Multi-index evaluation model ability for MXNET classification model Training (ACCURACY,CROSS-ENTROPY,TOP_K_ACCURACY)

Multi-index evaluation model ability for MXNET classification model Training (accuracy,cross-entropy,top_k_accuracy)
The code is as follows

    Metric=[mx.metric.create (' acc '),
        mx.metric.create (' top_k_accuracy ', top_k=3), mx.metric.create (' CE ')]
    Mod.fit (Train, Val,
        Num_epoch=num_epoch,
        arg_params=arg_params,
        aux_params=aux_params,
        allow_ Missing=true,
        batch_end_callback = Mx.callback.Speedometer (batch_size),
        epoch_end_callback= Checkpoint,
        kvstore= ' device ',
        optimizer= ' sgd ',
        optimizer_params={' learning_rate ': 0.00001, ' Momentum ": 0.9},
        initializer=mx.init.xavier (rnd_type= ' Gaussian ', factor_type=" in ", magnitude=2),
        Eval_ Metric=metric)

The results are as follows:

2017-09-06 16:46:25,648 epoch[0] Batch [$] speed:39.24 samples/sec accuracy=0.929890 t     op_k_accuracy_3=0.983782 cross-entropy=0.264878 2017-09-06 16:49:49,687 epoch[0] Batch [1000] speed:39.21 samples/sec   accuracy=0.949125 top_k_accuracy_3=0.987875 cross-entropy=0.215848 2017-09-06 16:53:13,980 Epoch[0] Batch [1500] speed:39.16 samples/sec accuracy=0.960625 top_k_accuracy_3=0.991625 cross-entropy=0.179014