# Copyright 2021 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.
# ============================================================================

from maskrcnn_benchmark.utils.env import setup_environment  # noqa F401 isort:skip

import argparse
import os
from apex import amp

import torch.npu
import torch
from maskrcnn_benchmark.config import cfg
from maskrcnn_benchmark.data import make_data_loader
from maskrcnn_benchmark.solver import make_lr_scheduler
from maskrcnn_benchmark.solver import make_optimizer
from maskrcnn_benchmark.engine.inference import inference
from maskrcnn_benchmark.engine.trainer import do_train
from maskrcnn_benchmark.modeling.detector import build_detection_model
from maskrcnn_benchmark.utils.checkpoint import DetectronCheckpointer
from maskrcnn_benchmark.utils.collect_env import collect_env_info
from maskrcnn_benchmark.utils.comm import synchronize, get_rank
from maskrcnn_benchmark.utils.logger import setup_logger
from maskrcnn_benchmark.utils.miscellaneous import mkdir


def train(cfg, local_rank, distributed, device):
    model = build_detection_model(cfg)

    model = model.to(device)

    optimizer = make_optimizer(cfg, model)
    if cfg.AMP:
        model, optimizer = amp.initialize(model, optimizer, opt_level=cfg.OPT_LEVEL, loss_scale=cfg.LOSS_SCALE_VALUE,
                                          combine_grad=True)
    scheduler = make_lr_scheduler(cfg, optimizer)

    if distributed:
        model = torch.nn.parallel.DistributedDataParallel(
            model, device_ids=[local_rank], broadcast_buffers=False
        )

    arguments = {}
    arguments["iteration"] = 0

    output_dir = cfg.OUTPUT_DIR

    save_to_disk = get_rank() == 0
    checkpointer = DetectronCheckpointer(
        cfg, model, optimizer, scheduler, output_dir, save_to_disk
    )
    extra_checkpoint_data = checkpointer.load(cfg.MODEL.WEIGHT)
    arguments.update(extra_checkpoint_data)

    data_loader = make_data_loader(
        cfg,
        is_train=True,
        is_distributed=distributed,
        start_iter=arguments["iteration"]
    )

    checkpoint_period = cfg.SOLVER.CHECKPOINT_PERIOD

    do_train(
        model,
        data_loader,
        optimizer,
        scheduler,
        checkpointer,
        device,
        checkpoint_period,
        arguments,
        cfg.AMP,
        local_rank
    )

    return model


def test(cfg, model, distributed):
    if distributed:
        model = model.module
    torch.cuda.empty_cache()  # TODO check if it helps
    iou_types = ("bbox",)
    if cfg.MODEL.MASK_ON:
        iou_types = iou_types + ("segm",)
    output_folders = [None] * len(cfg.DATASETS.TEST)
    if cfg.OUTPUT_DIR:
        dataset_names = cfg.DATASETS.TEST
        for idx, dataset_name in enumerate(dataset_names):
            output_folder = os.path.join(cfg.OUTPUT_DIR, "inference", dataset_name)
            mkdir(output_folder)
            output_folders[idx] = output_folder
    data_loaders_val = make_data_loader(cfg, is_train=False, is_distributed=distributed)
    for output_folder, data_loader_val in zip(output_folders, data_loaders_val):
        inference(
            model,
            data_loader_val,
            iou_types=iou_types,
            # box_only=cfg.MODEL.RPN_ONLY,
            box_only=False if cfg.RETINANET.RETINANET_ON else cfg.MODEL.RPN_ONLY,
            device=cfg.MODEL.DEVICE,
            expected_results=cfg.TEST.EXPECTED_RESULTS,
            expected_results_sigma_tol=cfg.TEST.EXPECTED_RESULTS_SIGMA_TOL,
            output_folder=output_folder,
        )
        synchronize()


def main():
    parser = argparse.ArgumentParser(description="PyTorch Object Detection Training")
    parser.add_argument(
        "--config-file",
        default="",
        metavar="FILE",
        help="path to config file",
        type=str,
    )
    parser.add_argument("--local_rank", type=int, default=0)
    parser.add_argument("--data_path", type=str, default='')
    parser.add_argument(
        "--skip-test",
        dest="skip_test",
        help="Do not test the final model",
        action="store_true",
    )
    parser.add_argument(
        "opts",
        help="Modify config options using the command-line",
        default=None,
        nargs=argparse.REMAINDER,
    )

    args = parser.parse_args()

    num_gpus = int(os.environ["WORLD_SIZE"]) if "WORLD_SIZE" in os.environ else 1
    args.distributed = num_gpus > 1
    device = 'npu:{}'.format(args.local_rank)
    torch.npu.set_device(device)
    if args.distributed:
        host_addr_full = 'tcp://' + os.environ["MASTER_ADDR"] + ':' + os.environ["MASTER_PORT"]
        rank = int(os.environ['RANK'])
        world_size = int(os.environ["WORLD_SIZE"])
        print(host_addr_full, rank, world_size)
        # init_method = host_addr_full,
        torch.distributed.init_process_group(backend=cfg.DIST_BACKEND, rank=rank, world_size=world_size)

    cfg.DATASETS.DATA_DIR = args.data_path
    cfg.merge_from_file(args.config_file)
    cfg.merge_from_list(args.opts)
    cfg.freeze()

    output_dir = cfg.OUTPUT_DIR
    if output_dir:
        mkdir(output_dir)

    logger = setup_logger("maskrcnn_benchmark", output_dir, get_rank())
    logger.info("Using {} GPUs".format(num_gpus))
    logger.info(args)

    logger.info("Collecting env info (might take some time)")
    logger.info("\n" + collect_env_info())

    logger.info("Loaded configuration file {}".format(args.config_file))
    with open(args.config_file, "r") as cf:
        config_str = "\n" + cf.read()
        logger.info(config_str)
    logger.info("Running with config:\n{}".format(cfg))

    model = train(cfg, args.local_rank, args.distributed, device)

    if not args.skip_test:
        test(cfg, model, args.distributed)


if __name__ == "__main__":
    main()