欢迎访问 生活随笔!

生活随笔

当前位置: 首页 > 编程资源 > 编程问答 >内容正文

编程问答

TensorFlow维度变换函数语句

发布时间:2025/3/20 编程问答 28 豆豆
生活随笔 收集整理的这篇文章主要介绍了 TensorFlow维度变换函数语句 小编觉得挺不错的,现在分享给大家,帮大家做个参考.

学习课程
1.reshape

a = tf.random.normal([4,28,28,3]) #4张照片 a.shape,a.ndim #TensorShape([4,28,28,3]),4 tf.reshape(a,[4,784,3]).shape #TensorShape([4,784,3]) tf.reshape(a,[4,-1,3]).shape #TensorShape([4,784,3]) tf.reshape(a,[4,-1]).shape #TensorShape([4,2352]) tf.reshae(tf.reshape(a,[4,-1])[4,1,784,3]).shape #TensorShape([4,1,784,3])

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])

总结

以上是生活随笔为你收集整理的TensorFlow维度变换函数语句的全部内容,希望文章能够帮你解决所遇到的问题。

如果觉得生活随笔网站内容还不错,欢迎将生活随笔推荐给好友。