opencv-dnn

复制代码
# utils_words.txt  标签文件
import os


image_types = (".jpg", ".jpeg", ".png", ".bmp", ".tif", ".tiff")


def list_images(basePath, contains=None):
    # return the set of files that are valid
    return list_files(basePath, validExts=image_types, contains=contains)


def list_files(basePath, validExts=None, contains=None):
    # loop over the directory structure
    for (rootDir, dirNames, filenames) in os.walk(basePath):
        # loop over the filenames in the current directory
        for filename in filenames:
            # if the contains string is not none and the filename does not contain
            # the supplied string, then ignore the file
            if contains is not None and filename.find(contains) == -1:
                continue

            # determine the file extension of the current file
            ext = filename[filename.rfind("."):].lower()

            # check to see if the file is an image and should be processed
            if validExts is None or ext.endswith(validExts):
                # construct the path to the image and yield it
                imagePath = os.path.join(rootDir, filename)
                yield imagePath

​
# 导入工具包
import utils_paths
import numpy as np
import cv2

# 标签文件处理
rows = open("synset_words.txt").read().strip().split("\n")
classes = [r[r.find(" ") + 1:].split(",")[0] for r in rows]

# Caffe所需配置文件
net = cv2.dnn.readNetFromCaffe("bvlc_googlenet.prototxt",
	"bvlc_googlenet.caffemodel")

# 图像路径
imagePaths = sorted(list(utils_paths.list_images("images/")))

# 图像数据预处理
image = cv2.imread(imagePaths[0])
resized = cv2.resize(image, (224, 224))
# image scalefactor size mean swapRB 
blob = cv2.dnn.blobFromImage(resized, 1, (224, 224), (104, 117, 123))
print("First Blob: {}".format(blob.shape))

# 得到预测结果
net.setInput(blob)
preds = net.forward()

# 排序,取分类可能性最大的
idx = np.argsort(preds[0])[::-1][0]
text = "Label: {}, {:.2f}%".format(classes[idx],
	preds[0][idx] * 100)
cv2.putText(image, text, (5, 25),  cv2.FONT_HERSHEY_SIMPLEX,
	0.7, (0, 0, 255), 2)

# 显示
cv2.imshow("Image", image)
cv2.waitKey(0)

# Batch数据制作
images = []

# 方法一样,数据是一个batch
for p in imagePaths[1:]:
	image = cv2.imread(p)
	image = cv2.resize(image, (224, 224))
	images.append(image)

# blobFromImages函数,注意有s
blob = cv2.dnn.blobFromImages(images, 1, (224, 224), (104, 117, 123))
print("Second Blob: {}".format(blob.shape))

# 获取预测结果
net.setInput(blob)
preds = net.forward()
for (i, p) in enumerate(imagePaths[1:]):
	image = cv2.imread(p)
	idx = np.argsort(preds[i])[::-1][0]
	text = "Label: {}, {:.2f}%".format(classes[idx],
		preds[i][idx] * 100)
	cv2.putText(image, text, (5, 25),  cv2.FONT_HERSHEY_SIMPLEX,
		0.7, (0, 0, 255), 2)
	cv2.imshow("Image", image)
	cv2.waitKey(0)

​
相关推荐
聚客AI18 分钟前
🌟大模型为什么产生幻觉?预训练到推理的漏洞全揭秘
人工智能·llm·掘金·日新计划
Juchecar23 分钟前
一文讲清 nn.Sequential 等容器类
人工智能
阿里云云原生1 小时前
如何快速看懂「祖传项目」?Qoder 强势推出新利器
人工智能
美团技术团队1 小时前
LongCat-Flash:如何使用 SGLang 部署美团 Agentic 模型
人工智能·算法
程序员小袁3 小时前
基于C-MTEB/CMedQAv2-rerankingv的Qwen3-1.7b模型微调-demo
人工智能
飞哥数智坊3 小时前
AI 编程一年多,我终于明白:比技巧更重要的,是熟练度
人工智能·ai编程
新智元4 小时前
收手吧 GPT-5-Codex,外面全是 AI 编程智能体!
人工智能·openai
IT_陈寒4 小时前
Java 性能优化:5个被低估的JVM参数让你的应用吞吐量提升50%
前端·人工智能·后端
阿里云云原生5 小时前
阿里云基础设施 AI Tech Day AI 原生,智构未来——AI 原生架构与企业实践专场
人工智能
Memene摸鱼日报6 小时前
「Memene 摸鱼日报 2025.9.16」OpenAI 推出 GPT-5-Codex 编程模型,xAI 发布 Grok 4 Fast
人工智能·aigc