\u6548\u679c：\u611f\u53d7\u91ce\u5185\u90e8\u7684\u4f4d\u7f6e\u4fe1\u606f\u88ab\u663e\u5f0f\u4fdd\u7559\u548c\u52a0\u6743，\u800c\u6807\u51c6\u5377\u79ef\u628a 9 \u4e2a\u4f4d\u7f6e\u538b\u6210\u4e00\u7ec4\u5171\u4eab\u6743\u91cd\u3002<\/li>\n<\/ul>\n\u4e09\u3001\u5b9e\u73b0\u4ee3\u7801<\/h3>\n
\u7531\u5b98\u65b9 Liuchen1997\/RFAConv \u7b49\u4ef7\u9002\u914d：\u5b98\u65b9\u7528 einops.rearrange \u505a\u7a7a\u95f4\u91cd\u6392，\u672c\u6587\u4ee5 view\/permute \u7b49\u4ef7\u66ff\u6362，\u5df2\u505a\u540c\u6743\u91cd\u8f93\u51fa\u9010\u4f4d\u6bd4\u5bf9（320\u00d7320 \u8f93\u5165\u4e0b max diff = 0）：<\/p>\n
import torch
\nimport torch.nn as nn<\/p>\n
class RFAConv(nn.Module):
\n """RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef (Liu et al., 2023)，\u5b98\u65b9\u7b49\u4ef7\u9002\u914d\u7248\u3002<\/p>\n
\u8f93\u51fa\u7a7a\u95f4\u5c3a\u5bf8 = \u8f93\u5165 \/ stride（k=3, s=2 \u65f6\u4e0e\u666e\u901a stride-2 \u5377\u79ef\u5bf9\u9f50，
\n \u53ef\u76f4\u63a5\u66ff\u6362\u4e0b\u91c7\u6837\u5377\u79ef）\u3002
\n """<\/p>\n
def __init__(self, c1, c2, kernel_size=3, stride=1):
\n super().__init__()
\n self.kernel_size = kernel_size
\n self.get_weight = nn.Sequential(
\n nn.AvgPool2d(kernel_size=kernel_size, padding=kernel_size \/\/ 2, stride=stride),
\n nn.Conv2d(c1, c1 * (kernel_size ** 2), kernel_size=1, groups=c1, bias=False))
\n self.generate_feature = nn.Sequential(
\n nn.Conv2d(c1, c1 * (kernel_size ** 2), kernel_size=kernel_size,
\n padding=kernel_size \/\/ 2, stride=stride, groups=c1, bias=False),
\n nn.BatchNorm2d(c1 * (kernel_size ** 2)),
\n nn.ReLU())
\n self.conv = nn.Sequential(
\n nn.Conv2d(c1, c2, kernel_size=kernel_size, stride=kernel_size))<\/p>\n
def forward(self, x):
\n b, c = x.shape[0:2]
\n weight = self.get_weight(x)
\n h, w = weight.shape[2:]
\n weighted = weight.view(b, c, self.kernel_size ** 2, h, w).softmax(2)
\n feature = self.generate_feature(x).view(b, c, self.kernel_size ** 2, h, w)
\n weighted_data = feature * weighted
\n # \u7b49\u4ef7\u4e8e\u5b98\u65b9 rearrange('b c (n1 n2) h w -> b c (h n1) (w n2)')
\n conv_data = weighted_data.view(b, c, self.kernel_size, self.kernel_size, h, w)
\n conv_data = conv_data.permute(0, 1, 4, 2, 5, 3).reshape(
\n b, c, h * self.kernel_size, w * self.kernel_size)
\n return self.conv(conv_data)<\/p>\n
\u6ce8\u610f\u7b7e\u540d\u4e0e Conv \u5bf9\u9f50（c1 \u81ea\u52a8\u4f20\u5165，c2\/k\/s \u6765\u81ea yaml），\u6ce8\u518c\u7528\u5377\u79ef\u7c7b\u5206\u652f（c2 \u5bbd\u5ea6\u7f29\u653e）\u3002<\/p>\n
\u56db\u3001\u6dfb\u52a0\u6b65\u9aa4（v13 \u7248）<\/h3>\n1. \u4fee\u6539 ultralytics\/nn\/modules\/conv.py<\/h4>\n
RFAConv \u7c7b\u7c98\u8d34\u5230 conv.py \u672b\u5c3e\u3002<\/p>\n
2. \u4fee\u6539 ultralytics\/nn\/modules\/__init__.py<\/h4>\n
from .conv import (…) \u91cc\u8ffd\u52a0 RFAConv,；__all__ \u91cc\u7ed9\u6700\u540e\u4e00\u9879 "DSConv" \u8865\u9017\u53f7\u540e\u8ffd\u52a0 "RFAConv"\u3002<\/p>\n
3. \u4fee\u6539 ultralytics\/nn\/tasks.py<\/h4>\n
\u9876\u90e8\u5bfc\u5165\u5757\u52a0 RFAConv；parse_model() \u91cc\u65b0\u589e\u5377\u79ef\u7c7b\u5206\u652f（c2 \u5bbd\u5ea6\u7f29\u653e）：<\/p>\n
elif m is RFAConv: # \u5377\u79ef\u7c7b：c1 \u81ea\u52a8\u4f20\u5165，c2 \u6309\u5bbd\u5ea6\u7cfb\u6570\u7f29\u653e
\n c1 = ch[f]
\n c2 = args[0]
\n if c2 != nc:
\n c2 = make_divisible(min(c2, max_channels) * width, 8)
\n args = [c1, c2, *args[1:]]<\/p>\n
\u63d2\u5165\u4f4d\u7f6e：elif m is FullPAD_Tunnel: \u4e4b\u540e\u3001else: \u4e4b\u524d\u3002<\/p>\n
\u4e94\u3001yaml \u6a21\u578b\u6587\u4ef6<\/h3>\n
\u53ea\u6539\u7b2c 1 \u5c42，\u5176\u4f59\u4e0e\u5b98\u65b9 yolov13.yaml \u9010\u884c\u4e00\u81f4：<\/p>\n
# Ultralytics YOLOv13n + RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef 🚀
\nnc: 80
\nscales:
\n n: [0.50, 0.25, 1024]
\n s: [0.50, 0.50, 1024]
\n l: [1.00, 1.00, 512]
\n x: [1.00, 1.50, 512]<\/p>\n
backbone:
\n # [from, repeats, module, args]
\n – [-1, 1, Conv, [64, 3, 2]] # 0-P1\/2
\n – [-1, 1, RFAConv, [128, 3, 2]] # 1-P2\/4 \u2605RFAConv（\u66ff\u6362stride-2\u5377\u79ef，\u5c42\u6570\u4e0d\u53d8）
\n – [-1, 2, DSC3k2, [256, False, 0.25]]# 2
\n – [-1, 1, Conv, [256, 3, 2, 1, 4]] # 3-P3\/8
\n – [-1, 2, DSC3k2, [512, False, 0.25]]# 4
\n – [-1, 1, DSConv, [512, 3, 2]] # 5-P4\/16
\n – [-1, 4, A2C2f, [512, True, 4]] # 6
\n – [-1, 1, DSConv, [1024, 3, 2]] # 7-P5\/32
\n – [-1, 4, A2C2f, [1024, True, 1]] # 8<\/p>\n
head:
\n – [[4, 6, 8], 2, HyperACE, [512, 8, True, True, 0.5, 1, "both"]] # 9
\n – [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 10
\n – [ 9, 1, DownsampleConv, []] # 11
\n – [[6, 9], 1, FullPAD_Tunnel, []] # 12
\n – [[4, 10], 1, FullPAD_Tunnel, []] # 13
\n – [[8, 11], 1, FullPAD_Tunnel, []] # 14
\n – [-1, 1, nn.Upsample, [None, 2, "nearest"]] # 15
\n – [[-1, 12], 1, Concat, [1]] # 16 cat backbone P4
\n – [-1, 2, DSC3k2, [512, True]] # 17
\n – [[-1, 9], 1, FullPAD_Tunnel, []] # 18
\n – [17, 1, nn.Upsample, [None, 2, "nearest"]] # 19
\n – [[-1, 13], 1, Concat, [1]] # 20 cat backbone P3
\n – [-1, 2, DSC3k2, [256, True]] # 21
\n – [10, 1, Conv, [256, 1, 1]] # 22
\n – [[21, 22], 1, FullPAD_Tunnel, []] # 23
\n – [-1, 1, Conv, [256, 3, 2]] # 24
\n – [[-1, 18], 1, Concat, [1]] # 25 cat head P4
\n – [-1, 2, DSC3k2, [512, True]] # 26
\n – [[-1, 9], 1, FullPAD_Tunnel, []] # 27
\n – [26, 1, Conv, [512, 3, 2]] # 28
\n – [[-1, 14], 1, Concat, [1]] # 29 cat head P5
\n – [-1, 2, DSC3k2, [1024,True]] # 30
\n – [[-1, 11], 1, FullPAD_Tunnel, []] # 31
\n – [[23, 27, 31], 1, Detect, [nc]] # 32 Detect(P3, P4, P5)<\/p>\n
\u516d\u3001\u6210\u529f\u8fd0\u884c\u7ed3\u679c<\/h3>\n
yolo detect train model=yolov13n-RFAConv.yaml data=mydata.yaml epochs=100 imgsz=640 batch=16<\/p>\n
Python \u65b9\u5f0f：<\/p>\n
from ultralytics import YOLO<\/p>\n
model = YOLO("yolov13n-RFAConv.yaml").load("yolov13n.pt")
\nmodel.train(data="mydata.yaml", epochs=100, imgsz=640, batch=16)<\/p>\n
\u672c\u6587\u5b9e\u6d4b（YOLOv13 \u5b98\u65b9\u4ed3\u5e93，Windows CPU，v13n \u7ed3\u6784，\u66ff\u6362\u5c42 1）：<\/p>\n
\u57fa\u7ebf yolov13n: 2,494,151 parameters, 6.5 GFLOPs（\u5c421\u4e3a 2,368 \u53c2\u6570）
\n+RFAConv: 2,498,151 parameters, 6.7 GFLOPs（\u5c421\u4e3a 6,368 \u53c2\u6570）
\n3 epochs completed. Results saved to runs\\\\detect\\\\v13_rfaconv_smoke<\/p>\n
\u2705 \u65ad\u8a00\u5168\u90e8\u901a\u8fc7：\u2460 \u9002\u914d\u7248\u4e0e\u5b98\u65b9 RFAConv \u540c\u6743\u91cd\u8f93\u51fa\u9010\u4f4d\u4e00\u81f4（max diff = 0，einops \u91cd\u6392\u5df2\u7b49\u4ef7\u66ff\u6362）；\u2461 \u7b2c 1 \u5c42\u4e3a RFAConv，\u603b\u53c2\u6570\u91cf\u6070\u4e3a\u57fa\u7ebf +4,000；\u2462 \u5c42\u6570\u4e0d\u53d8，\u6574\u7f51 640 \u524d\u5411\u6b63\u5e38，3 \u8f6e\u5192\u70df\u8bad\u7ec3\u6b63\u5e38\u6536\u655b\u3002<\/p>\n
\u53c2\u6570\u91cf\u5206\u89e3（c1=16, c2=32, k=3, s=2）：<\/p>\n
\n\u90e8\u4ef6\u53c2\u6570\u91cf\u8bf4\u660e<\/tr>\n
\n\n| get_weight \u5206\u7ec4 1\u00d71<\/td>\n | 144<\/td>\n | \u611f\u53d7\u91ce\u6253\u5206（16 \u7ec4，\u6bcf\u7ec4 9 \u5206）<\/td>\n<\/tr>\n |
\n| generate_feature \u5206\u7ec4 3\u00d73 + BN<\/td>\n | 1,584<\/td>\n | \u611f\u53d7\u91ce\u7279\u5f81\u5c55\u5f00<\/td>\n<\/tr>\n |
\n| \u8f93\u51fa\u5377\u79ef 3\u00d73<\/td>\n | 4,640<\/td>\n | \u91cd\u6392\u540e\u7684\u6807\u51c6\u5377\u79ef<\/td>\n<\/tr>\n |
\n| \u5408\u8ba1<\/td>\n | 6,368（+4,000）<\/td>\n | <\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\u6a21\u578bParamsGFLOPs\u5c421\u53c2\u6570\u53d8\u5316\u8bf4\u660e<\/tr>\n \n\n| YOLOv13n \u57fa\u7ebf<\/td>\n | 2,494,151<\/td>\n | 6.5<\/td>\n | 2,368<\/td>\n | \u5b98\u65b9 stride-2 \u5206\u7ec4\u5377\u79ef<\/td>\n<\/tr>\n | \n| +RFAConv<\/td>\n | 2,498,151<\/td>\n | 6.7<\/td>\n | 6,368（+4,000）<\/td>\n | \u611f\u53d7\u91ce\u5185\u9010\u4f4d\u7f6e\u52a0\u6743<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\u4e03\u3001\u603b\u7ed3<\/h3>\nRFAConv \u7684\u4e09\u70b9\u8bb0\u5fc6\u951a：\u6ce8\u610f\u529b\u4f5c\u7528\u5728\u611f\u53d7\u91ce\u5185\u90e8（k\u00b2 \u4e2a\u4f4d\u7f6e\u6253\u5206，\u800c\u975e\u6574\u5f20\u7279\u5f81\u56fe）\u3001\u7a7a\u95f4\u91cd\u6392\u662f\u5173\u952e\u4e00\u6b65（\u628a\u52a0\u6743\u540e\u7684\u7279\u5f81\u7247\u62fc\u56de\u5927\u56fe\u518d\u5377\u79ef）\u3001stride \u7531\u8f93\u51fa\u5377\u79ef\u7684 stride=kernel_size \u5b9e\u73b0（k=3, s=2 \u6070\u597d\u5bf9\u9f50\u4e0b\u91c7\u6837）\u3002\u5b83\u4e0e CoordConv \u540c\u4f4d\u66ff\u6362\u5c42 1，\u4e24\u8005\u4e92\u4e3a\u5bf9\u7167：CoordConv \u8865"\u7edd\u5bf9\u4f4d\u7f6e\u611f"，RFAConv \u8865"\u611f\u53d7\u91ce\u5185\u76f8\u5bf9\u91cd\u8981\u6027"\u3002<\/p>\n \u89c9\u5f97\u6709\u5e2e\u52a9\u7684\u8bdd，\u70b9\u8d5e\u6536\u85cf\u5173\u6ce8\u4e09\u8fde\u652f\u6301\u4e00\u4e0b，\u8bc4\u8bba\u533a\u6b22\u8fce\u4ea4\u6d41\u4f60\u7684\u5b9e\u9a8c\u7ed3\u679c~<\/p>\n \u4e13\u680f\u76ee\u5f55：YOLOv13\u6539\u8fdb\u76ee\u5f55\u4e00\u89c8 \u4e13\u680f\u5730\u5740：YOLOv13\u6539\u8fdb\u4e13\u680f\u2014\u2014\u6301\u7eed\u66f4\u65b0\u5404\u65b9\u5411\u5373\u63d2\u5373\u7528\u6539\u8fdb<\/p>\n","protected":false},"excerpt":{"rendered":" \u672c\u6587\u57fa\u4e8e YOLOv13 \u5b98\u65b9\u4ed3\u5e93（iMoonLab\/yolov13，ultralytics 8.3.63 fork） \u5b9e\u6d4b\u6574\u7406，Windows\/CPU \u5168\u7a0b\u53ef\u8dd1\u3002\u6807\u51c6\u5377\u79ef\u6709\u4e2a\u9690\u542b\u5047\u8bbe：3\u00d73 \u611f\u53d7\u91ce\u91cc\u7684 9 \u4e2a\u4f4d\u7f6e\u540c\u7b49\u91cd\u8981\u3002RFAConv（Receptive-Field Attention Convolution，2023）\u63a8\u7ffb\u4e86\u8fd9\u4e2a\u5047\u8bbe\u2014\u2014\u5148\u7ed9\u611f\u53d7\u91ce\u91cc\u6bcf\u4e2a\u4f4d\u7f6e\u6253<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[156,86,1665,427,523],"topic":[],"class_list":["post-114736","post","type-post","status-publish","format-standard","hentry","category-server","tag-yolo","tag-86","tag-1665","tag-427","tag-523"],"yoast_head":"\n YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.wsisp.com\/helps\/114736.html\" \/>\n<meta property=\"og:locale\" content=\"zh_CN\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"og:description\" content=\"\u672c\u6587\u57fa\u4e8e YOLOv13 \u5b98\u65b9\u4ed3\u5e93（iMoonLab\/yolov13，ultralytics 8.3.63 fork） \u5b9e\u6d4b\u6574\u7406，Windows\/CPU \u5168\u7a0b\u53ef\u8dd1\u3002\u6807\u51c6\u5377\u79ef\u6709\u4e2a\u9690\u542b\u5047\u8bbe：3\u00d73 \u611f\u53d7\u91ce\u91cc\u7684 9 \u4e2a\u4f4d\u7f6e\u540c\u7b49\u91cd\u8981\u3002RFAConv（Receptive-Field Attention Convolution，2023）\u63a8\u7ffb\u4e86\u8fd9\u4e2a\u5047\u8bbe\u2014\u2014\u5148\u7ed9\u611f\u53d7\u91ce\u91cc\u6bcf\u4e2a\u4f4d\u7f6e\u6253\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.wsisp.com\/helps\/114736.html\" \/>\n<meta property=\"og:site_name\" content=\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\" \/>\n<meta property=\"article:published_time\" content=\"2026-10-09T16:08:43+00:00\" \/>\n<meta name=\"author\" content=\"admin\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"\u4f5c\u8005\" \/>\n\t<meta name=\"twitter:data1\" content=\"admin\" \/>\n\t<meta name=\"twitter:label2\" content=\"\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 \u5206\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/114736.html\",\"url\":\"https:\/\/www.wsisp.com\/helps\/114736.html\",\"name\":\"YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"isPartOf\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\"},\"datePublished\":\"2026-10-09T16:08:43+00:00\",\"dateModified\":\"2026-10-09T16:08:43+00:00\",\"author\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.wsisp.com\/helps\/114736.html#breadcrumb\"},\"inLanguage\":\"zh-Hans\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.wsisp.com\/helps\/114736.html\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/114736.html#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"\u9996\u9875\",\"item\":\"https:\/\/www.wsisp.com\/helps\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#website\",\"url\":\"https:\/\/www.wsisp.com\/helps\/\",\"name\":\"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3\",\"description\":\"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}\"},\"query-input\":\"required name=search_term_string\"}],\"inLanguage\":\"zh-Hans\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41\",\"name\":\"admin\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"zh-Hans\",\"@id\":\"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"contentUrl\":\"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery\",\"caption\":\"admin\"},\"sameAs\":[\"http:\/\/wp.wsisp.com\"],\"url\":\"https:\/\/www.wsisp.com\/helps\/author\/admin\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.wsisp.com\/helps\/114736.html","og_locale":"zh_CN","og_type":"article","og_title":"YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","og_description":"\u672c\u6587\u57fa\u4e8e YOLOv13 \u5b98\u65b9\u4ed3\u5e93（iMoonLab\/yolov13，ultralytics 8.3.63 fork） \u5b9e\u6d4b\u6574\u7406，Windows\/CPU \u5168\u7a0b\u53ef\u8dd1\u3002\u6807\u51c6\u5377\u79ef\u6709\u4e2a\u9690\u542b\u5047\u8bbe：3\u00d73 \u611f\u53d7\u91ce\u91cc\u7684 9 \u4e2a\u4f4d\u7f6e\u540c\u7b49\u91cd\u8981\u3002RFAConv（Receptive-Field Attention Convolution，2023）\u63a8\u7ffb\u4e86\u8fd9\u4e2a\u5047\u8bbe\u2014\u2014\u5148\u7ed9\u611f\u53d7\u91ce\u91cc\u6bcf\u4e2a\u4f4d\u7f6e\u6253","og_url":"https:\/\/www.wsisp.com\/helps\/114736.html","og_site_name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","article_published_time":"2026-10-09T16:08:43+00:00","author":"admin","twitter_card":"summary_large_image","twitter_misc":{"\u4f5c\u8005":"admin","\u9884\u8ba1\u9605\u8bfb\u65f6\u95f4":"4 \u5206"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.wsisp.com\/helps\/114736.html","url":"https:\/\/www.wsisp.com\/helps\/114736.html","name":"YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743 - \u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","isPartOf":{"@id":"https:\/\/www.wsisp.com\/helps\/#website"},"datePublished":"2026-10-09T16:08:43+00:00","dateModified":"2026-10-09T16:08:43+00:00","author":{"@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41"},"breadcrumb":{"@id":"https:\/\/www.wsisp.com\/helps\/114736.html#breadcrumb"},"inLanguage":"zh-Hans","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.wsisp.com\/helps\/114736.html"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/www.wsisp.com\/helps\/114736.html#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"\u9996\u9875","item":"https:\/\/www.wsisp.com\/helps"},{"@type":"ListItem","position":2,"name":"YOLOv13\u6539\u8fdb\u7b56\u7565\u3010\u5377\u79ef\u5c42\u7bc7\u3011| RFAConv \u611f\u53d7\u91ce\u6ce8\u610f\u529b\u5377\u79ef\uff0c\u6bcf\u4e2a\u4f4d\u7f6e\u90fd\u503c\u5f97\u88ab\u5355\u72ec\u52a0\u6743"}]},{"@type":"WebSite","@id":"https:\/\/www.wsisp.com\/helps\/#website","url":"https:\/\/www.wsisp.com\/helps\/","name":"\u7f51\u7855\u4e92\u8054\u5e2e\u52a9\u4e2d\u5fc3","description":"\u9999\u6e2f\u670d\u52a1\u5668_\u9999\u6e2f\u4e91\u670d\u52a1\u5668\u8d44\u8baf_\u670d\u52a1\u5668\u5e2e\u52a9\u6587\u6863_\u670d\u52a1\u5668\u6559\u7a0b","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.wsisp.com\/helps\/?s={search_term_string}"},"query-input":"required name=search_term_string"}],"inLanguage":"zh-Hans"},{"@type":"Person","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/358e386c577a3ab51c4493330a20ad41","name":"admin","image":{"@type":"ImageObject","inLanguage":"zh-Hans","@id":"https:\/\/www.wsisp.com\/helps\/#\/schema\/person\/image\/","url":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","contentUrl":"https:\/\/gravatar.wp-china-yes.net\/avatar\/?s=96&d=mystery","caption":"admin"},"sameAs":["http:\/\/wp.wsisp.com"],"url":"https:\/\/www.wsisp.com\/helps\/author\/admin"}]}},"_links":{"self":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/114736","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/comments?post=114736"}],"version-history":[{"count":0,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/posts\/114736\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/media?parent=114736"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/categories?post=114736"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/tags?post=114736"},{"taxonomy":"topic","embeddable":true,"href":"https:\/\/www.wsisp.com\/helps\/wp-json\/wp\/v2\/topic?post=114736"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}} | |