基于pytorch的YOLOv5单张图片检测实现

当我们训练完yolov5模型后，如何使用这个模型呢？这里简单写一下，可以看到大部分代码在detect.py中都可以找到，算是我自己对这个代码的改装吧，有需要的可以看看。

# coding=utf-8
import torch
import torchvision
import torch.nn as nn
import os
import time
import numpy as np
import math
import random
import cv2.cv2 as cv2

def autopad(k, p=None):  # kernel, padding
    # Pad to 'same'
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p

class Conv(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super(Conv, self).__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())

    def forward(self, x):
        return self.act(self.bn(self.conv(x)))

    def fuseforward(self, x):
        return self.act(self.conv(x))

class Ensemble(torch.nn.ModuleList):
    '''模型集成'''
    def __init__(self):
        super(Ensemble,self).__init__()

    def forward(self, x, augment=False):
        y = []
        for module in self:
            y.append(module(x, augment)[0])
        # y = torch.stack(y).max(0)[0] # max ensemble
        # y = torch.stack(y).mean(0) # mean ensemble
        y = torch.cat(y, 1)  # nms ensemble
        return y, None  # inference, train output

class YOLOV5(object):
    def __init__(self,conf_thres=0.25,
                 iou_thres=0.45,
                 classes=None,
                 imgsz=640,
                 weights="./weights/image_detect.pt"):
        # 超参数设置
        self.conf_thres=conf_thres#置信度阈值
        self.iou_thres=iou_thres#iou阈值
        self.classes=classes#分类个数
        self.imgsz=imgsz #归一化大小
        # Load model
        self.device=torch.device('cpu')
        self.model = self.attempt_load(weights,map_location=self.device)  # load FP32 model
        self.stride = int(self.model.stride.max())  # model stride
        self.imgsz = self.check_img_size(imgsz, s=self.stride)  # check img_size


    def attempt_load(self,weights, map_location=None):
        # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
        model = Ensemble()
        for w in weights if isinstance(weights, list) else [weights]:
            ckpt = torch.load(w, map_location=map_location)  # load
            model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval())  # FP32 model

        # Compatibility updates
        for m in model.modules():
            if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
                m.inplace = True  # pytorch 1.7.0 compatibility
            elif type(m) is Conv:
                m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility

        if len(model) == 1:
            return model[-1]  # return model
        else:
            print('Ensemble created with %s\n' % weights)
            for k in ['names', 'stride']:
                setattr(model, k, getattr(model[-1], k))
            return model  # return ensemble

    def make_divisible(self,x, divisor):
        # Returns x evenly divisible by divisor
        return math.ceil(x / divisor) * divisor

    def check_img_size(self,img_size, s=32):
        # Verify img_size is a multiple of stride s
        new_size = self.make_divisible(img_size, int(s))  # ceil gs-multiple
        if new_size != img_size:
            print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
        return new_size

    def letterbox(self,img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True,
                  stride=32):
        # Resize and pad image while meeting stride-multiple constraints
        shape = img.shape[:2]  # current shape [height, width]
        if isinstance(new_shape, int):
            new_shape = (new_shape, new_shape)

        # Scale ratio (new / old)
        r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
        if not scaleup:  # only scale down, do not scale up (for better test mAP)
            r = min(r, 1.0)

        # Compute padding
        ratio = r, r  # width, height ratios
        new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
        dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
        if auto:  # minimum rectangle
            dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
        elif scaleFill:  # stretch
            dw, dh = 0.0, 0.0
            new_unpad = (new_shape[1], new_shape[0])
            ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios

        dw /= 2  # divide padding into 2 sides
        dh /= 2

        if shape[::-1] != new_unpad:  # resize
            img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
        top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
        left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
        img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
        return img, ratio, (dw, dh)

    def box_iou(self,box1, box2):
        # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
        """ Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Arguments: box1 (Tensor[N, 4]) box2 (Tensor[M, 4]) Returns: iou (Tensor[N, M]): the NxM matrix containing the pairwise IoU values for every element in boxes1 and boxes2 """

        def box_area(box):
            # box = 4xn
            return (box[2] - box[0]) * (box[3] - box[1])

        area1 = box_area(box1.T)
        area2 = box_area(box2.T)

        # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
        inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
        return inter / (area1[:, None] + area2 - inter)  # iou = inter / (area1 + area2 - inter)

    def xywh2xyxy(self,x):
        # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
        y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
        y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
        y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
        y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
        y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
        return y

    def non_max_suppression(self,prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False,
                            multi_label=False,
                            labels=()):
        """Runs Non-Maximum Suppression (NMS) on inference results Returns: list of detections, on (n,6) tensor per image [xyxy, conf, cls] """

        nc = prediction.shape[2] - 5  # number of classes
        xc = prediction[..., 4] > conf_thres  # candidates

        # Settings
        min_wh, max_wh = 2, 4096  # (pixels) minimum and maximum box width and height
        max_det = 300  # maximum number of detections per image
        max_nms = 30000  # maximum number of boxes into torchvision.ops.nms()
        time_limit = 10.0  # seconds to quit after
        redundant = True  # require redundant detections
        multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)
        merge = False  # use merge-NMS

        t = time.time()
        output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
        for xi, x in enumerate(prediction):  # image index, image inference
            # Apply constraints
            # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
            x = x[xc[xi]]  # confidence

            # Cat apriori labels if autolabelling
            if labels and len(labels[xi]):
                l = labels[xi]
                v = torch.zeros((len(l), nc + 5), device=x.device)
                v[:, :4] = l[:, 1:5]  # box
                v[:, 4] = 1.0  # conf
                v[range(len(l)), l[:, 0].long() + 5] = 1.0  # cls
                x = torch.cat((x, v), 0)

            # If none remain process next image
            if not x.shape[0]:
                continue

            # Compute conf
            x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf

            # Box (center x, center y, width, height) to (x1, y1, x2, y2)
            box = self.xywh2xyxy(x[:, :4])

            # Detections matrix nx6 (xyxy, conf, cls)
            if multi_label:
                i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
                x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
            else:  # best class only
                conf, j = x[:, 5:].max(1, keepdim=True)
                x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]

            # Filter by class
            if classes is not None:
                x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]

            # Apply finite constraint
            # if not torch.isfinite(x).all():
            # x = x[torch.isfinite(x).all(1)]

            # Check shape
            n = x.shape[0]  # number of boxes
            if not n:  # no boxes
                continue
            elif n > max_nms:  # excess boxes
                x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence

            # Batched NMS
            c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
            boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
            i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
            if i.shape[0] > max_det:  # limit detections
                i = i[:max_det]
            if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
                # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
                iou = self.box_iou(boxes[i], boxes) > iou_thres  # iou matrix
                weights = iou * scores[None]  # box weights
                x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
                if redundant:
                    i = i[iou.sum(1) > 1]  # require redundancy

            output[xi] = x[i]
            if (time.time() - t) > time_limit:
                print(f'WARNING: NMS time limit {time_limit}s exceeded')
                break  # time limit exceeded

        return output

    def clip_coords(self,boxes, img_shape):
        # Clip bounding xyxy bounding boxes to image shape (height, width)
        boxes[:, 0].clamp_(0, img_shape[1])  # x1
        boxes[:, 1].clamp_(0, img_shape[0])  # y1
        boxes[:, 2].clamp_(0, img_shape[1])  # x2
        boxes[:, 3].clamp_(0, img_shape[0])  # y2

    def scale_coords(self,img1_shape, coords, img0_shape, ratio_pad=None):
        # Rescale coords (xyxy) from img1_shape to img0_shape
        if ratio_pad is None:  # calculate from img0_shape
            gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain = old / new
            pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
        else:
            gain = ratio_pad[0][0]
            pad = ratio_pad[1]

        coords[:, [0, 2]] -= pad[0]  # x padding
        coords[:, [1, 3]] -= pad[1]  # y padding
        coords[:, :4] /= gain
        self.clip_coords(coords, img0_shape)
        return coords

    def plot_one_box(self,x, img, color=None, label=None, line_thickness=3):
        # Plots one bounding box on image img
        tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line/font thickness
        color = color or [random.randint(0, 255) for _ in range(3)]
        c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
        cv2.rectangle(img, c1, c2, color, thickness=tl, lineType=cv2.LINE_AA)
        if label:
            tf = max(tl - 1, 1)  # font thickness
            t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
            c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
            cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA)  # filled
            cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA)

    def infer(self,img_path,agnostic_nms=False):
        # read image
        image=cv2.imread(img_path)

        # Padded resize
        img = self.letterbox(image, self.imgsz, stride=self.stride)[0]

        # Convert
        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
        img = np.ascontiguousarray(img)

        img = torch.from_numpy(img).to(self.device)
        img = img.float()  # uint8 to fp16/32
        img /= 255.0  # 0 - 255 to 0.0 - 1.0
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        # Inference
        pred = self.model(img, augment=False)[0]

        # Apply NMS
        pred = self.non_max_suppression(pred, self.conf_thres, self.iou_thres, classes=None, agnostic=agnostic_nms)


        # Process detections
        s=""
        s += '%gx%g ' % img.shape[2:]  # print string
        result=[]
        for i, det in enumerate(pred):  # detections per image
            # Rescale boxes from img_size to im0 size
            det[:, :4] = self.scale_coords(img.shape[2:], det[:, :4], image.shape).round()

            for *xyxy, conf, cls in reversed(det):
                x1,y1,x2,y2= int(xyxy[0]), int(xyxy[1]), int(xyxy[2]), int(xyxy[3])
                result.append([x1,y1,x2,y2])


            # Print results
            for c in det[:, -1].unique():
                n = (det[:, -1] == c).sum()  # detections per class
                s += f"{n} {img_path}{'s' * (n > 1)}, "  # add to string

                # Write results
                # Get names and colors
                names = self.model.module.names if hasattr(self.model, 'module') else self.model.names
                colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
                for *xyxy, conf, cls in reversed(det):
                    label = f'{names[int(cls)]} {conf:.2f}'
                    self.plot_one_box(xyxy, image, label=label, color=colors[int(cls)], line_thickness=3)


        # 显示预测结果
        print(s)
        print(result)
        cv2.namedWindow("result",0)
        cv2.imshow("result", image)
        cv2.waitKey(0)  # 1 millisecond

        #后处理

        return result

if __name__=="__main__":
    yolov5=YOLOV5()
    yolov5.infer("data/1.png")

这是我自己训练的图片检测模型，结果如下：

github链接：yolov5前向推理实现
参考链接：
yolov5
onnxruntime-for-yolov5