我試圖在張量流中編寫我自己的成本函數,但顯然我不能'分割'張量對象? import tensorflow as tf
import numpy as np
# Establish variables
x = tf.placeholder("float", [None, 3])
W = tf.Variable(tf.zeros([3,6]))
b = tf.Variable(tf.zer
當我寫的所有代碼here到.py文件,然後運行它,我得到以下的輸出: can't determine number of CPU cores: assuming 4
I tensorflow/core/common_runtime/local_device.cc:25] Local device intra op parallelism threads: 4
can't determine
有關於如何安裝它的an official guide,並沒有多說關於它的實際開發。我的理解是quite big challenge in developing with Docker in general。更不用說可能有deeper technical complications關於TensorFlow的使用,也許主要是thanks to GPUs。所以拉動碼頭圖像後有很多東西... 有沒有人有一