![](https://img-blog.csdnimg.cn/20201014180756928.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
tf api
github_元宝
这个作者很懒,什么都没留下…
展开
-
tf estimator debug
How to print tensor in Tensorflow custom estimator for debugging?原创 2021-10-21 13:39:35 · 172 阅读 · 0 评论 -
tfrecord和tf.dataset
老版本:filename_queue = tf.train.string_input_producer([tfrecords_filename],num_epochs=None) #读入流中reader = tf.TFRecordReader()_, serialized_example = reader.read(filename_queue)features = tf.parse_single_example(serialized_example,原创 2021-04-16 21:06:42 · 315 阅读 · 0 评论 -
keras下model.fit()——fit函数参数及返回值详解
network.fit( x, y,batch_size=32, epochs=10, verbose=1, callbacks=None,validation_split=0.0, validation_data=None,shuffle=True, class_weight=None,sample_weight=None, initial_epoch=0)x:输入数据。如果模型只有一个输入,那么x的类型是numpyarray,如果模型有多个输入,那么x的类型应当为list,list的元素是原创 2021-04-19 11:59:15 · 4701 阅读 · 0 评论 -
tf.newaxis vs tf.expand_dims
There is no real difference between the three, but sometimes one or the other may be more convenient:What’s the difference between using tf.expand_dims and tf.newaxis in Tensorflow?原创 2021-09-15 13:20:29 · 151 阅读 · 0 评论 -
tf 维度变化 汇总
tf.reduce_mean(input_tensor, axis=None, keep_dims=False, name=None, reduction_indices=None)Computes the mean of elements across dimensions of a tensor.Reduces input_tensor along the dimensions given in axis. Unless keep_dims is true, the rank of the ten原创 2021-05-09 21:07:14 · 98 阅读 · 0 评论