# -*- coding: utf-8 -*-
# BSD 3-Clause License
#
# Copyright (c) 2017
# All rights reserved.
# Copyright 2022 Huawei Technologies Co., Ltd
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice, this
#   list of conditions and the following disclaimer.
#
# * Redistributions in binary form must reproduce the above copyright notice,
#   this list of conditions and the following disclaimer in the documentation
#   and/or other materials provided with the distribution.
#
# * Neither the name of the copyright holder nor the names of its
#   contributors may be used to endorse or promote products derived from
#   this software without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
# ==========================================================================

import argparse
import time

import torch
from mmcv import Config
from mmcv.parallel import MMDataParallel
from mmcv.runner import load_checkpoint

from mmseg.datasets import build_dataloader, build_dataset
from mmseg.models import build_segmentor


def parse_args():
    parser = argparse.ArgumentParser(description='MMSeg benchmark a model')
    parser.add_argument('config', help='test config file path')
    parser.add_argument('checkpoint', help='checkpoint file')
    parser.add_argument(
        '--log-interval', type=int, default=50, help='interval of logging')
    args = parser.parse_args()
    return args


def main():
    args = parse_args()

    cfg = Config.fromfile(args.config)
    # set cudnn_benchmark
    torch.backends.cudnn.benchmark = False
    cfg.model.pretrained = None
    cfg.data.test.test_mode = True

    # build the dataloader
    # TODO: support multiple images per gpu (only minor changes are needed)
    dataset = build_dataset(cfg.data.test)
    data_loader = build_dataloader(
        dataset,
        samples_per_gpu=1,
        workers_per_gpu=cfg.data.workers_per_gpu,
        dist=False,
        shuffle=False)

    # build the model and load checkpoint
    cfg.model.train_cfg = None
    model = build_segmentor(cfg.model, test_cfg=cfg.get('test_cfg'))
    load_checkpoint(model, args.checkpoint, map_location='cpu')

    model = MMDataParallel(model, device_ids=[0])

    model.eval()

    # the first several iterations may be very slow so skip them
    num_warmup = 5
    pure_inf_time = 0
    total_iters = 200

    # benchmark with 200 image and take the average
    for i, data in enumerate(data_loader):

        torch.cuda.synchronize()
        start_time = time.perf_counter()

        with torch.no_grad():
            model(return_loss=False, rescale=True, **data)

        torch.cuda.synchronize()
        elapsed = time.perf_counter() - start_time

        if i >= num_warmup:
            pure_inf_time += elapsed
            if (i + 1) % args.log_interval == 0:
                fps = (i + 1 - num_warmup) / pure_inf_time
                print(f'Done image [{i + 1:<3}/ {total_iters}], '
                      f'fps: {fps:.2f} img / s')

        if (i + 1) == total_iters:
            fps = (i + 1 - num_warmup) / pure_inf_time
            print(f'Overall fps: {fps:.2f} img / s')
            break


if __name__ == '__main__':
    main()