【发布时间】:2017-06-23 19:07:22
【问题描述】:
我正在尝试使用 tensorflow 学习卷积神经网络,我正在使用下面的代码来创建我的网络。
# network weights
W_conv1 = weight_variable([8, 8, 4, 32])
b_conv1 = bias_variable([32])
W_conv2 = weight_variable([4, 4, 32, 64])
b_conv2 = bias_variable([64])
W_conv3 = weight_variable([3, 3, 64, 64])
b_conv3 = bias_variable([64])
W_fc1 = weight_variable([1600, 512])
b_fc1 = bias_variable([512])
W_fc2 = weight_variable([512, ACTIONS])
b_fc2 = bias_variable([ACTIONS])
# input layer
s = tf.placeholder("float", [None, 80, 80, 4])
# hidden layers
h_conv1 = tf.nn.relu(conv2d(s, W_conv1, 4) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2, 2) + b_conv2)
#h_pool2 = max_pool_2x2(h_conv2)
h_conv3 = tf.nn.relu(conv2d(h_conv2, W_conv3, 1) + b_conv3)
#h_pool3 = max_pool_2x2(h_conv3)
#h_pool3_flat = tf.reshape(h_pool3, [-1, 256])
h_conv3_flat = tf.reshape(h_conv3, [-1, 1600])
h_fc1 = tf.nn.relu(tf.matmul(h_conv3_flat, W_fc1) + b_fc1)
# readout layer
readout = tf.matmul(h_fc1, W_fc2) + b_fc2
此网络采用 [80,80,4] 对象输出 ACTIONS 预测;(ACTIONS 类数)
我的问题是如何创建一个输出 [a,b] 之间值的网络
【问题讨论】:
-
任何 CNN 都可以输出 [0, 1] 中的数字,然后你将你的范围归一化为 [0, 1],然后问题就解决了。
标签: tensorflow neural-network deep-learning