mindspore2022/mindspore/train/callback/_loss_monitor.py

# Copyright 2020 Huawei Technologies Co., Ltd
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
"""LossMonitor Callback class."""

import numpy as np
from mindspore.common.tensor import Tensor

from ._callback import Callback


class LossMonitor(Callback):
    """
    Monitor the loss in training.

    If the loss is NAN or INF, it will terminate training.

    Note:
        If per_print_times is 0, do not print loss.

    Args:
        per_print_times (int): Print the loss each every time. Default: 1.

    Raises:
        ValueError: If print_step is not an integer or less than zero.
    """

    def __init__(self, per_print_times=1):
        super(LossMonitor, self).__init__()
        if not isinstance(per_print_times, int) or per_print_times < 0:
            raise ValueError("print_step must be int and >= 0.")
        self._per_print_times = per_print_times

    def step_end(self, run_context):
        cb_params = run_context.original_args()
        loss = cb_params.net_outputs

        if isinstance(loss, (tuple, list)):
            if isinstance(loss[0], Tensor) and isinstance(loss[0].asnumpy(), np.ndarray):
                loss = loss[0]

        if isinstance(loss, Tensor) and isinstance(loss.asnumpy(), np.ndarray):
            loss = np.mean(loss.asnumpy())

        cur_step_in_epoch = (cb_params.cur_step_num - 1) % cb_params.batch_num + 1

        if isinstance(loss, float) and (np.isnan(loss) or np.isinf(loss)):
            raise ValueError("epoch: {} step: {}. Invalid loss, terminating training.".format(
                cb_params.cur_epoch_num, cur_step_in_epoch))
        if self._per_print_times != 0 and cb_params.cur_step_num % self._per_print_times == 0:
            print("epoch: %s step: %s, loss is %s" % (cb_params.cur_epoch_num, cur_step_in_epoch, loss), flush=True)