[0]):
i, j = a1[k], a2[k]
hist1[i] += 1
hist2[j] += 1
o += (i - j) * (i - j)
e = 0
for i in range(max_rat + 1):
for j in range(max_rat + 1):
e += hist1[i] * hist2[j] * (i - j) * (i - j)
e = e / a1.shape[0]
return sum(1 - o / e)/len(1 - o / e)并使用
nn_y_valid=tf.cast(nn_y_train.values, dtype='float')
print(qwk3(nn_y_valid, trainPredict))其中nn_x_train和nn_y_train是pandas数据框
