随笔分类 - tensorflow进阶
摘要：import tensorflow as tf @tf.function #启用图必须开启 def my_func(x, y): # A simple hand-rolled layer. return tf.multiply(x, y) # Set up logging. logdir = r"C
阅读全文
摘要：https://www.bilibili.com/video/BV1Lx411j7ws?p=9点击进入
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 matplotlib numpy """ import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import numpy a
阅读全文
摘要：ncies: tensorflow: 1.1.0 matplotlib numpy """ import tensorflow as tf import numpy as np import matplotlib.pyplot as plt tf.set_random_seed(1) np.rand
阅读全文
摘要：""" Know more, visit my Python tutorial page: https://morvanzhou.github.io/tutorials/ My Youtube Channel: https://www.youtube.com/user/MorvanZhou More
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 numpy """ import tensorflow as tf import numpy as np tf.set_random_seed(1) np.random.seed(1) # fake data x = np.linspa
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 matplotlib numpy """ import tensorflow as tf import matplotlib.pyplot as plt import numpy as np tf.set_random_seed(1)
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 matplotlib numpy """ import tensorflow as tf import matplotlib.pyplot as plt import numpy as np tf.set_random_seed(1)
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 matplotlib numpy """ import tensorflow as tf import matplotlib.pyplot as plt import numpy as np tf.set_random_seed(1)
阅读全文
摘要：#tensorflow2代码 #设置优化器 x_data = np.random.rand(100).astype(np.float32) b_data = tf.random.normal([1],mean=1,stddev=0.5) print(tf.reduce_mean(b_data)) y
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 matplotlib """ import tensorflow as tf import numpy as np import matplotlib.pyplot as plt # fake data x = np.linspace(
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 """ import tensorflow as tf var = tf.Variable(0) # our first variable in the "global_variable" set add_operation = tf.
阅读全文
摘要：Dependencies: tensorflow: 1.1.0 """ import tensorflow as tf x1 = tf.placeholder(dtype=tf.float32, shape=None) y1 = tf.placeholder(dtype=tf.float32, sh
阅读全文
摘要：session """ Dependencies: tensorflow: 1.1.0 """ import tensorflow as tf m1 = tf.constant([[2, 2]]) m2 = tf.constant([[3], [3]]) dot_operation = tf.mat
阅读全文
