ironrat

摘要： 一、Activation function Sigmod\[g(z) = \frac{1}{1 + e^{-z}} \] For Binary Classification(Logistic regression)/Output layer is binary. ReLU——most common 閱讀全文

摘要： 1.how to build layers Manually（1x3matrix） x = np.arrat([200.0, 17.0]) layer_1 = Dense(units=3, activation='sigmoid') a1 = layer_1(x) layer_2 = Dense(u 閱讀全文

摘要： 點擊查看代碼 python train.py \ --image_root [path to image directory] \ --mask_root [path mask directory] python train.py \ --image_root [path to image dire 閱讀全文