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
chh5639 小时前
从 BERT 到大模型:让模型从“会接龙”到“会回答
人工智能·深度学习·bert
TomEval9 小时前
【测AI】第26篇:线上模型监控与告警体系 — 测试不是终点
人工智能·python·功能测试·ai
ZhengEnCi10 小时前
AI 总模仿代码库里的过时写法怎么办:先清坏样例,再用类型与测试让 AI 无法犯错
人工智能·ai编程
一只爱撸猫的程序猿10 小时前
五周、两个开源仓库、九次拦截之后:AI 时代程序员缺的到底是什么
人工智能·后端·开源
GitCode官方11 小时前
开源鸿蒙跨平台直播|AI 时代,用 cj-tauri 开发鸿蒙 PC 应用
人工智能·华为·harmonyos·atomgit
老金带你玩AI11 小时前
GPT-6.2更强更便宜了,为什么还有人骂?
人工智能
CyrusYiVPP11 小时前
实测 uv 0.13.7:同一套包,pip 装 94 秒,它只用 19 秒
人工智能·python
泯泷12 小时前
OpenClaw 退潮背后,是 AI 圈“技术自嗨”的终结
人工智能·chatgpt·llm
罗西的思考12 小时前
【轻量化复刻大模型 / KIMI K3】Muon 优化器及 训练系统
人工智能·算法·机器学习
屿华AI12 小时前
AUTOSAR 实战-诊断工具 | 用 Claude Code 开发诊断测试工具:AI 协作开发实践
人工智能·测试工具