import os
import onnx
import torch
import torch.nn as nn

from damo.config.base import parse_config
from damo.utils.model_utils import replace_module
from damo.base_models.core.ops import RepConv, SiLU
from damo.detectors.detector import build_local_model


class DeepStreamOutput(nn.Module):
    def __init__(self):
        super().__init__()

    def forward(self, x):
        boxes = x[1]
        scores, labels = torch.max(x[0], dim=-1, keepdim=True)
        return torch.cat([boxes, scores, labels.to(boxes.dtype)], dim=-1)


def suppress_warnings():
    import warnings
    warnings.filterwarnings('ignore', category=torch.jit.TracerWarning)
    warnings.filterwarnings('ignore', category=UserWarning)
    warnings.filterwarnings('ignore', category=DeprecationWarning)
    warnings.filterwarnings('ignore', category=FutureWarning)
    warnings.filterwarnings('ignore', category=ResourceWarning)


def damoyolo_export(weights, config_file, device):
    config = parse_config(config_file)
    config.model.head.export_with_post = True
    model = build_local_model(config, device)
    ckpt = torch.load(weights, map_location=device)
    model.eval()
    if 'model' in ckpt:
        ckpt = ckpt['model']
    model.load_state_dict(ckpt, strict=True)
    model = replace_module(model, nn.SiLU, SiLU)
    for layer in model.modules():
        if isinstance(layer, RepConv):
            layer.switch_to_deploy()
    model.head.nms = False
    return config, model


def main(args):
    suppress_warnings()

    print(f'\nStarting: {args.weights}')

    print('Opening DAMO-YOLO model')

    device = torch.device('cpu')
    cfg, model = damoyolo_export(args.weights, args.config, device)

    if len(cfg.dataset['class_names']) > 0:
        print('Creating labels.txt file')
        with open('labels.txt', 'w', encoding='utf-8') as f:
            for name in cfg.dataset['class_names']:
                f.write(f'{name}\n')

    model = nn.Sequential(model, DeepStreamOutput())

    img_size = args.size * 2 if len(args.size) == 1 else args.size

    onnx_input_im = torch.zeros(args.batch, 3, *img_size).to(device)
    onnx_output_file = f'{args.weights}.onnx'

    dynamic_axes = {
        'input': {
            0: 'batch'
        },
        'output': {
            0: 'batch'
        }
    }

    print('Exporting the model to ONNX')
    torch.onnx.export(
        model, onnx_input_im, onnx_output_file, verbose=False, opset_version=args.opset, do_constant_folding=True,
        input_names=['input'], output_names=['output'], dynamic_axes=dynamic_axes if args.dynamic else None
    )

    if args.simplify:
        print('Simplifying the ONNX model')
        import onnxslim
        model_onnx = onnx.load(onnx_output_file)
        model_onnx = onnxslim.slim(model_onnx)
        onnx.save(model_onnx, onnx_output_file)

    print(f'Done: {onnx_output_file}\n')


def parse_args():
    import argparse
    parser = argparse.ArgumentParser(description='DeepStream DAMO-YOLO conversion')
    parser.add_argument('-w', '--weights', required=True, help='Input weights (.pth) file path (required)')
    parser.add_argument('-c', '--config', required=True, help='Input config (.py) file path (required)')
    parser.add_argument('-s', '--size', nargs='+', type=int, default=[640], help='Inference size [H,W] (default [640])')
    parser.add_argument('--opset', type=int, default=11, help='ONNX opset version')
    parser.add_argument('--simplify', action='store_true', help='ONNX simplify model')
    parser.add_argument('--dynamic', action='store_true', help='Dynamic batch-size')
    parser.add_argument('--batch', type=int, default=1, help='Static batch-size')
    args = parser.parse_args()
    if not os.path.isfile(args.weights):
        raise SystemExit('Invalid weights file')
    if not os.path.isfile(args.config):
        raise SystemExit('Invalid config file')
    if args.dynamic and args.batch > 1:
        raise SystemExit('Cannot set dynamic batch-size and static batch-size at same time')
    return args


if __name__ == '__main__':
    args = parse_args()
    main(args)