CNN , Dataset by MyPath
Train/Validation split Import Dataset (folders Train/test) append list Load the labels , Image pre-processing labelencoder() and...
top of page
搜尋
What’s Neural Networks ??
市面上一堆產品AI、AI的在喊，了解的人，基本上應該都不會去盲從，因為絕大多數都是廣告式AI。 AI 、deep Learn，廣泛的用在廣告用語。其中架構，不外乎 只有 Neural Networks。當然，瞭解之後，千萬別刁難產品推銷業務人員。 Neural...
CNN example
Script : This slideshow requires JavaScript. Result : This slideshow requires JavaScript. judge from fig. I think the loss...
LSTM
Long Short Term Memory networks – usually just called LSTMs – are a special kind of RNN This slideshow requires JavaScript. Excerpt from...
MNIST
import 0 ~ 255 This slideshow requires JavaScript. Convert 0 ~ 255 to 0 ~ 1 ， float32 ， (60000 , 28 , 28 ) to (60000 , 1 , 28 ,...
RNN
Recurrent Neural Network This slideshow requires JavaScript. Excerpt from colah’s blog
CNN
# sample train: 60000 test: 10000, 28 x 28 (nb_samples, 28, 28) The train dataset ， X_train == image data ， y_train == label number，...
KNN example
Use the K-Nearest Neighbor to comparison This slideshow requires JavaScript.
KNN
K-Nearest Neighbor This slideshow requires JavaScript. This slideshow requires JavaScript.
seaborn example
https://github.com/susanli2016/Machine-Learning-with-Python/blob/master/diabetes.csv
Linear Regression
the best-fit regression line is in blue the intercept (b0) and the slope (b1) are shown in green the error terms (e) are represented by...
MNIST MLP – Dropout
減少過度擬合。在深度學習的訓練過程中，Dropout會每次都依據機率丟棄一定比例的神經元不予計算。下面程式，義該Dropout層每次訓練時要丟棄25%的神經元。
魚菜共生系統
魚養殖槽(防水帆布) ， 菜養殖槽 x 4 ，K1消化菌培養瓶 x 3 ， 沉水馬達 x 1 ，植物燈 x 8 ，角鋼，打氣機 ，IOT遙控定時模組 ， 6分PVC管 第一道過濾桶，第二道消化菌桶(含回水至養殖槽) ， 第三道沉澱槽 ，第四道沉澱桶回養殖槽(含K1消化菌培養瓶)
bottom of page