# Copyright (c) OpenMMLab. All rights reserved.
import sys
import argparse
import time
import os
import torch
from mmcv import Config
from mmcv.parallel import MMDataParallel
from mmcv.runner import load_checkpoint, wrap_fp16_model

from mmdet3d.datasets import build_dataloader, build_dataset
from mmdet3d.models import build_detector
from tools.misc.fuse_conv_bn import fuse_module

sys.path.insert(0, os.getcwd())
print(sys.path)


def parse_args():
    parser = argparse.ArgumentParser(description='MMDet benchmark a model')
    parser.add_argument('config', help='test config file path')
    parser.add_argument('checkpoint', help='checkpoint file')
    parser.add_argument('--samples', default=500, help='samples to benchmark')
    parser.add_argument(
        '--log-interval', default=50, help='interval of logging')
    parser.add_argument(
        '--fuse-conv-bn',
        action='store_true',
        help='Whether to fuse conv and bn, this will slightly increase'
        'the inference speed')
    parser.add_argument(
        '--w_pano',
        action='store_true')
    parser.add_argument(
        '--w_panoproc',
        action='store_true')
    parser.add_argument(
        '--no-acceleration',
        action='store_true',
        help='Omit the pre-computation acceleration')
    args = parser.parse_args()
    return args

def main():
    args = parse_args()

    cfg = 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

    # import modules from plguin/xx, registry will be updated
    if hasattr(cfg, 'plugin'):
        if cfg.plugin:
            import importlib
            if hasattr(cfg, 'plugin_dir'):
                plugin_dir = cfg.plugin_dir
                _module_dir = os.path.dirname(plugin_dir)
                _module_dir = _module_dir.split('/')
                _module_path = _module_dir[0]

                for m in _module_dir[1:]:
                    _module_path = _module_path + '.' + m
                print(_module_path)
                plg_lib = importlib.import_module(_module_path)
            else:
                # import dir is the dirpath for the config file
                _module_dir = os.path.dirname(args.config)
                _module_dir = _module_dir.split('/')
                _module_path = _module_dir[0]
                for m in _module_dir[1:]:
                    _module_path = _module_path + '.' + m
                plg_lib = importlib.import_module(_module_path)

    # 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=0,
        dist=False,
        shuffle=False)

    # build the model and load checkpoint
    if not args.no_acceleration:
        cfg.model.img_view_transformer.accelerate=True
    cfg.model.train_cfg = None
    model = build_detector(cfg.model, test_cfg=cfg.get('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 args.fuse_conv_bn:
        model = fuse_module(model)

    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

    # benchmark with several samples and take the average
    # for i, data_ori in enumerate(data_loader):
    #     if i == 0:
    #         break
    # import copy
    # for i in range(500):
    #     data = copy.deepcopy(data_ori)
    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, 
                  w_pano=args.w_pano,
                  w_panoproc=args.w_panoproc,
                  **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}/ {args.samples}], '
                      f'fps: {fps:.1f} img / s')

        if (i + 1) == args.samples:
            pure_inf_time += elapsed
            fps = (i + 1 - num_warmup) / pure_inf_time
            print(f'Overall \nfps: {fps:.2f} img / s '
                  f'\ninference time: {1000 / fps:.2f} ms')
            break


if __name__ == '__main__':
    main()