import argparse
import json
import os
import sys
from pathlib import Path
from threading import Thread
from functools import partial
import torch
import onnxruntime
import numpy as np
from tqdm import tqdm
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval

FILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # YOLOv5 root directory
if str(ROOT) not in sys.path:
    sys.path.append(str(ROOT))  # add ROOT to PATH
ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
import sys
import pathlib
CURRENT_DIR = pathlib.Path(__file__).parent
sys.path.append(str(CURRENT_DIR))
from utils import create_dataloader, coco80_to_coco91_class, check_dataset, box_iou, non_max_suppression, post_process, scale_coords, xyxy2xywh, xywh2xyxy, \
                  increment_path, colorstr, ap_per_class, ConfusionMatrix, output_to_target, plot_val_study, check_yaml


def save_one_txt(predn, save_conf, shape, file):
    # Save one txt result
    gn = torch.tensor(shape)[[1, 0, 1, 0]]  # normalization gain whwh
    for *xyxy, conf, cls in predn.tolist():
        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
        line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
        with open(file, 'a') as f:
            f.write(('%g ' * len(line)).rstrip() % line + '\n')


def save_one_json(predn, jdict, path, class_map):
    # Save one JSON result {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
    image_id = int(path.stem) if path.stem.isnumeric() else path.stem
    box = xyxy2xywh(predn[:, :4])  # xywh
    box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
    for p, b in zip(predn.tolist(), box.tolist()):
        jdict.append({'image_id': image_id,
                      'category_id': class_map[int(p[5])],
                      'bbox': [round(x, 3) for x in b],
                      'score': round(p[4], 5)})


def process_batch(detections, labels, iouv):
    """
    Return correct predictions matrix. Both sets of boxes are in (x1, y1, x2, y2) format.
    Arguments:
        detections (Array[N, 6]), x1, y1, x2, y2, conf, class
        labels (Array[M, 5]), class, x1, y1, x2, y2
    Returns:
        correct (Array[N, 10]), for 10 IoU levels
    """
    correct = torch.zeros(detections.shape[0], iouv.shape[0], dtype=torch.bool, device=iouv.device)
    iou = box_iou(labels[:, 1:], detections[:, :4])
    x = torch.where((iou >= iouv[0]) & (labels[:, 0:1] == detections[:, 5]))  # IoU above threshold and classes match
    if x[0].shape[0]:
        matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()  # [label, detection, iou]
        if x[0].shape[0] > 1:
            matches = matches[matches[:, 2].argsort()[::-1]]
            matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
            # matches = matches[matches[:, 2].argsort()[::-1]]
            matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
        matches = torch.Tensor(matches).to(iouv.device)
        correct[matches[:, 1].long()] = matches[:, 2:3] >= iouv
    return correct


def run(data,
        weights=None,  # model.pt path(s)
        batch_size=32,  # batch size
        imgsz=640,  # inference size (pixels)
        conf_thres=0.001,  # confidence threshold
        iou_thres=0.6,  # NMS IoU threshold
        task='val',  # train, val, test, speed or study
        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
        single_cls=False,  # treat as single-class dataset
        augment=False,  # augmented inference
        verbose=False,  # verbose output
        save_txt=False,  # save results to *.txt
        save_hybrid=False,  # save label+prediction hybrid results to *.txt
        save_conf=False,  # save confidences in --save-txt labels
        save_json=False,  # save a COCO-JSON results file
        project=ROOT / 'runs/val',  # save to project/name
        name='exp',  # save to project/name
        exist_ok=False,  # existing project/name ok, do not increment
        half=True,  # use FP16 half-precision inference
        nndct_quant=False,
        nndct_bitwidth=8,
        model=None,
        dataloader=None,
        save_dir=Path(''),
        plots=False,
        callbacks=None,
        compute_loss=None,
        quant_mode='calib',
        dump_xmodel=False,
        dump_onnx=False,
        dump_torch_script=False,
        nndct_stat=0,
        with_postprocess=False,
        onnx_runtime=True,
        onnx_weights="./yolov5s_qat.onnx",
        ipu=False,
        provider_config='',
        ):
    # Initialize/load model and set device
    device = torch.device('cpu')

    # Directories
    save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    # Load model
    if isinstance(onnx_weights, list):
        onnx_weights = onnx_weights[0]
    if ipu:
        providers = ["VitisAIExecutionProvider"]
        provider_options = [{"config_file": provider_config}]
        onnx_model = onnxruntime.InferenceSession(onnx_weights, providers=providers, provider_options=provider_options)
    else:
        onnx_model = onnxruntime.InferenceSession(onnx_weights)

    # Data
    data = check_dataset(data)  # check
    gs = 32  # grid size (max stride)

    is_coco = isinstance(data.get('val'), str) and data['val'].endswith('val2017.txt')  # COCO dataset
    nc = 1 if single_cls else int(data['nc'])  # number of classes
    iouv = torch.linspace(0.5, 0.95, 10).to(device)  # iou vector for mAP@0.5:0.95
    niou = iouv.numel()

    # Dataloader
    pad = 0.0 if task == 'speed' else 0.5
    task = task if task in ('train', 'val', 'test') else 'val'  # path to train/val/test images
    dataloader = create_dataloader(data[task], imgsz, batch_size, gs, single_cls, pad=pad, rect=False,
                                    prefix=colorstr(f'{task}: '), workers=8)[0]

    seen = 0
    names = ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
        'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
        'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
        'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
        'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
        'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
        'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
        'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
        'hair drier', 'toothbrush'] 
    class_map = coco80_to_coco91_class() if is_coco else list(range(1000))
    s = ('%20s' + '%11s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
    dt, p, r, f1, mp, mr, map50, map = [0.0, 0.0, 0.0], 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
    loss = torch.zeros(3, device=device)
    jdict, stats, ap, ap_class = [], [], [], []                                      

    for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s, total=len(dataloader))):
        img = img.to(device, non_blocking=True)
        img = img.half() if half else img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        targets = targets.to(device)
        nb, _, height, width = img.shape  # batch size, channels, height, width
        # outputs = onnx_model.run(None, {onnx_model.get_inputs()[0].name: img.cpu().numpy()})
        outputs = onnx_model.run(None, {onnx_model.get_inputs()[0].name: img.permute(0, 2, 3, 1).cpu().numpy()})
        # outputs = [torch.tensor(item).to(device) for item in outputs]
        outputs = [torch.tensor(item).permute(0, 3, 1, 2).to(device) for item in outputs]
        outputs = post_process(outputs)
        out, train_out = outputs[0], outputs[1]

        # Run NMS
        targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device)  # to pixels
        lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
        out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)

        # Statistics per image
        for si, pred in enumerate(out):
            labels = targets[targets[:, 0] == si, 1:]
            nl = len(labels)
            tcls = labels[:, 0].tolist() if nl else []  # target class
            path, shape = Path(paths[si]), shapes[si][0]
            seen += 1

            if len(pred) == 0:
                if nl:
                    stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
                continue

            # Predictions
            if single_cls:
                pred[:, 5] = 0
            predn = pred.clone()
            scale_coords(img[si].shape[1:], predn[:, :4], shape, shapes[si][1])  # native-space pred

            # Evaluate
            if nl:
                tbox = xywh2xyxy(labels[:, 1:5])  # target boxes
                scale_coords(img[si].shape[1:], tbox, shape, shapes[si][1])  # native-space labels
                labelsn = torch.cat((labels[:, 0:1], tbox), 1)  # native-space labels
                correct = process_batch(predn, labelsn, iouv)
            else:
                correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool)
            stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))  # (correct, conf, pcls, tcls)

            # Save/log
            if save_txt:
                save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / (path.stem + '.txt'))
            if save_json:
                save_one_json(predn, jdict, path, class_map)  # append to COCO-JSON dictionary

    # Compute statistics
    stats = [np.concatenate(x, 0) for x in zip(*stats)]  # to numpy
    if len(stats) and stats[0].any():
        p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
        ap50, ap = ap[:, 0], ap.mean(1)  # AP@0.5, AP@0.5:0.95
        mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
        nt = np.bincount(stats[3].astype(np.int64), minlength=nc)  # number of targets per class
    else:
        nt = torch.zeros(1)

    # Print results
    pf = '%20s' + '%11i' * 2 + '%11.3g' * 4  # print format
    print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))

    # Print results per class
    if (verbose or (nc < 50)) and nc > 1 and len(stats):
        for i, c in enumerate(ap_class):
            print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))

    # Save JSON
    if save_json and len(jdict):
        w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
        anno_json = str(Path(data.get('path', '../coco')) / 'annotations/instances_val2017.json')  # annotations json
        pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
        print(f'\nEvaluating pycocotools mAP... saving {pred_json}...')
        with open(pred_json, 'w') as f:
            json.dump(jdict, f)

        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
            anno = COCO(anno_json)  # init annotations api
            pred = anno.loadRes(pred_json)  # init predictions api
            eval = COCOeval(anno, pred, 'bbox')
            if is_coco:
                eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files]  # image IDs to evaluate
            eval.evaluate()
            eval.accumulate()
            eval.summarize()
            map, map50 = eval.stats[:2]  # update results (mAP@0.5:0.95, mAP@0.5)
        except Exception as e:
            print(f'pycocotools unable to run: {e}')

    s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
    print(f"Results saved to {colorstr('bold', save_dir)}{s}")
    maps = np.zeros(nc) + map
    for i, c in enumerate(ap_class):
        maps[c] = ap[i]
    return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, 0


def parse_opt():
    parser = argparse.ArgumentParser()
    parser.add_argument('--data', type=str, default='./coco.yaml', help='dataset.yaml path')
    parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)')
    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
    parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.001, help='confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.65, help='NMS IoU threshold')
    parser.add_argument('--task', default='val', help='train, val, test, speed or study')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--verbose', action='store_true', help='report mAP by class')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--save-json', action='store_true', help='save a COCO-JSON results file')
    parser.add_argument('--project', default=ROOT / 'runs/val', help='save to project/name')
    parser.add_argument('--name', default='exp', help='save to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
    parser.add_argument('--quant_mode', default='calib', help='nndct quant mode')
    parser.add_argument('--nndct_quant', action='store_true', help='use nndct quant model for inference')
    parser.add_argument('--dump_xmodel', action='store_true', help='dump nndct xmodel')
    parser.add_argument('--dump_onnx', action='store_true', help='dump nndct onnx xmodel')
    parser.add_argument('--with_postprocess', action='store_true', help='nndct model with postprocess')
    parser.add_argument('--onnx_runtime', default=True, action='store_true', help='onnx_runtime')
    parser.add_argument('-m', '--onnx_weights', default='./yolov5s_qat.onnx', nargs='+', type=str, help='onnx_weights')
    parser.add_argument('--nndct_stat', type=int, required=False, default=0)
    parser.add_argument('--ipu', action='store_true', help='flag for ryzen ai')
    parser.add_argument('--provider_config', default='', type=str, help='provider config for ryzen ai')
    opt = parser.parse_args()
    opt.save_json |= opt.data.endswith('coco.yaml')
    opt.save_txt |= opt.save_hybrid
    return opt


def main(opt):
    run(**vars(opt))


if __name__ == "__main__":
    opt = parse_opt()
    main(opt)