YOLOv8 | 热力图可视化 | 即插即用 | GradCam

提示:文章写完后,目录可以自动生成,如何生成可参考右边的帮助文档


前言

本文提供YOLOv8项目及各种改进模型输出特征的热力图可视化代码,即插即用,不需要对源码做任何修改。有GradCAMPlusPlus, GradCAM, XGradCAM可选。


一、YOLOv8热力图可视化代码

代码如下:

import warnings

warnings.filterwarnings('ignore')
warnings.simplefilter('ignore')
import torch, cv2, os, shutil
import numpy as np

np.random.seed(0)
import matplotlib.pyplot as plt
from tqdm import trange
from PIL import Image
from ultralytics.nn.tasks import DetectionModel as Model
from ultralytics.utils.torch_utils import intersect_dicts
from ultralytics.utils.ops import xywh2xyxy
from pytorch_grad_cam import GradCAMPlusPlus, GradCAM, XGradCAM
from pytorch_grad_cam.utils.image import show_cam_on_image
from pytorch_grad_cam.activations_and_gradients import ActivationsAndGradients


def letterbox(im, 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 = im.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 val 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
        im = cv2.resize(im, 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))
    im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return im, ratio, (dw, dh)


class yolov8_heatmap:
    def __init__(self, weight, cfg, device, method, layer, backward_type, conf_threshold, ratio):
        device = torch.device(device)
        ckpt = torch.load(weight)
        model_names = ckpt['model'].names
        csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
        model = Model(cfg, ch=3, nc=len(model_names)).to(device)
        csd = intersect_dicts(csd, model.state_dict(), exclude=['anchor'])  # intersect
        model.load_state_dict(csd, strict=False)  # load
        model.eval()
        print(f'Transferred {len(csd)}/{len(model.state_dict())} items')

        target_layers = [eval(layer)]
        method = eval(method)

        colors = np.random.uniform(0, 255, size=(len(model_names), 3)).astype(np.int32)
        self.__dict__.update(locals())

    def post_process(self, result):
        logits_ = result[:, 4:]
        boxes_ = result[:, :4]
        sorted, indices = torch.sort(logits_.max(1)[0], descending=True)
        return torch.transpose(logits_[0], dim0=0, dim1=1)[indices[0]], torch.transpose(boxes_[0], dim0=0, dim1=1)[
            indices[0]], xywh2xyxy(torch.transpose(boxes_[0], dim0=0, dim1=1)[indices[0]]).cpu().detach().numpy()

    def draw_detections(self, box, color, name, img):
        xmin, ymin, xmax, ymax = list(map(int, list(box)))
        cv2.rectangle(img, (xmin, ymin), (xmax, ymax), tuple(int(x) for x in color), 2)
        cv2.putText(img, str(name), (xmin, ymin - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.8, tuple(int(x) for x in color), 2,
                    lineType=cv2.LINE_AA)
        return img

    def __call__(self, img_path, save_path):
        # remove dir if exist
        if os.path.exists(save_path):
            shutil.rmtree(save_path)
        # make dir if not exist
        os.makedirs(save_path, exist_ok=True)

        # img process
        img = cv2.imread(img_path)
        img = letterbox(img)[0]
        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
        img = np.float32(img) / 255.0
        tensor = torch.from_numpy(np.transpose(img, axes=[2, 0, 1])).unsqueeze(0).to(self.device)

        # init ActivationsAndGradients
        grads = ActivationsAndGradients(self.model, self.target_layers, reshape_transform=None)

        # get ActivationsAndResult
        result = grads(tensor)
        activations = grads.activations[0].cpu().detach().numpy()

        # postprocess to yolo output
        post_result, pre_post_boxes, post_boxes = self.post_process(result[0])
        for i in trange(int(post_result.size(0) * self.ratio)):
            if float(post_result[i].max()) < self.conf_threshold:
                break

            self.model.zero_grad()
            # get max probability for this prediction
            if self.backward_type == 'class' or self.backward_type == 'all':
                score = post_result[i].max()
                score.backward(retain_graph=True)

            if self.backward_type == 'box' or self.backward_type == 'all':
                for j in range(4):
                    score = pre_post_boxes[i, j]
                    score.backward(retain_graph=True)

            # process heatmap
            if self.backward_type == 'class':
                gradients = grads.gradients[0]
            elif self.backward_type == 'box':
                gradients = grads.gradients[0] + grads.gradients[1] + grads.gradients[2] + grads.gradients[3]
            else:
                gradients = grads.gradients[0] + grads.gradients[1] + grads.gradients[2] + grads.gradients[3] + \
                            grads.gradients[4]
            b, k, u, v = gradients.size()
            weights = self.method.get_cam_weights(self.method, None, None, None, activations,
                                                  gradients.detach().numpy())
            weights = weights.reshape((b, k, 1, 1))
            saliency_map = np.sum(weights * activations, axis=1)
            saliency_map = np.squeeze(np.maximum(saliency_map, 0))
            saliency_map = cv2.resize(saliency_map, (tensor.size(3), tensor.size(2)))
            saliency_map_min, saliency_map_max = saliency_map.min(), saliency_map.max()
            if (saliency_map_max - saliency_map_min) == 0:
                continue
            saliency_map = (saliency_map - saliency_map_min) / (saliency_map_max - saliency_map_min)

            # add heatmap and box to image
            cam_image = show_cam_on_image(img.copy(), saliency_map, use_rgb=True)
            cam_image = Image.fromarray(cam_image)
            cam_image.save(f'{save_path}/{i}.png')

def get_params():
    params = {
        'weight': './yolov8s.pt', # 这选择想要热力可视化的模型权重路径
        'cfg': './ultralytics/cfg/models/v8/yolov8s.yaml', # 这里选择与训练上面模型权重相对应的.yaml文件路径
        'device': 'cuda:0', # 选择设备,其中0表示0号显卡。如果使用CPU可视化 # 'device': 'cpu'
        'method': 'GradCAM', # GradCAMPlusPlus, GradCAM, XGradCAM
        'layer': 'model.model[4]',   # 选择特征层
        'backward_type': 'all', # class, box, all
        'conf_threshold': 0.65, # 置信度阈值默认0.65, 可根据情况调节
        'ratio': 0.02 # 取前多少数据,默认是0.02,可根据情况调节
    }
    return params

if __name__ == '__main__':
    model = yolov8_heatmap(**get_params()) # 初始化
    model('heatmap.jpg', './result') # 第一个参数是图片的路径,第二个参数是保存路径,比如是result的话,其会创建一个名字为result的文件夹,如果result文件夹不为空,其会先清空文件夹。

其中 ‘layer’: ‘model.model[4]’ 表示选择特征层4,也可以选择其它特征层
在这里插入图片描述

二、使用步骤

1.拷贝上述热力图可视化代码,在yolov8项目下创建heatmap.py文件,

在这里插入图片描述

2.修改配置,主要配置如下

代码如下:

def get_params():
    params = {
        'weight': './yolov8s.pt', # 这选择想要热力可视化的模型权重路径
        'cfg': './ultralytics/cfg/models/v8/yolov8s.yaml', # 这里选择与训练上面模型权重相对应的.yaml文件路径
        'device': 'cuda:0', # 选择设备,其中0表示0号显卡。如果使用CPU可视化 # 'device': 'cpu'
        'method': 'GradCAM', # GradCAMPlusPlus, GradCAM, XGradCAM
        'layer': 'model.model[4]',   # 选择特征层
        'backward_type': 'all', # class, box, all
        'conf_threshold': 0.65, # 置信度阈值默认0.65, 可根据情况调节
        'ratio': 0.02 # 取前多少数据,默认是0.02,可根据情况调节
    }
    return params

if __name__ == '__main__':
    model = yolov8_heatmap(**get_params()) # 初始化
    model('heatmap.jpg', './result') # 第一个参数是图片的路径,第二个参数是保存路径,比如是result的话,其会创建一个名字为result的文件夹,如果result文件夹不为空,其会先清空文件夹。

3.运行heatmap.py文件,在指定保存路径下查看热力图效果

热力图可视化效果图

在这里插入图片描述

  • 15
    点赞
  • 30
    收藏
    觉得还不错? 一键收藏
  • 8
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 8
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值