mxnet中自定义loss fuction/ metric

mxnet中使用MakeLoss自定义损失函数

######mxnet.symbol.MakeLoss(data=None, grad_scale=_Null, valid_thresh=_Null, normalization=_Null, name=None, attr=None, out=None, **kwargs)

cross_entropy = label * log(out) + (1 - label) * log(1 - out)
loss = MakeLoss(cross_entropy)

# -*- coding=utf-8 -*-

import mxnet as mx
import numpy as np
import logging

logging.basicConfig(level=logging.INFO)

x = mx.sym.Variable('data')
y = mx.sym.FullyConnected(data=x, num_hidden=1)
label = mx.sym.Variable('label')
cross_entropy = label * log(out) + (1 - label) * log(1 - out)
loss = MakeLoss(cross_entropy)
pred_loss = mx.sym.Group([mx.sym.BlockGrad(y), loss])
ex = pred_loss.simple_bind(mx.cpu(), data=(32, 2))

# test
test_data = mx.nd.array(np.random.random(size=(32, 2)))
test_label = mx.nd.array(np.random.random(size=(32, 1)))

ex.forward(is_train=True, data=test_data, label=test_label)
ex.backward()

print ex.arg_dict
fc_w = ex.arg_dict['fullyconnected0_weight'].asnumpy()
fc_w_grad = ex.grad_arrays[1].asnumpy()
fc_bias = ex.arg_dict['fullyconnected0_bias'].asnumpy()
fc_bias_grad = ex.grad_arrays[2].asnumpy()

logging.info('fc_weight:{}, fc_weights_grad:{}'.format(fc_w, fc_w_grad))
logging.info('fc_bias:{}, fc_bias_grad:{}'.format(fc_bias, fc_bias_grad))

使用makeloss只能得到损失而不是预测，要得到损失和预测需要使用mx.sym.Group()和mx.sym.BlockGrad()
https://stackoverflow.com/questions/42304820/how-to-weight-observations-in-mxnet/42323339#42323339
{

label = mx.sym.Variable('label')
out = mx.sym.Activation(data=final, act_type='sigmoid')
ce = label * mx.sym.log(out) + (1 - label) * mx.sym.log(1 - out)
weights = mx.sym.Variable('weights')
loss = mx.sym.MakeLoss(weigths * ce, normalization='batch')

Then you want to input your weight vector into the weights Variable along with your normal input data and labels.

As an added tip, the output of an mxnet network with a custom loss via MakeLoss outputs the loss, not the prediction. You’ll probably want both in practice, in which case its useful to group the loss with a gradient-blocked version of the prediction so that you can get both. You’d do that like this:
pred_loss = mx.sym.Group([mx.sym.BlockGrad(out), loss])
}

---

用mxnet.metric.create(metric, *args, **kwargs)创建自己的评估标准

or

通过继承mx.metric.EvalMetric类添加自己的损失函数和评估验证函数

class Siamise_metric(mx.metric.EvalMetric):

    def __init__(self, name='siamise_acc'):
        super(Siamise_metric, self).__init__(name=name)

    def update(self, label, pred):
        preds = pred[0]
        labels = label[0]
        preds_label = preds.asnumpy().ravel()
        labels = labels.asnumpy().ravel()
        #self.sum_metric += labels[preds_label < 0.5].sum() + len(
        #    labels[preds_label >= 0.5]) - labels[preds_label >= 0.5].sum()
        #self.num_inst += len(labels)

        pred = (preds_label < 0.5)
        acc = (pred == labels).sum()
        self.sum_metric += acc
        self.num_inst += len(labels)  # numpy.prod(label.shape)


class Contrastive_loss(mx.metric.EvalMetric):
    def __init__(self, name='contrastive_loss'):
        super(Contrastive_loss, self).__init__(name=name)

    def update(self, label, pred):
        loss = pred[1].asnumpy()
        self.sum_metric += loss
        self.num_inst += len(loss)