如何在 Python 中使用函式式 API 處理殘差連線?
Keras 存在於 Tensorflow 包中。可以使用以下程式碼行訪問它。
import tensorflow from tensorflow import keras
Keras 函式式 API 有助於建立比使用順序式 API 建立的模型更靈活的模型。函式式 API 可以處理具有非線性拓撲的模型,可以共享層,並可以處理多個輸入和輸出。深度學習模型通常是一個包含多個層的無環有向圖 (DAG)。函式式 API 有助於構建圖層圖。
我們正在使用 Google Colaboratory 來執行以下程式碼。Google Colab 或 Colaboratory 有助於在瀏覽器上執行 Python 程式碼,無需任何配置,並且可以免費訪問 GPU(圖形處理單元)。Colaboratory 建立在 Jupyter Notebook 之上。以下是程式碼片段:
示例
print("Toy ResNet model for CIFAR10")
print("Layers generated for model")
inputs = keras.Input(shape=(32, 32, 3), name="img")
x = layers.Conv2D(32, 3, activation="relu")(inputs)
x = layers.Conv2D(64, 3, activation="relu")(x)
block_1_output = layers.MaxPooling2D(3)(x)
x = layers.Conv2D(64, 3, activation="relu", padding="same")(block_1_output)
x = layers.Conv2D(64, 3, activation="relu", padding="same")(x)
block_2_output = layers.add([x, block_1_output])
x = layers.Conv2D(64, 3, activation="relu", padding="same")(block_2_output)
x = layers.Conv2D(64, 3, activation="relu", padding="same")(x)
block_3_output = layers.add([x, block_2_output])
x = layers.Conv2D(64, 3, activation="relu")(block_3_output)
x = layers.GlobalAveragePooling2D()(x)
x = layers.Dense(256, activation="relu")(x)
x = layers.Dropout(0.5)(x)
outputs = layers.Dense(10)(x)
model = keras.Model(inputs, outputs, name="toy_resnet")
print("More information about the model")
model.summary()程式碼來源 − https://www.tensorflow.org/guide/keras/functional
輸出
Toy ResNet model for CIFAR10 Layers generated for model More information about the model Model: "toy_resnet" ________________________________________________________________________________ __________________ Layer (type) Output Shape Param # Connected to ================================================================================ ================== img (InputLayer) [(None, 32, 32, 3)] 0 ________________________________________________________________________________ __________________ conv2d_32 (Conv2D) (None, 30, 30, 32) 896 img[0][0] ________________________________________________________________________________ __________________ conv2d_33 (Conv2D) (None, 28, 28, 64) 18496 conv2d_32[0][0] ________________________________________________________________________________ __________________ max_pooling2d_8 (MaxPooling2D) (None, 9, 9, 64) 0 conv2d_33[0][0] ________________________________________________________________________________ __________________ conv2d_34 (Conv2D) (None, 9, 9, 64) 36928 max_pooling2d_8[0][0] ________________________________________________________________________________ __________________ conv2d_35 (Conv2D) (None, 9, 9, 64) 36928 conv2d_34[0][0] ________________________________________________________________________________ __________________ add_12 (Add) (None, 9, 9, 64) 0 conv2d_35[0][0] max_pooling2d_8[0][0] ________________________________________________________________________________ __________________ conv2d_36 (Conv2D) (None, 9, 9, 64) 36928 add_12[0][0] ________________________________________________________________________________ __________________ conv2d_37 (Conv2D) (None, 9, 9, 64) 36928 conv2d_36[0][0] ________________________________________________________________________________ __________________ add_13 (Add) (None, 9, 9, 64) 0 conv2d_37[0][0] add_12[0][0] ________________________________________________________________________________ __________________ conv2d_38 (Conv2D) (None, 7, 7, 64) 36928 add_13[0][0] ________________________________________________________________________________ __________________ global_average_pooling2d_1 (Glo (None, 64) 0 conv2d_38[0][0] ________________________________________________________________________________ __________________ dense_40 (Dense) (None, 256) 16640 global_average_pooling2d_1[0][0] ________________________________________________________________________________ __________________ dropout_2 (Dropout) (None, 256) 0 dense_40[0][0] ________________________________________________________________________________ __________________ dense_41 (Dense) (None, 10) 2570 dropout_2[0][0] ================================================================================ ================== Total params: 223,242 Trainable params: 223,242 Non-trainable params: 0 ________________________________________________________________________________ __________________
解釋
該模型具有多個輸入和輸出。
函式式 API 簡化了與非線性連線拓撲的工作。
此模型的各層並非按順序連線,因此“Sequential”API 無法處理它。
這就是殘差連線發揮作用的地方。
構建了一個使用 CIFAR10 的示例 ResNet 模型來演示這一點。
廣告
資料結構
網路
關係資料庫管理系統 (RDBMS)
作業系統
Java
iOS
HTML
CSS
Android
Python
C 程式設計
C++
C#
MongoDB
MySQL
Javascript
PHP