- 博客(10)
- 收藏
- 关注
RSS订阅原创 How to train your Object Detection classifier
1.安装Anaconda安装步骤参考文章https://blog.csdn.net/weixin_43715458/article/details/100096496注意：有关anaconda的环境变量都要设置好2.从Github上下载TensorFlow Object Detection API ，我使用的是tensorflow1.13版本的https://github.com/tensorflow/models/tree/r1.13.0最新版本https://github.com/tensor
2020-10-29 21:53:47
210
原创 introduction of Activation Function
Many people may have some questions like:What is activation function? Why do we have so many activation function?Today,I will introduce the activation functions in neural network.Convolutional neural network always consist of many neurons stacked in layer
2020-05-20 20:01:54
287
原创 Classification Model:Resnet
Since the convolutional neural network is applied to image classification, the structure of the network has continued to develop and optimize. From Lenet, AlexNet, VGGNet, to ResNet, the depth of the network is getting larger and larger.So here I want to
2020-05-11 21:43:12
335
原创 The first step to build the project :use dataset and dataloader to read our data
The first step in building image classification and other projects is usually to process our dataset. Today I will introduce how the dataloader and dataset in pytorch get our data.When we create our ...
2020-04-28 15:47:02
187
原创 The evaluation of SSD algorith:calculate the mAP
In the past few weeks, I have successfully identified flames by using the trained SSD model, and the effect looks good. So can we simply think that this model is good enough?It often requires several...
2020-04-17 21:33:59
298
原创 The analysis of the code of the ssd-pytorch
The analysis of the core of the ssd-pytorch Data Preprocessing一级目录一级目录一级目录Data PreprocessingThe object detection project always begin with loading the dateset.First of all,inherit the dataset class,...
2020-04-08 09:02:24
544
原创 Deep Learning：Hello world
MNIST手写数字识别数据集的加载二级目录三级目录数据集的加载首先解决这个本地数据加载过慢的问题，因为下载的url官网太慢了，因此建议大家先从网上下载好数据集，放到对应目录的data文件中，然后运行以下代码就ok了。import torchimport torchvisionimport torchvision.transforms as transformstransform = ...
2020-04-07 09:18:34
113
原创 Pytorch入门深度学习
神经网络的搭建numpy搭建两层神经网络pytorch改写网络torch.nn包搭建网络torch.optim更新参数numpy搭建两层神经网络#用numpy搭建两层神经网络N,D_in,H,D_out=64,1000,100,10 #输入64*1000，隐藏层为64*100，输出64*10x=np.random.randn(N,D_in)w1=np.random.randn(D_in,...
2020-03-31 10:51:30
89
原创 SSD project
object detection algorithmSSDLast time,we find out a problem that we can not identify a flame only by its RGB and HSI feature as well as use the Background segmentation algorithm and designed filter...
2020-03-29 09:41:26
175
原创 First step on Fire Detection1
First step on Fire DetectionCV|The method about fire detectionHello,guys.If you are interested in object detection in the video stream based on python,follow me.Let’s study about how to find the fir...
2020-03-19 08:26:20
182
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人