The ann from dreamilk

👋 Hi, I’m @dreamilk
👀 I’m interested in coding
🌱 I’m currently learning cpp
💞️ I’m currently studying in zju
📫 How to reach me ...

ann's People

Contributors

Stargazers

Watchers

ann's Issues

直接run 所有的loss都是nan

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

saveModel Error是怎么回事

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

Recommend Projects