使用grad

import os
import numpy as np
import torch
from PIL import Image
import matplotlib.pyplot as plt
from torchvision import models
from torchvision import transforms
from utils import GradCAM, show_cam_on_image, center_crop_img
from resnet1 import Mymodel


def main():
    
    model = Mymodel(num_classes=7) #导入自己的模型，num_classes数为自己数据集的类别数
    weights_dict = torch.load("自己模型的训练权重", map_location='cpu')
    
    model.load_state_dict(weights_dict, strict=False)  #加载自己模型的权重
    # target_layers = [model.backbone.layer4]
    target_layers = [model.backbone.layer4[-1]]         #定义目标层

    # model = models.mobilenet_v3_large(pretrained=True)
    # target_layers = [model.features[-1]]


    # model = models.vgg16(pretrained=True)
    # target_layers = [model.features]

    # model = models.resnet34(pretrained=True)
    # target_layers = [model.layer4]

    # model = models.regnet_y_800mf(pretrained=True)
    # target_layers = [model.trunk_output]

    # model = models.efficientnet_b0(pretrained=True)
    # target_layers = [model.features]

    data_transform = transforms.Compose([
                                         transforms.ToTensor(),
                                         transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
    # load image        
    img_path = "导入图片路径"  
    assert os.path.exists(img_path), "file: '{}' dose not exist.".format(img_path)
    img = Image.open(img_path).convert('RGB')
    img = np.array(img, dtype=np.uint8)
    img = center_crop_img(img, 448)             #将导入的图片reshape到自己想要的尺寸

    # [C, H, W]
    img_tensor = data_transform(img)
    # expand batch dimension
    # [C, H, W] -> [N, C, H, W]
    input_tensor = torch.unsqueeze(img_tensor, dim=0)

    cam = GradCAM(model=model, target_layers=target_layers, use_cuda=False)
    # target_category = 281  # tabby, tabby cat
    # target_category = 254  # pug, pug-dog
    target_category = 4

    grayscale_cam = cam(input_tensor=input_tensor, target_category=target_category)

    grayscale_cam = grayscale_cam[0, :]
    visualization = show_cam_on_image(img.astype(dtype=np.float32) / 255.,
                                      grayscale_cam,
                                      use_rgb=True)
    plt.imshow(visualization)
    plt.show()


if __name__ == '__main__':
    main()

下面是grad_cam的代码，注意：如果自己的模型是多输出的，要选择模型的指定输出。

import cv2
import numpy as np


class ActivationsAndGradients:
    """ Class for extracting activations and
    registering gradients from targeted intermediate layers """

    def __init__(self, model, target_layers, reshape_transform):
        self.model = model
        self.gradients = []
        self.activations = []
        self.reshape_transform = reshape_transform
        self.handles = []
        for target_layer in target_layers:
            self.handles.append(
                target_layer.register_forward_hook(
                    self.save_activation))
            # Backward compatibility with older pytorch versions:
            if hasattr(target_layer, 'register_full_backward_hook'):
                self.handles.append(
                    target_layer.register_full_backward_hook(
                        self.save_gradient))
            else:
                self.handles.append(
                    target_layer.register_backward_hook(
                        self.save_gradient))

    def save_activation(self, module, input, output):
        activation = output
        if self.reshape_transform is not None:
            activation = self.reshape_transform(activation)
        self.activations.append(activation.cpu().detach())

    def save_gradient(self, module, grad_input, grad_output):
        # Gradients are computed in reverse order
        grad = grad_output[0]
        if self.reshape_transform is not None:
            grad = self.reshape_transform(grad)
        self.gradients = [grad.cpu().detach()] + self.gradients

    def __call__(self, x):
        self.gradients = []
        self.activations = []
        return self.model(x)

    def release(self):
        for handle in self.handles:
            handle.remove()


class GradCAM:
    def __init__(self,
                 model,
                 target_layers,
                 reshape_transform=None,
                 use_cuda=False):
        self.model = model.eval()
        self.target_layers = target_layers
        self.reshape_transform = reshape_transform
        self.cuda = use_cuda
        if self.cuda:
            self.model = model.cuda()
        self.activations_and_grads = ActivationsAndGradients(
            self.model, target_layers, reshape_transform)

    """ Get a vector of weights for every channel in the target layer.
        Methods that return weights channels,
        will typically need to only implement this function. """

    @staticmethod
    def get_cam_weights(grads):
        return np.mean(grads, axis=(2, 3), keepdims=True)

    @staticmethod
    def get_loss(output, target_category):
        loss = 0
        output = output[2]           #注意：如果模型是多输出，需要选择自己想要的输出
        for i in range(len(target_category)):
            loss = loss + output[i, target_category[i]]
        return loss

    def get_cam_image(self, activations, grads):
        weights = self.get_cam_weights(grads)
        weighted_activations = weights * activations
        cam = weighted_activations.sum(axis=1)

        return cam

    @staticmethod
    def get_target_width_height(input_tensor):
        width, height = input_tensor.size(-1), input_tensor.size(-2)
        return width, height

    def compute_cam_per_layer(self, input_tensor):
        activations_list = [a.cpu().data.numpy()
                            for a in self.activations_and_grads.activations]
        grads_list = [g.cpu().data.numpy()
                      for g in self.activations_and_grads.gradients]
        target_size = self.get_target_width_height(input_tensor)

        cam_per_target_layer = []
        # Loop over the saliency image from every layer

        for layer_activations, layer_grads in zip(activations_list, grads_list):
            cam = self.get_cam_image(layer_activations, layer_grads)
            cam[cam  np.ndarray:
    """ This function overlays the cam mask on the image as an heatmap.
    By default the heatmap is in BGR format.

    :param img: The base image in RGB or BGR format.
    :param mask: The cam mask.
    :param use_rgb: Whether to use an RGB or BGR heatmap, this should be set to True if 'img' is in RGB format.
    :param colormap: The OpenCV colormap to be used.
    :returns: The default image with the cam overlay.
    """

    heatmap = cv2.applyColorMap(np.uint8(255 * mask), colormap)
    if use_rgb:
        heatmap = cv2.cvtColor(heatmap, cv2.COLOR_BGR2RGB)
    heatmap = np.float32(heatmap) / 255

    if np.max(img) > 1:
        raise Exception(
            "The input image should np.float32 in the range [0, 1]")

    cam = heatmap + img
    cam = cam / np.max(cam)
    return np.uint8(255 * cam)


def center_crop_img(img: np.ndarray, size: int):
    h, w, c = img.shape

    if w == h == size:
        return img

    if w < h:
        ratio = size / w
        new_w = size
        new_h = int(h * ratio)
    else:
        ratio = size / h
        new_h = size
        new_w = int(w * ratio)

    img = cv2.resize(img, dsize=(new_w, new_h))

    if new_w == size:
        h = (new_h - size) // 2
        img = img[h: h+size]
    else:
        w = (new_w - size) // 2
        img = img[:, w: w+size]

    return img