YOLOv5热力图可视化GradCAM

本文是针对yolov5热力图可视化的实现过程，并指出其中需要更改的地方。更改后便可以即插即用，较为简单。

一、代码

源码地址：yolo-gradcam

Github上的代码已经复制在下方，如下所示。

import warnings
warnings.filterwarnings('ignore')
warnings.simplefilter('ignore')
import torch, yaml, 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 models.yolo import Model
from utils.general import intersect_dicts
from utils.augmentations import letterbox
from utils.general 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

class yolov5_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.int)
        self.__dict__.update(locals())
    
    def post_process(self, result):
        logits_ = result[..., 4:]
        boxes_ = result[..., :4]
        sorted, indices = torch.sort(logits_[..., 0], descending=True)
        return logits_[0][indices[0]], xywh2xyxy(boxes_[0][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