摘要：其中build5方法预测最准确mae loss最小 tensorflow 阅读全文

摘要：import tensorflow as tf from input_data import Data import matplotlib.pyplot as plt import os data=Data("./data/") X=tf.placeholder(tf.float32,[None,40,40,3]) y=tf.placeholder(tf.float32,[None,62... 阅读全文

摘要：brew tap homebrew/science brew install opencv cd /Library/Python/2.7/site-packages/ 如果是anaconda切换到anaconda目录 which python 查看python目录 将brew安装的opencv两个文 阅读全文

摘要：conda info --envs 查看全部环境 conda create -n snakes python=2 创建python2 环境snakes conda remove -n flowers --all 删除flowers环境 ·Linux，OS X：source activate snak 阅读全文

摘要：def add_layer(inputs, in_size, out_size, activation_function=None): # add one more layer and return the output of this layer Weights = tf.Variable(tf.random_normal([in_size, out_size])) b... 阅读全文

摘要：1 def compute_accuracy(v_xs, v_ys): 2 global prediction 3 y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1}) 4 correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_... 阅读全文