环境要求

我的版本是YOLOV5 7.0

先看结果：

结果仅供参考

具体步骤一：

首先配置好YOLO V5环境
这个采用pip install requirements即可
具体配置环境可以看我其他的博客有详细介绍
GPU环境自己配置

步骤二：

运行YOLO 没问题，输出结果：

步骤三

在项目文件夹下添加main_gradcam.py文件

main_gradcam.py

import os
import random
import time
import argparse
import numpy as np
from models.gradcam import YOLOV5GradCAM, YOLOV5GradCAMPP
from models.yolov5_object_detector import YOLOV5TorchObjectDetector
import cv2
# 数据集类别名
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 names
# yolov5s网络中的三个detect层
target_layers = ['model_17_cv3_act', 'model_20_cv3_act', 'model_23_cv3_act']

# Arguments
parser = argparse.ArgumentParser()
parser.add_argument('--model-path', type=str, default="yolov5s.pt", help='Path to the model')
parser.add_argument('--img-path', type=str, default='data/images/bus.jpg', help='input image path')
parser.add_argument('--output-dir', type=str, default='runs/result17', help='output dir')
parser.add_argument('--img-size', type=int, default=640, help="input image size")
parser.add_argument('--target-layer', type=str, default='model_17_cv3_act',
                    help='The layer hierarchical address to which gradcam will applied,'
                         ' the names should be separated by underline')
parser.add_argument('--method', type=str, default='gradcam', help='gradcam method')
parser.add_argument('--device', type=str, default='cuda', help='cuda or cpu')
parser.add_argument('--no_text_box', action='store_true',
                    help='do not show label and box on the heatmap')
args = parser.parse_args()


def get_res_img(bbox, mask, res_img):
    mask = mask.squeeze(0).mul(255).add_(0.5).clamp_(0, 255).permute(1, 2, 0).detach().cpu().numpy().astype(
        np.uint8)
    heatmap = cv2.applyColorMap(mask, cv2.COLORMAP_JET)
    # n_heatmat = (Box.fill_outer_box(heatmap, bbox) / 255).astype(np.float32)
    n_heatmat = (heatmap / 255).astype(np.float32)
    res_img = res_img / 255
    res_img = cv2.add(res_img, n_heatmat)
    res_img = (res_img / res_img.max())
    return res_img, n_heatmat


def plot_one_box(x, img, color=None, label=None, line_thickness=3):
    # this is a bug in cv2. It does not put box on a converted image from torch unless it's buffered and read again!
    cv2.imwrite('temp.jpg', (img * 255).astype(np.uint8))
    img = cv2.imread('temp.jpg')

    # 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]
        outside = c1[1] - t_size[1] - 3 >= 0  # label fits outside box up
        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3 if outside else c1[1] + t_size[1] + 3
        outsize_right = c2[0] - img.shape[:2][1] > 0  # label fits outside box right
        c1 = c1[0] - (c2[0] - img.shape[:2][1]) if outsize_right else c1[0], c1[1]
        c2 = c2[0] - (c2[0] - img.shape[:2][1]) if outsize_right else c2[0], c2[1]
        cv2.rectangle(img, c1, c2, color, -1, cv2.LINE_AA)  # filled
        cv2.putText(img, label, (c1[0], c1[1] - 2 if outside else c2[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf,
                    lineType=cv2.LINE_AA)
    return img


# 检测单个图片
def main(img_path):
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
    device = args.device
    input_size = (args.img_size, args.img_size)
    # 读入图片
    img = cv2.imread(img_path)  # 读取图像格式：BGR
    print('[INFO] Loading the model')
    # 实例化YOLOv5模型，得到检测结果
    model = YOLOV5TorchObjectDetector(args.model_path, device, img_size=input_size, names=names)
    # img[..., ::-1]: BGR --> RGB
    # (480, 640, 3) --> (1, 3, 480, 640)
    torch_img = model.preprocessing(img[..., ::-1])
    tic = time.time()
    # 遍历三层检测层
    for target_layer in target_layers:
        # 获取grad-cam方法
        if args.method == 'gradcam':
            saliency_method = YOLOV5GradCAM(model=model, layer_name=target_layer, img_size=input_size)
        elif args.method == 'gradcampp':
            saliency_method = YOLOV5GradCAMPP(model=model, layer_name=target_layer, img_size=input_size)
        masks, logits, [boxes, _, class_names, conf] = saliency_method(torch_img)  # 得到预测结果
        result = torch_img.squeeze(0).mul(255).add_(0.5).clamp_(0, 255).permute(1, 2, 0).detach().cpu().numpy()
        result = result[..., ::-1]  # convert to bgr
        # 保存设置
        imgae_name = os.path.basename(img_path)  # 获取图片名
        save_path = f'{args.output_dir}{imgae_name[:-4]}/{args.method}'
        if not os.path.exists(save_path):
            os.makedirs(save_path)
        print(f'[INFO] Saving the final image at {save_path}')
        # 遍历每张图片中的每个目标
        for i, mask in enumerate(masks):
            # 遍历图片中的每个目标
            res_img = result.copy()
            # 获取目标的位置和类别信息
            bbox, cls_name = boxes[0][i], class_names[0][i]
            label = f'{cls_name} {conf[0][i]}'  # 类别+置信分数
            # 获取目标的热力图
            res_img, heat_map = get_res_img(bbox, mask, res_img)
            res_img = plot_one_box(bbox, res_img, label=label, color=colors[int(names.index(cls_name))],
                                   line_thickness=3)
            # 缩放到原图片大小
            res_img = cv2.resize(res_img, dsize=(img.shape[:-1][::-1]))
            output_path = f'{save_path}/{target_layer[6:8]}_{i}.jpg'
            cv2.imwrite(output_path, res_img)
            print(f'{target_layer[6:8]}_{i}.jpg done!!')
    print(f'Total time : {round(time.time() - tic, 4)} s')


if __name__ == '__main__':
    # 图片路径为文件夹
    if os.path.isdir(args.img_path):
        img_list = os.listdir(args.img_path)
        print(img_list)
        for item in img_list:
            # 依次获取文件夹中的图片名，组合成图片的路径
            main(os.path.join(args.img_path, item))
    # 单个图片
    else:
        main(args.img_path)

步骤四

在model文件夹下添加如下两个py文件，分别是gradcam.py和yolov5_object_detector.py

gradcam.py代码如下：

import time
import torch
import torch.nn.functional as F


def find_yolo_layer(model, layer_name):
    """Find yolov5 layer to calculate GradCAM and GradCAM++

    Args:
        model: yolov5 model.
        layer_name (str): the name of layer with its hierarchical information.

    Return:
        target_layer: found layer
    """
    hierarchy = layer_name.split('_')
    target_layer = model.model._modules[hierarchy[0]]

    for h in hierarchy[1:]:
        target_layer = target_layer._modules[h]
    return target_layer


class YOLOV5GradCAM:
    # 初始化，得到target_layer层
    def __init__(self, model, layer_name, img_size=(640, 640)):
        self.model = model
        self.gradients = dict()
        self.activations = dict()

        def backward_hook(module, grad_input, grad_output):
            self.gradients['value'] = grad_output[0]
            return None

        def forward_hook(module, input, output):
            self.activations['value'] = output
            return None

        target_layer = find_yolo_layer(self.model, layer_name)
        # 获取forward过程中每层的输入和输出，用于对比hook是不是正确记录
        target_layer.register_forward_hook(forward_hook)
        target_layer.register_full_backward_hook(backward_hook)
        device = 'cuda' if next(self.model.model.parameters()).is_cuda else 'cpu'
        self.model(torch.zeros(1, 3, *img_size, device=device))

    def forward(self, input_img, class_idx=True):
        """
        Args:
            input_img: input image with shape of (1, 3, H, W)
        Return:
            mask: saliency map of the same spatial dimension with input
            logit: model output
            preds: The object predictions
        """
        saliency_maps = []
        b, c, h, w = input_img.size()
        preds, logits = self.model(input_img)
        for logit, cls, cls_name in zip(logits[0], preds[1][0], preds[2][0]):
            if class_idx:
                score = logit[cls]
            else:
                score = logit.max()
            self.model.zero_grad()
            tic = time.time()
            # 获取梯度
            score.backward(retain_graph=True)
            print(f"[INFO] {cls_name}, model-backward took: ", round(time.time() - tic, 4), 'seconds')
            gradients = self.gradients['value']
            activations = self.activations['value']
            b, k, u, v = gradients.size()
            alpha = gradients.view(b, k, -1).mean(2)
            weights = alpha.view(b, k, 1, 1)
            saliency_map = (weights * activations).sum(1, keepdim=True)
            saliency_map = F.relu(saliency_map)
            saliency_map = F.interpolate(saliency_map, size=(h, w), mode='bilinear', align_corners=False)
            saliency_map_min, saliency_map_max = saliency_map.min(), saliency_map.max()
            saliency_map = (saliency_map - saliency_map_min).div(saliency_map_max - saliency_map_min).data
            saliency_maps.append(saliency_map)
        return saliency_maps, logits, preds

    def __call__(self, input_img):
        return self.forward(input_img)


class YOLOV5GradCAMPP(YOLOV5GradCAM):
    def __init__(self, model, layer_name, img_size=(640, 640)):
        super(YOLOV5GradCAMPP, self).__init__(model, layer_name, img_size)

    def forward(self, input_img, class_idx=True):
        saliency_maps = []
        b, c, h, w = input_img.size()
        tic = time.time()
        preds, logits = self.model(input_img)
        print("[INFO] model-forward took: ", round(time.time() - tic, 4), 'seconds')
        for logit, cls, cls_name in zip(logits[0], preds[1][0], preds[2][0]):
            if class_idx:
                score = logit[cls]
            else:
                score = logit.max()
            self.model.zero_grad()
            tic = time.time()
            # 获取梯度
            score.backward(retain_graph=True)
            print(f"[INFO] {cls_name}, model-backward took: ", round(time.time() - tic, 4), 'seconds')
            gradients = self.gradients['value']  # dS/dA
            activations = self.activations['value']  # A
            b, k, u, v = gradients.size()

            alpha_num = gradients.pow(2)
            alpha_denom = gradients.pow(2).mul(2) + \
                          activations.mul(gradients.pow(3)).view(b, k, u * v).sum(-1, keepdim=True).view(b, k, 1, 1)
            # torch.where(condition, x, y) condition是条件，满足条件就返回x，不满足就返回y
            alpha_denom = torch.where(alpha_denom != 0.0, alpha_denom, torch.ones_like(alpha_denom))
            alpha = alpha_num.div(alpha_denom + 1e-7)

            positive_gradients = F.relu(score.exp() * gradients)  # ReLU(dY/dA) == ReLU(exp(S)*dS/dA))
            weights = (alpha * positive_gradients).view(b, k, u * v).sum(-1).view(b, k, 1, 1)

            saliency_map = (weights * activations).sum(1, keepdim=True)
            saliency_map = F.relu(saliency_map)
            saliency_map = F.interpolate(saliency_map, size=(h, w), mode='bilinear', align_corners=False)
            saliency_map_min, saliency_map_max = saliency_map.min(), saliency_map.max()
            saliency_map = (saliency_map - saliency_map_min).div(saliency_map_max - saliency_map_min).data
            saliency_maps.append(saliency_map)
        return saliency_maps, logits, preds

yolov5_object_detector.py的代码如下：

import numpy as np
import torch
from models.experimental import attempt_load
from utils.general import xywh2xyxy
from utils.dataloaders import letterbox
import cv2
import time
import torchvision
import torch.nn as nn
from utils.metrics import box_iou


class YOLOV5TorchObjectDetector(nn.Module):
    def __init__(self,
                 model_weight,
                 device,
                 img_size,
                 names=None,
                 mode='eval',
                 confidence=0.45,
                 iou_thresh=0.45,
                 agnostic_nms=False):
        super(YOLOV5TorchObjectDetector, self).__init__()
        self.device = device
        self.model = None
        self.img_size = img_size
        self.mode = mode
        self.confidence = confidence
        self.iou_thresh = iou_thresh
        self.agnostic = agnostic_nms
        self.model = attempt_load(model_weight, inplace=False, fuse=False)
        self.model.requires_grad_(True)
        self.model.to(device)

        if self.mode == 'train':
            self.model.train()
        else:
            self.model.eval()
        # fetch the names
        if names is None:
            self.names = ['your dataset classname']
        else:
            self.names = names

        # preventing cold start
        img = torch.zeros((1, 3, *self.img_size), device=device)
        self.model(img)

    @staticmethod
    def non_max_suppression(prediction, logits, conf_thres=0.3, iou_thres=0.45, classes=None, agnostic=False,
                            multi_label=False, labels=(), max_det=300):
        """Runs Non-Maximum Suppression (NMS) on inference and logits results

        Returns:
             list of detections, on (n,6) tensor per image [xyxy, conf, cls] and pruned input logits (n, number-classes)
        """

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

        # Checks
        assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
        assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'

        # Settings
        min_wh, max_wh = 2, 4096  # (pixels) minimum and maximum box width and height
        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]
        logits_output = [torch.zeros((0, nc), device=logits.device)] * logits.shape[0]
        # logits_output = [torch.zeros((0, 80), device=logits.device)] * logits.shape[0]
        for xi, (x, log_) in enumerate(zip(prediction, logits)):  # 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
            log_ = log_[xc[xi]]
            # 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 = 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]
                log_ = log_[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)]

            # 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 = 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]
            logits_output[xi] = log_[i]
            assert log_[i].shape[0] == x[i].shape[0]
            if (time.time() - t) > time_limit:
                print(f'WARNING: NMS time limit {time_limit}s exceeded')
                break  # time limit exceeded

        return output, logits_output

    @staticmethod
    def yolo_resize(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):

        return letterbox(img, new_shape=new_shape, color=color, auto=auto, scaleFill=scaleFill, scaleup=scaleup)

    def forward(self, img):
        prediction, logits, _ = self.model(img, augment=False)
        prediction, logits = self.non_max_suppression(prediction, logits, self.confidence, self.iou_thresh,
                                                      classes=None,
                                                      agnostic=self.agnostic)
        self.boxes, self.class_names, self.classes, self.confidences = [[[] for _ in range(img.shape[0])] for _ in
                                                                        range(4)]
        for i, det in enumerate(prediction):  # detections per image
            if len(det):
                for *xyxy, conf, cls in det:
                    # 返回整数
                    bbox = [int(b) for b in xyxy]
                    self.boxes[i].append(bbox)
                    self.confidences[i].append(round(conf.item(), 2))
                    cls = int(cls.item())
                    self.classes[i].append(cls)
                    if self.names is not None:
                        self.class_names[i].append(self.names[cls])
                    else:
                        self.class_names[i].append(cls)
        return [self.boxes, self.classes, self.class_names, self.confidences], logits

    def preprocessing(self, img):
        if len(img.shape) != 4:
            img = np.expand_dims(img, axis=0)
        im0 = img.astype(np.uint8)
        img = np.array([self.yolo_resize(im, new_shape=self.img_size)[0] for im in im0])
        img = img.transpose((0, 3, 1, 2))
        img = np.ascontiguousarray(img)
        img = torch.from_numpy(img).to(self.device)
        img = img / 255.0
        return img

步骤五

更改model/yolo.py

具体而言
Detect类中的forward函数

    def forward(self, x):
        z = []  # inference output

        logits_ = []               # 修改---1

        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

                logits = x[i][..., 5:]                 # 修改---2


                if isinstance(self, Segment):  # (boxes + masks)
                    xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4)
                    xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf.sigmoid(), mask), 4)
                else:  # Detect (boxes only)
                    xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)
                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf), 4)
                z.append(y.view(bs, self.na * nx * ny, self.no))

                logits_.append(logits.view(bs, -1, self.no - 5))     # 修改---3

        # return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
        return x if self.training else (torch.cat(z, 1), torch.cat(logits_, 1), x)  # 修改---4

为了防止大家不知道怎么修改yolo.py文件，我将修改后的yolo.py文件放在下方
yolo.py

# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
"""
YOLO-specific modules

Usage:
    $ python models/yolo.py --cfg yolov5s.yaml
"""

import argparse
import contextlib
import os
import platform
import sys
from copy import deepcopy
from pathlib import Path

FILE = Path(__file__).resolve()
ROOT = FILE.parents[1]  # YOLOv5 root directory
if str(ROOT) not in sys.path:
    sys.path.append(str(ROOT))  # add ROOT to PATH
if platform.system() != 'Windows':
    ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative

from models.common import *
from models.experimental import *
from utils.autoanchor import check_anchor_order
from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
from utils.plots import feature_visualization
from utils.torch_utils import (fuse_conv_and_bn, initialize_weights, model_info, profile, scale_img, select_device,
                               time_sync)

try:
    import thop  # for FLOPs computation
except ImportError:
    thop = None


class Detect(nn.Module):
    # YOLOv5 Detect head for detection models
    stride = None  # strides computed during build
    dynamic = False  # force grid reconstruction
    export = False  # export mode

    def __init__(self, nc=80, anchors=(), ch=(), inplace=True):  # detection layer
        super().__init__()
        self.nc = nc  # number of classes
        self.no = nc + 5  # number of outputs per anchor
        self.nl = len(anchors)  # number of detection layers
        self.na = len(anchors[0]) // 2  # number of anchors
        self.grid = [torch.empty(0) for _ in range(self.nl)]  # init grid
        self.anchor_grid = [torch.empty(0) for _ in range(self.nl)]  # init anchor grid
        self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2))  # shape(nl,na,2)
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        self.inplace = inplace  # use inplace ops (e.g. slice assignment)

    def forward(self, x):
        z = []  # inference output

        logits_ = []               # 修改---1

        for i in range(self.nl):
            x[i] = self.m[i](x[i])  # conv
            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()

            if not self.training:  # inference
                if self.dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
                    self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)

                logits = x[i][..., 5:]                 # 修改---2


                if isinstance(self, Segment):  # (boxes + masks)
                    xy, wh, conf, mask = x[i].split((2, 2, self.nc + 1, self.no - self.nc - 5), 4)
                    xy = (xy.sigmoid() * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh.sigmoid() * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf.sigmoid(), mask), 4)
                else:  # Detect (boxes only)
                    xy, wh, conf = x[i].sigmoid().split((2, 2, self.nc + 1), 4)
                    xy = (xy * 2 + self.grid[i]) * self.stride[i]  # xy
                    wh = (wh * 2) ** 2 * self.anchor_grid[i]  # wh
                    y = torch.cat((xy, wh, conf), 4)
                z.append(y.view(bs, self.na * nx * ny, self.no))

                logits_.append(logits.view(bs, -1, self.no - 5))     # 修改---3

        # return x if self.training else (torch.cat(z, 1),) if self.export else (torch.cat(z, 1), x)
        return x if self.training else (torch.cat(z, 1), torch.cat(logits_, 1), x)  # 修改---4

    def _make_grid(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0')):
        d = self.anchors[i].device
        t = self.anchors[i].dtype
        shape = 1, self.na, ny, nx, 2  # grid shape
        y, x = torch.arange(ny, device=d, dtype=t), torch.arange(nx, device=d, dtype=t)
        yv, xv = torch.meshgrid(y, x, indexing='ij') if torch_1_10 else torch.meshgrid(y, x)  # torch>=0.7 compatibility
        grid = torch.stack((xv, yv), 2).expand(shape) - 0.5  # add grid offset, i.e. y = 2.0 * x - 0.5
        anchor_grid = (self.anchors[i] * self.stride[i]).view((1, self.na, 1, 1, 2)).expand(shape)
        return grid, anchor_grid


class Segment(Detect):
    # YOLOv5 Segment head for segmentation models
    def __init__(self, nc=80, anchors=(), nm=32, npr=256, ch=(), inplace=True):
        super().__init__(nc, anchors, ch, inplace)
        self.nm = nm  # number of masks
        self.npr = npr  # number of protos
        self.no = 5 + nc + self.nm  # number of outputs per anchor
        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
        self.proto = Proto(ch[0], self.npr, self.nm)  # protos
        self.detect = Detect.forward

    def forward(self, x):
        p = self.proto(x[0])
        x = self.detect(self, x)
        return (x, p) if self.training else (x[0], p) if self.export else (x[0], p, x[1])


class BaseModel(nn.Module):
    # YOLOv5 base model
    def forward(self, x, profile=False, visualize=False):
        return self._forward_once(x, profile, visualize)  # single-scale inference, train

    def _forward_once(self, x, profile=False, visualize=False):
        y, dt = [], []  # outputs
        for m in self.model:
            if m.f != -1:  # if not from previous layer
                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
            if profile:
                self._profile_one_layer(m, x, dt)
            x = m(x)  # run
            y.append(x if m.i in self.save else None)  # save output
            if visualize:
                feature_visualization(x, m.type, m.i, save_dir=visualize)
        return x

    def _profile_one_layer(self, m, x, dt):
        c = m == self.model[-1]  # is final layer, copy input as inplace fix
        o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPs
        t = time_sync()
        for _ in range(10):
            m(x.copy() if c else x)
        dt.append((time_sync() - t) * 100)
        if m == self.model[0]:
            LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s}  module")
        LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f}  {m.type}')
        if c:
            LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s}  Total")

    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
        LOGGER.info('Fusing layers... ')
        for m in self.model.modules():
            if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
                delattr(m, 'bn')  # remove batchnorm
                m.forward = m.forward_fuse  # update forward
        self.info()
        return self

    def info(self, verbose=False, img_size=640):  # print model information
        model_info(self, verbose, img_size)

    def _apply(self, fn):
        # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
        self = super()._apply(fn)
        m = self.model[-1]  # Detect()
        if isinstance(m, (Detect, Segment)):
            m.stride = fn(m.stride)
            m.grid = list(map(fn, m.grid))
            if isinstance(m.anchor_grid, list):
                m.anchor_grid = list(map(fn, m.anchor_grid))
        return self


class DetectionModel(BaseModel):
    # YOLOv5 detection model
    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
        super().__init__()
        if isinstance(cfg, dict):
            self.yaml = cfg  # model dict
        else:  # is *.yaml
            import yaml  # for torch hub
            self.yaml_file = Path(cfg).name
            with open(cfg, encoding='ascii', errors='ignore') as f:
                self.yaml = yaml.safe_load(f)  # model dict

        # Define model
        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
        if nc and nc != self.yaml['nc']:
            LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
            self.yaml['nc'] = nc  # override yaml value
        if anchors:
            LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
            self.yaml['anchors'] = round(anchors)  # override yaml value
        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
        self.inplace = self.yaml.get('inplace', True)

        # Build strides, anchors
        m = self.model[-1]  # Detect()
        if isinstance(m, (Detect, Segment)):
            s = 256  # 2x min stride
            m.inplace = self.inplace
            forward = lambda x: self.forward(x)[0] if isinstance(m, Segment) else self.forward(x)
            m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
            check_anchor_order(m)
            m.anchors /= m.stride.view(-1, 1, 1)
            self.stride = m.stride
            self._initialize_biases()  # only run once

        # Init weights, biases
        initialize_weights(self)
        self.info()
        LOGGER.info('')

    def forward(self, x, augment=False, profile=False, visualize=False):
        if augment:
            return self._forward_augment(x)  # augmented inference, None
        return self._forward_once(x, profile, visualize)  # single-scale inference, train

    def _forward_augment(self, x):
        img_size = x.shape[-2:]  # height, width
        s = [1, 0.83, 0.67]  # scales
        f = [None, 3, None]  # flips (2-ud, 3-lr)
        y = []  # outputs
        for si, fi in zip(s, f):
            xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
            yi = self._forward_once(xi)[0]  # forward
            # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
            yi = self._descale_pred(yi, fi, si, img_size)
            y.append(yi)
        y = self._clip_augmented(y)  # clip augmented tails
        return torch.cat(y, 1), None  # augmented inference, train

    def _descale_pred(self, p, flips, scale, img_size):
        # de-scale predictions following augmented inference (inverse operation)
        if self.inplace:
            p[..., :4] /= scale  # de-scale
            if flips == 2:
                p[..., 1] = img_size[0] - p[..., 1]  # de-flip ud
            elif flips == 3:
                p[..., 0] = img_size[1] - p[..., 0]  # de-flip lr
        else:
            x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale  # de-scale
            if flips == 2:
                y = img_size[0] - y  # de-flip ud
            elif flips == 3:
                x = img_size[1] - x  # de-flip lr
            p = torch.cat((x, y, wh, p[..., 4:]), -1)
        return p

    def _clip_augmented(self, y):
        # Clip YOLOv5 augmented inference tails
        nl = self.model[-1].nl  # number of detection layers (P3-P5)
        g = sum(4 ** x for x in range(nl))  # grid points
        e = 1  # exclude layer count
        i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e))  # indices
        y[0] = y[0][:, :-i]  # large
        i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e))  # indices
        y[-1] = y[-1][:, i:]  # small
        return y

    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
        # https://arxiv.org/abs/1708.02002 section 3.3
        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
        m = self.model[-1]  # Detect() module
        for mi, s in zip(m.m, m.stride):  # from
            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
            b.data[:, 5:5 + m.nc] += math.log(0.6 / (m.nc - 0.99999)) if cf is None else torch.log(cf / cf.sum())  # cls
            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)


Model = DetectionModel  # retain YOLOv5 'Model' class for backwards compatibility


class SegmentationModel(DetectionModel):
    # YOLOv5 segmentation model
    def __init__(self, cfg='yolov5s-seg.yaml', ch=3, nc=None, anchors=None):
        super().__init__(cfg, ch, nc, anchors)


class ClassificationModel(BaseModel):
    # YOLOv5 classification model
    def __init__(self, cfg=None, model=None, nc=1000, cutoff=10):  # yaml, model, number of classes, cutoff index
        super().__init__()
        self._from_detection_model(model, nc, cutoff) if model is not None else self._from_yaml(cfg)

    def _from_detection_model(self, model, nc=1000, cutoff=10):
        # Create a YOLOv5 classification model from a YOLOv5 detection model
        if isinstance(model, DetectMultiBackend):
            model = model.model  # unwrap DetectMultiBackend
        model.model = model.model[:cutoff]  # backbone
        m = model.model[-1]  # last layer
        ch = m.conv.in_channels if hasattr(m, 'conv') else m.cv1.conv.in_channels  # ch into module
        c = Classify(ch, nc)  # Classify()
        c.i, c.f, c.type = m.i, m.f, 'models.common.Classify'  # index, from, type
        model.model[-1] = c  # replace
        self.model = model.model
        self.stride = model.stride
        self.save = []
        self.nc = nc

    def _from_yaml(self, cfg):
        # Create a YOLOv5 classification model from a *.yaml file
        self.model = None


def parse_model(d, ch):  # model_dict, input_channels(3)
    # Parse a YOLOv5 model.yaml dictionary
    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
    anchors, nc, gd, gw, act = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple'], d.get('activation')
    if act:
        Conv.default_act = eval(act)  # redefine default activation, i.e. Conv.default_act = nn.SiLU()
        LOGGER.info(f"{colorstr('activation:')} {act}")  # print
    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)

    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
        m = eval(m) if isinstance(m, str) else m  # eval strings
        for j, a in enumerate(args):
            with contextlib.suppress(NameError):
                args[j] = eval(a) if isinstance(a, str) else a  # eval strings

        n = n_ = max(round(n * gd), 1) if n > 1 else n  # depth gain
        if m in {
                Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
                BottleneckCSP, C3, C3TR, C3SPP, C3Ghost, nn.ConvTranspose2d, DWConvTranspose2d, C3x}:
            c1, c2 = ch[f], args[0]
            if c2 != no:  # if not output
                c2 = make_divisible(c2 * gw, 8)

            args = [c1, c2, *args[1:]]
            if m in {BottleneckCSP, C3, C3TR, C3Ghost, C3x}:
                args.insert(2, n)  # number of repeats
                n = 1
        elif m is nn.BatchNorm2d:
            args = [ch[f]]
        elif m is Concat:
            c2 = sum(ch[x] for x in f)
        # TODO: channel, gw, gd
        elif m in {Detect, Segment}:
            args.append([ch[x] for x in f])
            if isinstance(args[1], int):  # number of anchors
                args[1] = [list(range(args[1] * 2))] * len(f)
            if m is Segment:
                args[3] = make_divisible(args[3] * gw, 8)
        elif m is Contract:
            c2 = ch[f] * args[0] ** 2
        elif m is Expand:
            c2 = ch[f] // args[0] ** 2
        else:
            c2 = ch[f]

        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
        t = str(m)[8:-2].replace('__main__.', '')  # module type
        np = sum(x.numel() for x in m_.parameters())  # number params
        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # print
        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
        layers.append(m_)
        if i == 0:
            ch = []
        ch.append(c2)
    return nn.Sequential(*layers), sorted(save)


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
    parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--profile', action='store_true', help='profile model speed')
    parser.add_argument('--line-profile', action='store_true', help='profile model speed layer by layer')
    parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
    opt = parser.parse_args()
    opt.cfg = check_yaml(opt.cfg)  # check YAML
    print_args(vars(opt))
    device = select_device(opt.device)

    # Create model
    im = torch.rand(opt.batch_size, 3, 640, 640).to(device)
    model = Model(opt.cfg).to(device)

    # Options
    if opt.line_profile:  # profile layer by layer
        model(im, profile=True)

    elif opt.profile:  # profile forward-backward
        results = profile(input=im, ops=[model], n=3)

    elif opt.test:  # test all models
        for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
            try:
                _ = Model(cfg)
            except Exception as e:
                print(f'Error in {cfg}: {e}')

    else:  # report fused model summary
        model.fuse()

步骤六：

运行main_gradcam.py
参数列表可以自己进行修改。

# Arguments
parser = argparse.ArgumentParser()
parser.add_argument('--model-path', type=str, default="yolov5s.pt", help='Path to the model')
parser.add_argument('--img-path', type=str, default='data/images/bus.jpg', help='input image path')
parser.add_argument('--output-dir', type=str, default='runs/result17', help='output dir')
parser.add_argument('--img-size', type=int, default=640, help="input image size")
parser.add_argument('--target-layer', type=str, default='model_17_cv3_act',
                    help='The layer hierarchical address to which gradcam will applied,'
                         ' the names should be separated by underline')
parser.add_argument('--method', type=str, default='gradcam', help='gradcam method')
parser.add_argument('--device', type=str, default='cuda', help='cuda or cpu')
parser.add_argument('--no_text_box', action='store_true',
                    help='do not show label and box on the heatmap')
args = parser.parse_args()

完成