TensorFlow维度变换函数语句
生活随笔
收集整理的這篇文章主要介紹了
TensorFlow维度变换函数语句
小編覺得挺不錯的,現(xiàn)在分享給大家,幫大家做個參考.
學習課程
1.reshape
Reshape could lead to potential bugs!
2.tf.transpose
a = tf.random.normal([4,28,56,3]) tf.transpose(a).shape #TensorShape([3,56,28,4]) tf.transpose(a,perm=[0,1,3,2]).shape #TensorShape([4,28,3,56])3.Expand dim
a = tf.random.normal([4,35,8]) tf.expand_dims(a,axis=0).shape #TensorShape([1,4,35,8]) tf.expand_dims(a,axis=1).shape #TensorShape([4,1,35,8]) tf.expand_dims(a,axis=-1).shape #TensorShape([4,35,8,1]) tf.expand_dims(a,axis=-4).shape #TensorShape([1,4,35,8])4.Squeeze dim
a = tf.random.normal([1,1,4,35,1,8]) tf.squeeze(a,axis=0).shape #TensorShape([1,4,35,1,8]) tf.squeeze(a,axis=4).shape #TensorShape([1,1,4,35,8]) tf.squeeze(a,axis=-2).shape #TensorShape([1,1,4,35,8])5.Broadcasting
x=tf.random.normal([4,32,32,3]) x+tf.random.normal([3]).shape #TensorShape([4,32,32,3]) x+tf.random.normal([32,32,1]).shape #TensorShape([4,32,32,3]) x+tf.random.normal([4,1,1,1]).shape #TensorShape([4,32,32,3])6.tf.broadcast_to
b=tf.broadcast_to(tf.random.normal([4,1,1,1]),[4,32,32,3]).shape #TensorShape([4,32,32,3])總結(jié)
以上是生活随笔為你收集整理的TensorFlow维度变换函数语句的全部內(nèi)容,希望文章能夠幫你解決所遇到的問題。
- 上一篇: TensorFlow索引与切片语句
- 下一篇: TensorFlow 合并与分割