import torch
import numpy as np

from yolov5.models.experimental import attempt_load
from yolov5.utils.datasets import letterbox
from yolov5.utils.general import non_max_suppression, scale_coords
from yolov5.utils.torch_utils import select_device


class Detector:

    def __init__(self, img_size, view_img_size,weights):
        self.img_size = img_size
        self.view_img_size=view_img_size
        self.threshold = 0.3
        self.stride = 1

        self.weights =weights

        self.device = '0' if torch.cuda.is_available() else 'cpu'
        self.device = select_device(self.device)
      
       
        half = self.device != 'cpu'  # half precision only supported on CUDA

        # Load model
        model = torch.load(self.weights, map_location=self.device)[
            'model'].float()  # load to FP32
        model.to(self.device).eval()
        if half:
            model.half()  # to FP16

        self.m = model
        self.names = model.module.names if hasattr(
            model, 'module') else model.names

    def preprocess(self, img):

        # img0 = img.copy()
        img = letterbox(img, new_shape=self.img_size)[0]
        img = img[:, :, ::-1].transpose(2, 0, 1)
        img = np.ascontiguousarray(img)
        img = torch.from_numpy(img).to(self.device)
        img = img.half()
        img /= 255.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        return img

    def detect(self, im):

        img = self.preprocess(im)

        pred = self.m(img, augment=False)[0]
        # pred = pred.float()
        # pred = non_max_suppression(pred, self.threshold, 0.4)
        return  img,pred
        # boxes = []
        # for det in pred:

        #     if det is not None and len(det):
        #         det[:, :4] = scale_coords(
        #             img.shape[2:], det[:, :4], im0.shape).round()

        #         for *x, conf, cls_id in det:
        #             lbl = self.names[int(cls_id)]
        #             print(lbl,':'+str(conf))
        #             if float(conf)<0.5:
        #                 continue
        #             if lbl not in ['person', 'bicycle', 'car', 'motorcycle', 'bus', 'truck','dog']:
        #                 continue
        #             pass
        #             x1, y1 = int(x[0]), int(x[1])
        #             x2, y2 = int(x[2]), int(x[3])
        #             boxes.append(
        #                 (x1, y1, x2, y2, cls_id, conf,lbl))

        # return boxes