import argparse
import os

import mmcv
import torch
from mmcv.parallel import MMDataParallel, MMDistributedDataParallel
from mmcv.runner import get_dist_info, init_dist, load_checkpoint

from mmcls.apis import multi_gpu_test, single_gpu_test
from mmcls.core import wrap_fp16_model
from mmcls.datasets import build_dataloader, build_dataset
from mmcls.models import build_model


def parse_args():
    parser = argparse.ArgumentParser(description='mmcls test model')
    parser.add_argument('config', help='test config file path')
    parser.add_argument('checkpoint', help='checkpoint file')
    parser.add_argument('--out', help='output result file')
    parser.add_argument(
        '--eval',
        type=str,
        nargs='+',
        choices=['proposal', 'proposal_fast', 'bbox', 'segm', 'keypoints'],
        help='eval types')
    parser.add_argument(
        '--gpu_collect',
        action='store_true',
        help='whether to use gpu to collect results')
    parser.add_argument('--tmpdir', help='tmp dir for writing some results')
    parser.add_argument(
        '--launcher',
        choices=['none', 'pytorch', 'slurm', 'mpi'],
        default='none',
        help='job launcher')
    parser.add_argument('--local_rank', type=int, default=0)
    args = parser.parse_args()
    if 'LOCAL_RANK' not in os.environ:
        os.environ['LOCAL_RANK'] = str(args.local_rank)
    return args


def main():
    args = parse_args()

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

    # init distributed env first, since logger depends on the dist info.
    if args.launcher == 'none':
        distributed = False
    else:
        distributed = True
        init_dist(args.launcher, **cfg.dist_params)

    # 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,
        imgs_per_gpu=1,
        workers_per_gpu=cfg.data.workers_per_gpu,
        dist=distributed,
        shuffle=False)

    # build the model and load checkpoint
    model = build_model(cfg.model, train_cfg=None, test_cfg=cfg.test_cfg)
    fp16_cfg = cfg.get('fp16', None)
    if fp16_cfg is not None:
        wrap_fp16_model(model)
    _ = load_checkpoint(model, args.checkpoint, map_location='cpu')

    if not distributed:
        model = MMDataParallel(model, device_ids=[0])
        outputs = single_gpu_test(model, data_loader)
    else:
        model = MMDistributedDataParallel(
            model.cuda(),
            device_ids=[torch.cuda.current_device()],
            broadcast_buffers=False)
        outputs = multi_gpu_test(model, data_loader, args.tmpdir,
                                 args.gpu_collect)

    rank, _ = get_dist_info()
    if args.out and rank == 0:
        print(f'\nwriting results to {args.out}')
        mmcv.dump(outputs, args.out)


if __name__ == '__main__':
    main()