[视觉工具]如何使用热力图可视化模型

最新推荐文章于 2025-05-15 17:50:38 发布

guaguastd

最新推荐文章于 2025-05-15 17:50:38 发布

阅读量3.3k

点赞数

CC 4.0 BY-SA版权

分类专栏： # 工程实战文章标签：人工智能计算机视觉热力图热图 heatmap

本文链接：https://blog.csdn.net/guaguastd/article/details/107479653

本文介绍了如何利用热力图(heatmap)作为工具，通过Grad-CAM方法来可视化人工智能模型，尤其是计算机视觉模型的内部工作原理，帮助理解模型的图像识别偏好和潜在偏差。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

一.背景

热力图(heatmap)可以帮我们可视化模型,方便我们知道模型是如何看待图片的,也方便我们检测出模型的偏向(bias).

二.工具

Grad-CAM

三.代码(法1)

# USAGE
# python apply_gradcam.py --image images/space_shuttle.jpg
# python apply_gradcam.py --image images/beagle.jpg
# python apply_gradcam.py --image images/soccer_ball.jpg --model resnet

# import the necessary packages
from tensorflow.keras.applications import ResNet50
from tensorflow.keras.applications import VGG16
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras.applications import imagenet_utils
import numpy as np
import argparse
import imutils
import cv2
from tensorflow.keras.models import Model
import tensorflow as tf

# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
        help="path to the input image")
ap.add_argument("-m", "--model", type=str, default="vgg",
        choices=("vgg", "resnet"),
        help="model to be used")
args = vars(ap.parse_args())

# initialize the model to be VGG16
Model = VGG16

# check to see if we are using ResNet
if args["model"] == "resnet":
        Model = ResNet50

# gradcam
class GradCAM:
	def __init__(self, model, classIdx, layerName=None):
		# store the model, the class index used to measure the class
		# activation map, and the layer to be used when visualizing
		# the class activation map
		self.model = model
		self.classIdx = classIdx
		self.layerName = layerName

		# if the layer name is None, attempt to automatically find
		# the target output layer
		if self.layerName is None:
			self.layerName = self.find_target_layer()

	def find_target_layer(self):
		# attempt to find the final convolutional layer in the network
		# by looping over the layers of the network in reverse order
		for layer in reversed(self.model.layers):
			# check to see if the layer has a 4D output
			if len(layer.output_shape) == 4:
				return layer.name

		# otherwise, we could not find a 4D layer so the GradCAM
		# algorithm cannot be applied
		raise ValueError("Could not find 4D layer. Cannot apply GradCAM.")

	def compute_heatmap(self, image, eps=1e-8):
		# construct our gradient model by supplying (1) the inputs
		# to our pre-trained model, (2) the output of the (presumably)
		# final 4D layer in the network, and (3) the output of the
		# softmax activations from the model
		gradModel = Model(
			inputs=[self.model.inputs],
			outputs=[self.model.get_layer(self.layerName).output, 
				self.model.output])

		# record operations for automatic differentiation
		with tf.GradientTape() as tape:
			# cast the image tensor to a float-32 data type, pass the
			# image