- 👋 Hi, I’m @dreamilk
- 👀 I’m interested in coding
- 🌱 I’m currently learning cpp
- 💞️ I’m currently studying in zju
- 📫 How to reach me ...
dreamilk / ann Goto Github PK
View Code? Open in Web Editor NEWAn artificial neural network framework based on c++
An artificial neural network framework based on c++
Welcome to mechine learning
train_image = 60000 train_lable = 60000
test_image = 10000 test_lable = 10000
Training Epoches = 10 LearningRate = 0.100000 BatchSize = 16 Shuffle = 1
TrainDataSize = 60000 TestDataSize = 10000
[1|10] TotalLoss nan Accuracy 0.098000
[2|10] TotalLoss nan Accuracy 0.098000
[3|10] TotalLoss nan Accuracy 0.098000
[4|10] TotalLoss nan Accuracy 0.098000
[5|10] TotalLoss nan Accuracy 0.098000
我的电脑比较烂,所以我把build_with_gcc_linux.sh
里的命令改成如下
g++ -I ./include ./src/* -o ann -w -O3
加入了O3编译优化,不然原本的O0不知道要等到什么时候
结果不管是windows还是linux(fedora38),结果都如下
$ bash build_with_gcc_linux.sh
$ ./ann
Welcome to mechine learning
train_image = 60000 train_lable = 60000
test_image = 10000 test_lable = 10000
Training Epoches = 10 LearningRate = 0.100000 BatchSize = 16 Shuffle = 1
TrainDataSize = 60000 TestDataSize = 10000
[1|10] TotalLoss 2514.289393 Accuracy 0.448900
[2|10] TotalLoss 1988.453718 Accuracy 0.542200
[3|10] TotalLoss 1687.064992 Accuracy 0.682900
[4|10] TotalLoss 1470.652503 Accuracy 0.655600
[5|10] TotalLoss 1336.882764 Accuracy 0.772700
[6|10] TotalLoss 1197.188578 Accuracy 0.818400
[7|10] TotalLoss 1070.062496 Accuracy 0.833900
[8|10] TotalLoss 987.018515 Accuracy 0.843400
[9|10] TotalLoss 943.501052 Accuracy 0.787000
[10|10] TotalLoss 910.489711 Accuracy 0.842000
save logs Error
End Training, Train Step 37500 , Time Cost 76.53 s, Save Logs ./logs/train_logs.txt
saveModel Error
accuracy 0.834383
Network Structure:
--------------------------------------------
[input_layer] input_size = 784
[hidden_layer] neuron_size = 10
[output_layer] output_size = 10
--------------------------------------------
Number of parameters: 8744
--------------------------------------------
######
##########
############
########## ####
############## ######
######## #### ####
######## ####
######## ######
###### ######
#### ######
###### ######
#### ####
#### ####
#### ####
## ######
#### ######
#### ##########
##################
##############
######
Predict expect is:
1.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
expect is 0
Predict output is:
0.944231 -0.051383 -0.007932 -0.001997 -0.021628 -0.002553 -0.012426 -0.002390 -0.054594 -0.018602
result is 0
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.