Created by: SnowWhite11235

您好，我自己再train.py中实现了带有ignore_labels的交叉熵函数，但是训练过程中损失函数不收敛，请问是哪里写的不太对吗？或者是反传需要什么特殊处理？用API的交叉熵是没有问题的。 （其中mask是一个过滤掉label小于-1的位置的模板） def cross_entropy_loss(fc, labels_int32, class_num): # labels: int32 to int64 and double labels_double = fluid.layers.cast(x=labels_int32, dtype='double') labels_int64 = fluid.layers.cast(x=labels_int32, dtype='int64') # generate mask ignore_labels = fluid.layers.fill_constant(shape=[1], value=0, dtype='int64') # mask thres mask_bool = fluid.layers.greater_equal(x=labels_int64, y=ignore_labels) mask_int = fluid.layers.cast(x=mask_bool, dtype='int64') mask_float = fluid.layers.cast(x=mask_bool, dtype='float32') # softmax the input fc fc_softmax = fluid.layers.softmax(input=fc) # change -1 to 1 in label labels_double_abs = paddle.fluid.layers.abs(x=labels_double) labels_int64_abs = fluid.layers.cast(x=labels_double_abs, dtype='int64') labels_int64_abs.stop_gradient=True # must # calculate loss labels = fluid.layers.one_hot(labels_int64_abs, depth=class_num) loss = -1.0 * fluid.layers.log(fc_softmax) * labels # mask the loss loss = fluid.layers.elementwise_mul(loss, mask_float) loss_mean = fluid.layers.reduce_sum(loss) return loss_mean