Question

我想将Follow pytorch网络（v1.2）更改为tensorflow。我在 tf.nn.conv2d 和 tf.keras.layers.Conv2D 之间感到困惑，我该选择什么？

import firebase from 'firebase';
import 'firebase/app';
import 'firebase/firestore'
import 'firebase/auth';



const config = { /* COPY THE ACTUAL CONFIG FROM FIREBASE CONSOLE */
    (there is my api info)
};
const fire = firebase.initializeApp(config);
export default fire;

Answer 1

tf.nn.conv2d是功能性api，tf.keras.layers.Conv2D是层级api。您应该使用后一种。它与torch.nn.functional.conv2d和torch.nn.Conv2D之间的关系非常相似。

import tensorflow as tf
from tensorflow.keras import Sequential
from tensorflow.keras.layers import Conv2D, ReLU, BatchNormalization

model = Sequential()
model.add(Conv2D(filters=10, kernel_size=3, strides=1))
model.add(BatchNormalization())
model.add(ReLU())

如何将以下代码从pytorch更改为tensorflow？

1 个答案: