resnet50 尝试 pytorch-grad-cam

参考链接：

GitHub - jacobgil/pytorch-grad-cam: Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

Grad_cam理解与代码 - 知乎

使用 resnet50 网络训练多分类模型完整代码_悄悄地努力的博客-CSDN博客_resnet50代码

pytorch_grad_cam——pytorch下的模型特征(Class Activation Mapping, CAM)可视化库_万里鹏程转瞬至的博客-CSDN博客

其中原图主要是做简单的转换，即将像素值由256 转入到0-1之间。

from pytorch_grad_cam import GradCAM, HiResCAM, ScoreCAM, GradCAMPlusPlus, AblationCAM, XGradCAM, EigenCAM, FullGrad
from pytorch_grad_cam.utils.model_targets import ClassifierOutputTarget
from pytorch_grad_cam.utils.image import show_cam_on_image
from torchvision.models import resnet50model = resnet50(pretrained=True)
target_layers = [model.layer4[-1]]
input_tensor = # Create an input tensor image for your model..
# Note: input_tensor can be a batch tensor with several images!# Construct the CAM object once, and then re-use it on many images:
cam = GradCAM(model=model, target_layers=target_layers, use_cuda=args.use_cuda)# You can also use it within a with statement, to make sure it is freed,
# In case you need to re-create it inside an outer loop:
# with GradCAM(model=model, target_layers=target_layers, use_cuda=args.use_cuda) as cam:
#   ...# We have to specify the target we want to generate
# the Class Activation Maps for.
# If targets is None, the highest scoring category
# will be used for every image in the batch.
# Here we use ClassifierOutputTarget, but you can define your own custom targets
# That are, for example, combinations of categories, or specific outputs in a non standard model.targets = None # 选择最大置信度的类进行热力图展示。本例281 指的就是标签id [ClassifierOutputTarget(281)]# You can also pass aug_smooth=True and eigen_smooth=True, to apply smoothing.
grayscale_cam = cam(input_tensor=input_tensor, targets=targets)# In this example grayscale_cam has only one image in the batch:
grayscale_cam = grayscale_cam[0, :]
#rgb_img 需要传入visualization = show_cam_on_image(rgb_img, grayscale_cam, use_rgb=True)

resnet50 尝试 pytorch-grad-cam相关推荐

PyTorch grad 与 Optimizer(params) 区别
目录 PyTorch grad 与 Optimizer(params) 区别 PyTorch grad 与 Optimizer(params) 区别 Tensor 可以设置属性 requires_gr ...
Pytorch 中 CAM绘制热度图
本篇主要介绍基于类激活映射(Class Activation Mapping, CAM)的热度图绘制算法原理出自论文: Learning Deep Features for Discriminati ...
通过和resnet18和resnet50理解PyTorch的ResNet模块
文章目录模型介绍 resnet18模型流程总结 resnet50 总结 resnet和resnext的框架基本相同的,这里先学习下resnet的构建,感觉高度模块化,很方便.本文算是对 PyTor ...
ResNet50《pytorch学习篇》
引言:resNet50网络作为res网络家族中的一员,特别强调的是残差网络是何大神提出的,轰动世界的大江南北,主要是因为:当时的卷积神经网络主要通过不断地增加卷积层来提取图像的特征,但是这会引发一个问 ...
pytorch: grad can be implicitly created only for scalar outputs 的解决办法
如果X.grad报错: grad can be implicitly created only for scalar outputs 加上去 X.backward(torch.ones_like(X) ...
pytorch : grad can be implicitly created only for scalar outputs
错误信息 File "***.py", line 101, in trainloss.backward()File "***/anaconda3/envs/ngepc/l ...
特征可视化技术(CAM)
https://zhuanlan.zhihu.com/p/269702192 CAM技术可以帮助我们理解CNN在图像中寻找目标对象的过程,并且可以用于可视化CNN的中间层特征,以及对图像分类结果的解释 ...
PyTorch 深度学习实用指南：1~5
原文:PyTorch Deep Learning Hands-On 协议:CC BY-NC-SA 4.0 译者:飞龙本文来自[ApacheCN 深度学习译文集],采用译后编辑(MTPE)流程来尽可 ...
pytorch自带网络_【方家之言】一篇长文学懂 pytorch
作为目前越来越受欢迎的深度学习框架,pytorch 基本上成了新人进入深度学习领域最常用的框架.相比于 TensorFlow,pytorch 更易学,更快上手,也可以更容易的实现自己想要的 demo. ...
《南溪的目标检测学习笔记》——PyTorch模型搭建模板
1 前言南溪在学习基于PyTorch的目标检测模型,对一些十分好的代码模板进行学习- 2 PyTorch模型模板 2.1 Faster R-CNN ResNet-50 FPN--PyTorch官方的 ...

resnet50 尝试 pytorch-grad-cam

resnet50 尝试 pytorch-grad-cam相关推荐

最新文章

热门文章