摘要:
import tensorflow as tf import numpy as np import pandas as pd import matplotlib.pylab as plt import matplotlib as mpl # 读取数据集 TRIN_URL = 'http://down 阅读全文
posted @ 2020-08-04 20:24
山…隹
阅读(496)
评论(0)
推荐(0)
摘要:
import tensorflow as tf import numpy as np import matplotlib.pylab as plt # 模拟数据 x = np.array( [137.97, 104.50, 100, 126.32, 79.20, 99.00, 124.0, 114. 阅读全文
posted @ 2020-08-04 16:21
山…隹
阅读(715)
评论(0)
推荐(0)
摘要:
import tensorflow as tf import numpy as np x = np.array([1, 2, 3, 4]) y = np.array([0,0,1,1]) w = tf.Variable(1.) b = tf.Variable(1.) sigmodX = 1 / (1 阅读全文
posted @ 2020-08-04 15:17
山…隹
阅读(520)
评论(0)
推荐(0)
摘要:
平方损失函数求导后,偏导太小,迭代更新慢,所以考虑用交叉熵损失函数(注意标记值和预测值不能写反了)(标记值为0或1,对0取对数是不存在的额): 交叉熵损失函数满足作为损失函数的两大规则:非负性,单调一致性 阅读全文
posted @ 2020-08-04 14:38
山…隹
阅读(1235)
评论(0)
推荐(0)
摘要:
阅读全文
posted @ 2020-08-04 12:15
山…隹
阅读(293)
评论(0)
推荐(0)

浙公网安备 33010602011771号