resnet系列+mobilenet v2+pytorch代码实现

一.resnet系列backbone

import torch.nn as nn
import math
import torch.utils.model_zoo as model_zooBatchNorm2d = nn.BatchNorm2d__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101', 'deformable_resnet18', 'deformable_resnet50','resnet152']model_urls = {'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth','resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth','resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth','resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth','resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}def constant_init(module, constant, bias=0):nn.init.constant_(module.weight, constant)if hasattr(module, 'bias'):nn.init.constant_(module.bias, bias)def conv3x3(in_planes, out_planes, stride=1):"""3x3 convolution with padding"""return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,padding=1, bias=False)class BasicBlock(nn.Module):expansion = 1def __init__(self, inplanes, planes, stride=1, downsample=None, dcn=None):super(BasicBlock, self).__init__()self.with_dcn = dcn is not Noneself.conv1 = conv3x3(inplanes, planes, stride)self.bn1 = BatchNorm2d(planes)self.relu = nn.ReLU(inplace=True)self.with_modulated_dcn = Falseif not self.with_dcn:self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1, bias=False)else:from torchvision.ops import DeformConv2ddeformable_groups = dcn.get('deformable_groups', 1)offset_channels = 18self.conv2_offset = nn.Conv2d(planes, deformable_groups * offset_channels, kernel_size=3, padding=1)self.conv2 = DeformConv2d(planes, planes, kernel_size=3, padding=1, bias=False)self.bn2 = BatchNorm2d(planes)self.downsample = downsampleself.stride = stridedef forward(self, x):residual = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)if not self.with_dcn:out = self.conv2(out)else:offset = self.conv2_offset(out)out = self.conv2(out, offset)out = self.bn2(out)if self.downsample is not None:residual = self.downsample(x)out += residualout = self.relu(out)return outclass Bottleneck(nn.Module):expansion = 4def __init__(self, inplanes, planes, stride=1, downsample=None, dcn=None):super(Bottleneck, self).__init__()self.with_dcn = dcn is not Noneself.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)self.bn1 = BatchNorm2d(planes)self.with_modulated_dcn = Falseif not self.with_dcn:self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)else:deformable_groups = dcn.get('deformable_groups', 1)from torchvision.ops import DeformConv2doffset_channels = 18self.conv2_offset = nn.Conv2d(planes, deformable_groups * offset_channels, stride=stride, kernel_size=3, padding=1)self.conv2 = DeformConv2d(planes, planes, kernel_size=3, padding=1, stride=stride, bias=False)self.bn2 = BatchNorm2d(planes)self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)self.bn3 = BatchNorm2d(planes * 4)self.relu = nn.ReLU(inplace=True)self.downsample = downsampleself.stride = strideself.dcn = dcnself.with_dcn = dcn is not Nonedef forward(self, x):residual = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)# out = self.conv2(out)if not self.with_dcn:out = self.conv2(out)else:offset = self.conv2_offset(out)out = self.conv2(out, offset)out = self.bn2(out)out = self.relu(out)out = self.conv3(out)out = self.bn3(out)if self.downsample is not None:residual = self.downsample(x)out += residualout = self.relu(out)return outclass ResNet(nn.Module):def __init__(self, block, layers, in_channels=3, dcn=None):self.dcn = dcnself.inplanes = 64super(ResNet, self).__init__()self.out_channels = []self.conv1 = nn.Conv2d(in_channels, 64, kernel_size=7, stride=2, padding=3,bias=False)self.bn1 = BatchNorm2d(64)self.relu = nn.ReLU(inplace=True)self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.layer1 = self._make_layer(block, 64, layers[0])self.layer2 = self._make_layer(block, 128, layers[1], stride=2, dcn=dcn)self.layer3 = self._make_layer(block, 256, layers[2], stride=2, dcn=dcn)self.layer4 = self._make_layer(block, 512, layers[3], stride=2, dcn=dcn)for m in self.modules():if isinstance(m, nn.Conv2d):n = m.kernel_size[0] * m.kernel_size[1] * m.out_channelsm.weight.data.normal_(0, math.sqrt(2. / n))elif isinstance(m, BatchNorm2d):m.weight.data.fill_(1)m.bias.data.zero_()if self.dcn is not None:for m in self.modules():if isinstance(m, Bottleneck) or isinstance(m, BasicBlock):if hasattr(m, 'conv2_offset'):constant_init(m.conv2_offset, 0)def _make_layer(self, block, planes, blocks, stride=1, dcn=None):downsample = Noneif stride != 1 or self.inplanes != planes * block.expansion:downsample = nn.Sequential(nn.Conv2d(self.inplanes, planes * block.expansion,kernel_size=1, stride=stride, bias=False),BatchNorm2d(planes * block.expansion),)layers = []layers.append(block(self.inplanes, planes, stride, downsample, dcn=dcn))self.inplanes = planes * block.expansionfor i in range(1, blocks):layers.append(block(self.inplanes, planes, dcn=dcn))self.out_channels.append(planes * block.expansion)return nn.Sequential(*layers)def forward(self, x):x = self.conv1(x)x = self.bn1(x)x = self.relu(x)x = self.maxpool(x)x2 = self.layer1(x)x3 = self.layer2(x2)x4 = self.layer3(x3)x5 = self.layer4(x4)return x2, x3, x4, x5def resnet18(pretrained=True, **kwargs):"""Constructs a ResNet-18 model.Args:pretrained (bool): If True, returns a model pre-trained on ImageNet"""model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)if pretrained:assert kwargs['in_channels'] == 3, 'in_channels must be 3 whem pretrained is True'print('load from imagenet')model.load_state_dict(model_zoo.load_url(model_urls['resnet18']), strict=False)return modeldef deformable_resnet18(pretrained=True, **kwargs):"""Constructs a ResNet-18 model.Args:pretrained (bool): If True, returns a model pre-trained on ImageNet"""model = ResNet(BasicBlock, [2, 2, 2, 2], dcn=dict(deformable_groups=1), **kwargs)if pretrained:assert kwargs['in_channels'] == 3, 'in_channels must be 3 whem pretrained is True'print('load from imagenet')model.load_state_dict(model_zoo.load_url(model_urls['resnet18']), strict=False)return modeldef resnet34(pretrained=True, **kwargs):"""Constructs a ResNet-34 model.Args:pretrained (bool): If True, returns a model pre-trained on ImageNet"""model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)if pretrained:assert kwargs['in_channels'] == 3, 'in_channels must be 3 whem pretrained is True'model.load_state_dict(model_zoo.load_url(model_urls['resnet34']), strict=False)return modeldef resnet50(pretrained=True, **kwargs):"""Constructs a ResNet-50 model.Args:pretrained (bool): If True, returns a model pre-trained on ImageNet"""model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)if pretrained:assert kwargs['in_channels'] == 3, 'in_channels must be 3 whem pretrained is True'model.load_state_dict(model_zoo.load_url(model_urls['resnet50']), strict=False)return modeldef deformable_resnet50(pretrained=True, **kwargs):"""Constructs a ResNet-50 model with deformable conv.Args:pretrained (bool): If True, returns a model pre-trained on ImageNet"""model = ResNet(Bottleneck, [3, 4, 6, 3], dcn=dict(deformable_groups=1), **kwargs)if pretrained:assert kwargs['in_channels'] == 3, 'in_channels must be 3 whem pretrained is True'model.load_state_dict(model_zoo.load_url(model_urls['resnet50']), strict=False)return modeldef resnet101(pretrained=True, **kwargs):"""Constructs a ResNet-101 model.Args:pretrained (bool): If True, returns a model pre-trained on ImageNet"""model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)if pretrained:assert kwargs['in_channels'] == 3, 'in_channels must be 3 whem pretrained is True'model.load_state_dict(model_zoo.load_url(model_urls['resnet101']), strict=False)return modeldef resnet152(pretrained=True, **kwargs):"""Constructs a ResNet-152 model.Args:pretrained (bool): If True, returns a model pre-trained on ImageNet"""model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)if pretrained:assert kwargs['in_channels'] == 3, 'in_channels must be 3 whem pretrained is True'model.load_state_dict(model_zoo.load_url(model_urls['resnet152']), strict=False)return modelif __name__ == '__main__':import torchx = torch.zeros(2, 3, 640, 640)# net = deformable_resnet50(pretrained=False)model_resnet50 = resnet101(pretrained=False)y = model_resnet50(x)for u in y:print(u.shape)# print(model_resnet34.out_channels)

二.mobilenet v2

2.1基础知识

１．采用inverted residual，与resnet不一样的是通道１X1卷积先变宽－＞卷积提特征－>１X1卷积变窄,因为经过1x1的卷积扩大通道数以后，可以提升抽取特征的能力，图１所示。

２．最后不采用Relu，而使用Linear代替，因为降维后特征丢失部分，如果采用Relu还会丢失，图２所示.

 

　　　　　　　　　　　　　　　　图１　inverted residual

　　　　　　　　　　　　图２宽窄通道relu丢失信息对比

上图是嵌入高维空间的低维流形的ReLU变换示例。 在这些例子中，使用随机矩阵T和ReLU将第一个图的螺旋嵌入到n维空间中，然后使用T的逆矩阵投影回2D空间。 当n = 2，3导致信息损失很多，恢复后的张量坍缩严重，而对于n = 15到30，不会丢失太多的输入信息。显然当通道数较多时，如果输入流形可嵌入激活空间的显着较低维的子空间，则ReLU变换将保留信息。当通道数较少时，通道的信息很可能被丢弃。

综上所述，在通道数较少的层后，应该用线性激活代替ReLU。MobileNet V2的Linear bottleneck Inverted residual block中，降维后的1X1卷积层后接的是一个线性激活，其他情况用的是ReLU。 

v1使用可分离卷积的计算减少量,如果k=3，也就是３x3卷积核，能后减少９倍左右的计算量．(k^2+dj)/(k^2*dj)

2.2 代码实现

１.BottleNeck实现

import torch.nn as nn
import torch
class BottleNeck(nn.Module):def __init__(self, inchannles, outchannels, expansion=1, stride=1, downsample=None):super(BottleNeck, self).__init__()#1*1self.conv1 = nn.Conv2d(inchannles, inchannles*expansion, kernel_size=1)self.bn1 = nn.BatchNorm2d(inchannles*expansion)#3*3 可分离卷积　groups设置self.conv2 = nn.Conv2d(inchannles*expansion, inchannles * expansion, kernel_size=3, padding=1, stride=stride,groups=inchannles * expansion)self.bn2 = nn.BatchNorm2d(inchannles * expansion)#1*1self.conv3 = nn.Conv2d(inchannles*expansion, outchannels, kernel_size=1)self.bn3 = nn.BatchNorm2d(outchannels)self.relu = nn.ReLU(inplace=True)self.downsample = downsampledef forward(self, x):residul = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out = self.relu(out)out = self.conv3(out)out = self.bn3(out)if self.downsample is not None:residul = self.downsample(x)out += residulout = self.relu(out)return out
def BottleNeck_test():inchannels = 3outchannels = 3stride =2downsample_ = nn.Sequential(nn.Conv2d(inchannels, outchannels, kernel_size=1, stride=stride),nn.BatchNorm2d(outchannels))bottleneck = BottleNeck(inchannels, outchannels, expansion=2, downsample=downsample_, stride=stride)print('bottleneck:', bottleneck)x = torch.rand((8, 3, 224, 224))out = bottleneck(x)print('out.shape', out.shape)if __name__ == '__main__':BottleNeck_test()

２．整体代码，加了权重初始化

import torch.nn as nn
import torch
class BottleNeck(nn.Module):def __init__(self, inchannles, outchannels, expansion=1, stride=1, downsample=None):super(BottleNeck, self).__init__()#1*1self.conv1 = nn.Conv2d(inchannles, inchannles*expansion, kernel_size=1)self.bn1 = nn.BatchNorm2d(inchannles*expansion)#3*3 可分离卷积　groups设置self.conv2 = nn.Conv2d(inchannles*expansion, inchannles * expansion, kernel_size=3, padding=1, stride=stride,groups=inchannles * expansion)self.bn2 = nn.BatchNorm2d(inchannles * expansion)#1*1self.conv3 = nn.Conv2d(inchannles*expansion, outchannels, kernel_size=1)self.bn3 = nn.BatchNorm2d(outchannels)self.relu = nn.ReLU(inplace=True)self.downsample = downsampledef forward(self, x):residul = xout = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out = self.relu(out)out = self.conv3(out)out = self.bn3(out)if self.downsample is not None:residul = self.downsample(x)out += residulout = self.relu(out)return outclass MobileNetV2(nn.Module):def __init__(self, n, numclasses=1000):super(MobileNetV2, self).__init__()self.inchannels = 32self.conv1 = nn.Conv2d(3, 32, kernel_size=3, stride=2, padding=1)self.bn1 = nn.BatchNorm2d(32)self.relu = nn.ReLU(inplace=True)self.layer1 = self.make_layer(n[0], outchannels=16, stride=1, expansion=1)self.layer2 = self.make_layer(n[1], outchannels=24, stride=2, expansion=6)self.layer3 = self.make_layer(n[2], outchannels=32, stride=2, expansion=6)self.layer4 = self.make_layer(n[3], outchannels=64, stride=2, expansion=6)self.layer5 = self.make_layer(n[4], outchannels=96, stride=1, expansion=6)self.layer6 = self.make_layer(n[5], outchannels=160, stride=2, expansion=6)self.layer7 = self.make_layer(n[6], outchannels=320, stride=1, expansion=1)self.conv8 = nn.Conv2d(320, 1280, kernel_size=1, stride=1)self.avegpool = nn.AvgPool2d(7, stride=1)self.conv9 = nn.Conv2d(1280, numclasses, kernel_size=1, stride=1)def make_layer(self, blocks_num, outchannels, stride, expansion):downsample_ = nn.Sequential(nn.Conv2d(self.inchannels, outchannels, kernel_size=1, stride=stride),nn.BatchNorm2d(outchannels))layers = []#下采样的shortcut有downsampletemp = BottleNeck(self.inchannels, outchannels, expansion=expansion, stride=stride, downsample=downsample_)layers.append(temp)#剩下的shortcut干净self.inchannels = outchannelsfor i in range(1, blocks_num):layers.append(BottleNeck(self.inchannels, outchannels, expansion=expansion, stride=1))return nn.Sequential(*layers)#取出每一层def forward(self, x):x = self.conv1(x)print('conv1.shape:', x.shape)x = self.bn1(x)x = self.relu(x)x = self.layer1(x)print('layer1.shape:', x.shape)x = self.layer2(x)print('layer2.shape:', x.shape)x = self.layer3(x)print('layer3.shape:', x.shape)x = self.layer4(x)print('layer4.shape:', x.shape)x = self.layer5(x)print('layer5.shape:', x.shape)x = self.layer6(x)print('layer6.shape:', x.shape)x = self.layer7(x)print('layer7.shape:', x.shape)x = self.conv8(x)print('conv8.shape:', x.shape)x = self.avegpool(x)print('avegpool:', x.shape)x = self.conv9(x)print('conv9.shape:', x.shape)x = x.view(x.size(0), -1)return xdef BottleNeck_test():inchannels = 3outchannels = 3stride =2downsample_ = nn.Sequential(nn.Conv2d(inchannels, outchannels, kernel_size=1, stride=stride),nn.BatchNorm2d(outchannels))bottleneck = BottleNeck(inchannels, outchannels, expansion=2, downsample=downsample_, stride=stride)print('bottleneck:', bottleneck)x = torch.rand((8, 3, 224, 224))out = bottleneck(x)print('out.shape', out.shape)def weigth_init(m):if isinstance(m, nn.Conv2d):nn.init.xavier_uniform_(m.weight.data)nn.init.constant_(m.bias.data, 0.1)elif isinstance(m, nn.BatchNorm2d):m.weight.data.fill_(1)m.bias.data.zero_()elif isinstance(m, nn.Linear):m.weight.data.normal_(0,0.01)m.bias.data.zero_()# print('weigth_init!')
def MobileNetV2_test():model = MobileNetV2(n=[1, 2, 3, 4, 3, 3, 1], numclasses=10)model.apply(weigth_init)# print('model:', model)x = torch.rand((8, 3, 224, 224))out = model(x)print('out.shape', out.shape)
if __name__ == '__main__':# BottleNeck_test()MobileNetV2_test()

　　

1.0
==img.shape: torch.Size([1, 3, 256, 192])
==x.shape: torch.Size([1, 32, 128, 96])
==i, x.shape==: 0 torch.Size([1, 16, 128, 96])
==i, x.shape==: 1 torch.Size([1, 24, 64, 48])
==i, x.shape==: 2 torch.Size([1, 32, 32, 24])
==i, x.shape==: 3 torch.Size([1, 64, 16, 12])
==i, x.shape==: 4 torch.Size([1, 96, 16, 12])
==i, x.shape==: 5 torch.Size([1, 160, 8, 6])
==i, x.shape==: 6 torch.Size([1, 320, 8, 6])
==i, x.shape==: 7 torch.Size([1, 1280, 8, 6])0.5==img.shape: torch.Size([1, 3, 256, 192])
==x.shape: torch.Size([1, 16, 128, 96])
==i, x.shape==: 0 torch.Size([1, 8, 128, 96])
==i, x.shape==: 1 torch.Size([1, 16, 64, 48])
==i, x.shape==: 2 torch.Size([1, 16, 32, 24])
==i, x.shape==: 3 torch.Size([1, 32, 16, 12])
==i, x.shape==: 4 torch.Size([1, 48, 16, 12])
==i, x.shape==: 5 torch.Size([1, 80, 8, 6])
==i, x.shape==: 6 torch.Size([1, 160, 8, 6])
==i, x.shape==: 7 torch.Size([1, 640, 8, 6])

参考：

从MobileNet V1到MobileNet V2 - 知乎

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处：http://www.mzph.cn/news/493224.shtml

如若内容造成侵权/违法违规/事实不符，请联系多彩编程网进行投诉反馈email:809451989@qq.com，一经查实，立即删除！

相关文章

广度优先搜索（BFS）与深度优先搜索（DFS）

广度优先搜索（BFS）与深度优先搜索（DFS）

一.广度优先搜索（BFS） 1.二叉树代码 # 实现一个二叉树 class TreeNode:def __init__(self, x):self.val xself.left Noneself.right Noneself.nexts []root_node TreeNode(1) node_2 TreeNode(2) node_3 TreeNode(3) node_4 TreeNode(4) node_…
阅读更多...
骁龙855在AI性能上真的秒杀麒麟980？噱头而已

骁龙855在AI性能上真的秒杀麒麟980？噱头而已

来源：网易智能摘要：前段时间的高通发布会上，有关骁龙855 AI性能达到友商竞品两倍的言论可谓是赚足了眼球。高通指出，骁龙855针对CPU、GPU、DSP都进行了AI计算优化，结合第四代AI引擎可以实现每秒超过7万亿次运算&#x…
阅读更多...
MySQL主从复制（Master-Slave）与读写分离（MySQL-Proxy）实践 转载

MySQL主从复制（Master-Slave）与读写分离（MySQL-Proxy）实践 转载

http://heylinux.com/archives/1004.html MySQL主从复制（Master-Slave）与读写分离（MySQL-Proxy）实践 Mysql作为目前世界上使用最广泛的免费数据库，相信所有从事系统运维的工程师都一定接触过。但在实际的生产环境中&am…
阅读更多...
深度解析AIoT背后的发展逻辑

深度解析AIoT背后的发展逻辑

来源：iotworld摘要：AI与IoT融合领域近年来一片火热，不论是资本市场，还是大众创业，无不对其表现出极大的热情。AIoT领域中人机交互的市场机会自2017年开始，“AIoT”一词便开始频频刷屏，成为物联网…
阅读更多...
ubuntu安装Redis+安装mysql(配置远程登录)+安装jdk+安转nginx+安转teamviewer+安装terminator+安装sublime

ubuntu安装Redis+安装mysql(配置远程登录)+安装jdk+安转nginx+安转teamviewer+安装terminator+安装sublime

一．Ubuntu 安装 Redis sudo apt-get update sudo apt-get install redis-server redis-server 启动 修改redis配置 远程访问: sudo vim /etc/redis/redis.conf 注释掉本机ip:　有坑的地方 #bind 127.0.0.1　 service redis-server restart redis-cli ping　…
阅读更多...
深入理解SQL注入绕过WAF与过滤机制

深入理解SQL注入绕过WAF与过滤机制

知己知彼，百战不殆 --孙子兵法 [目录] 0x0 前言 0x1 WAF的常见特征 0x2 绕过WAF的方法 0x3 SQLi Filter的实现及Evasion 0x4 延伸及测试向量示例 0x5 本文小结 0x6 参考资料 0x0 前言 促使本文产生最初的动机是前些天在做测试时一些攻击向量被WAF挡掉了，…
阅读更多...
预测|麦肯锡预测2030年：1亿中国人面临职业转换，全球8亿人被机器人取代

预测|麦肯锡预测2030年：1亿中国人面临职业转换，全球8亿人被机器人取代

来源：先进制造业摘要：纵观人类技术的发展历程，往往遵循一个固定的规律，即先是概念萌芽，然后经历市场炒作，资本蜂拥，结果潮水退去，泡沫破灭。而繁华落尽后，才会经历技术成…
阅读更多...
计算polygon面积和判断顺逆时针方向的方法

计算polygon面积和判断顺逆时针方向的方法

一．利用shapely求polygon面积 import shapelyfrom shapely.geometry import Polygon, MultiPoint # 多边形# box1 [2, 0, 4, 2, 2, 4, 0, 2, 0, 0]box1 [2, 0, 4, 2, 2, 4, 0, 2, 2, 2]poly_box1 Polygon(np.array(box1).reshape(-1,2))print(poly_box1)print(p…
阅读更多...
亚洲与非洲：中国支付巨头的海外进击

亚洲与非洲：中国支付巨头的海外进击

来源：资本实验室摘要：当下，对国人消费影响最大的两家互联网公司莫过于阿里巴巴和腾讯。这两大公司将大量消费级应用整合在自身的平台上，已经彻底改变了许多人的餐饮、购物、出行、旅游等生活方式，而移动支付是其中最基…
阅读更多...
利用已有的标注文字信息制作fake数据

利用已有的标注文字信息制作fake数据

from PIL import Image, ImageDraw, ImageFont, ImageFilter import random import glob import numpy as np import os import cv2 from nespaper_semantics import seg_str 1. 从文字库随机选择10个字符 2. 生成图片 3. 随机使用函数# 从字库中随机选择n个字符 def sto_choic…
阅读更多...
汽车芯片：半导体芯片巨头加速成长

汽车芯片：半导体芯片巨头加速成长

来源：乐晴智库精选伴随汽车智能化提速，汽车半导体加速成长。2017年全球汽车销量9680万辆(3%);汽车半导体市场规模288亿美元(26%)，增速远超整车。汽车半导体按种类可分为功能芯片MCU(MicrocontrollerUnit)、功率半导体(IGBT、MOSFET等)、传感器…
阅读更多...
将MSRA-TD500标签转换成逆时针输出标签+labeleme json格式转四个点的txt

将MSRA-TD500标签转换成逆时针输出标签+labeleme json格式转四个点的txt

一．MSRA-TD500 : http://www.iapr-tc11.org/mediawiki/index.php/MSRA_Text_Detection_500_Database_%28MSRA-TD500%29 #coding:utf-8 """ fzh created on 2019/12/6 将MSRA-TD500数据标签转换成按逆时针输出 也即　 index,difficulty label,x,y,w…
阅读更多...
一文看尽2018全年AI技术大突破

一文看尽2018全年AI技术大突破

来源：量子位摘要：2018，仍是AI领域激动人心的一年。这一年成为NLP研究的分水岭，各种突破接连不断；CV领域同样精彩纷呈，与四年前相比GAN生成的假脸逼真到让人不敢相信；新工具、新框架的出现&#…
阅读更多...
pyecharts地图使用

pyecharts地图使用

1.首先安装包 pip install pyecharts0.5.1 2.安装地图包 依次是全球地图、中国省级地图、中国市级地图、中国区县级地图、中国区域地图 pip install echarts-countries-pypkg pip install echarts-china-provinces-pypkg pip install echarts-china-cities-pypkg …
阅读更多...
《科学》：基因编辑婴儿入选年度“科学崩坏”事件

《科学》：基因编辑婴儿入选年度“科学崩坏”事件

来源：知识分子摘要：《科学》杂志每年会评出在即将过去的一年里最为重要的十大科学突破（Science Breakthrough）。今年，夺得年度突破桂冠的是“单细胞水平细胞谱系追踪技术”，帮助破获多起悬案的法医系谱技术…
阅读更多...
利用scipy包计算表格线的峰值,还原表格得到表格结构

利用scipy包计算表格线的峰值,还原表格得到表格结构

1. 利用scipy包计算表格线的峰值 import cv2 import numpy as np from scipy.signal import find_peaks, peak_widthsdef get_lines_from_image(img_bin, axis, kernel_len_div 20, kernel_len None, iters 3):""":param img_bin: opencv img:param axis: 0…
阅读更多...
原子智库 | 刘伟：人工智能快追上人类思维？答案可能让你失望

原子智库 | 刘伟：人工智能快追上人类思维？答案可能让你失望

来源：原子智库摘要：2018年12月15日，原子智库主办的“改革的规则与创新——2018光华腾讯经济年会暨风云演讲”在北京大学举办北京邮电大学人机交互与认知工程实验室主任刘伟发表演讲。演讲的话题是未来工业化发展、智能化发展。刘伟在演讲中指…
阅读更多...
利用xlwt写excel并进行单元格的合并

利用xlwt写excel并进行单元格的合并

1.写入行列值 import xlwt # 创建一个workbook 设置编码 workbook xlwt.Workbook(encodingutf-8) # 创建一个worksheet worksheet workbook.add_sheet(My Worksheet)# 写入excel # 参数对应 行, 列, 值 worksheet.write(1, 0, label this is test)# 保存 workbook.save(Exc…
阅读更多...
为了边缘计算，亚马逊、谷歌、微软已正面交锋！

为了边缘计算，亚马逊、谷歌、微软已正面交锋！

来源：全球物联网观察摘要：so，你真的了解边缘计算吗？边缘计算的前世今生云计算自2005年提出之后，就开始逐步地改变我们的生活、学习、工作的方式。云计算使得公司能够在自己的物理硬件之外，通过远程服务器网…
阅读更多...
每日一小练——二项式系数加法解

每日一小练——二项式系数加法解

上得厅堂，下得厨房，写得代码，翻得围墙，欢迎来到睿不可挡的每日一小练！ 题目：二项式系数加法解 内容：请编写一个程序，仅仅用加法，求出n中取r个组合系数C(n,r)，…
阅读更多...
推荐文章
最新文章

Copyright @ 2022~2023