小编Kay*_*sch的帖子

我正在尝试制作一个简单的神经网络，但我有一个简单的问题：如何将等级为 1 的张量转换为等级为 2 的张量？

我尝试使用Tensorflow和OpenAI的Gym来编写Deep Q网络来玩Atari游戏.这是我的代码:

import tensorflow as tf
import gym
import numpy as np
import os

env_name = 'Breakout-v0'
env = gym.make(env_name)
num_episodes = 100
input_data = tf.placeholder(tf.float32,(None,)+env.observation_space.shape)
output_labels = tf.placeholder(tf.float32,(None,env.action_space.n))

def convnet(data):
    layer1 = tf.layers.conv2d(data,32,5,activation=tf.nn.relu)
    layer1_dropout = tf.nn.dropout(layer1,0.8)
    layer2 = tf.layers.conv2d(layer1_dropout,64,5,activation=tf.nn.relu)
    layer2_dropout = tf.nn.dropout(layer2,0.8)
    layer3 = tf.layers.conv2d(layer2_dropout,128,5,activation=tf.nn.relu)
    layer3_dropout = tf.nn.dropout(layer3,0.8)
    layer4 = tf.layers.dense(layer3_dropout,units=128,activation=tf.nn.softmax,kernel_initializer=tf.zeros_initializer)
    layer5 = tf.layers.flatten(layer4)
    layer5_dropout = tf.nn.dropout(layer5,0.8)
    layer6 = tf.layers.dense(layer5_dropout,units=env.action_space.n,activation=tf.nn.softmax,kernel_initializer=tf.zeros_initializer)
    return layer6

logits = convnet(input_data)
loss = tf.losses.sigmoid_cross_entropy(output_labels,logits)
train = tf.train.GradientDescentOptimizer(0.001).minimize(loss)
saver = tf.train.Saver()
init = tf.global_variables_initializer()
discount_factor = …