- 博客(5)
- 收藏
- 关注
RSS订阅原创 卷积神经网络
卷积神经网络卷积——池化——Image——Convolution——Max Pooling——Convolution——Max Pooling——Fully Connected——Fully Connected——Classifier
2021-03-05 16:47:47
223
原创 CNN识别手写数字-莫烦python
搭建一个 CNN识别手写数字前面跟着莫烦python/tensorflow教程完成了神经网络识别手写数字的代码。import tensorflow as tffrom tensorflow.examples.tutorials.mnist import input_datamnist = input_data.read_data_sets('MNIST_data', one_hot = True)def compute_accuracy(v_xs, v_ys): # 计算精度函数
2021-03-05 16:31:29
779
1
原创 Tensorboard
Tensorboardimport tensorflow as tfimport numpy as npdef addlayer(inputs, insize, outsize, activation_function=None): #add one more layer and return the output of this layer with tf.name_scope('layer'): with tf.name_scope('weights'):
2021-02-25 21:11:10
164
原创 用Tensorflow框架搭建神经网络
用Tensorflow框架搭建神经网络import tensorflow as tfimport numpy as npimport matplotlib.pyplot as pltdef addlayer(inputs, insize, outsize, activation_function=None): Weights = tf.Variable(tf.random_normal([insize, outsize])) # 定义权值矩阵，一般初始值为随机数比赋全0要好 bi
2021-02-25 15:52:02
241
1
原创 TensorFlow 莫烦python
这里写自定义目录标题举个栗子#create datax_data = np.random.rand(100).astype(np.float32)y_data = x_data *0.1 +0.3#create tensorflow structure start#Weight = tf.Variable(tf.random_uniform([1], -1.0,1.0))biases = tf.Variable(tf.zeros([1]))y = Weight * x_data +
2021-02-25 15:51:45
130
空空如也
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人