Question

从此文件：https://github.com/llSourcell/pong_neural_network_live/blob/master/RL.py

我已更新了这些行

#first convolutional layer. bias vector
#creates an empty tensor with all elements set to zero with a shape

W_conv1 = tf.Variable(tf.zeros([8, 8, 4, 32]) , name='W_conv1')
b_conv1 = tf.Variable(tf.zeros([32]), name='b_conv1')

W_conv2 = tf.Variable(tf.zeros([4, 4, 32, 64]), name='W_conv2')
b_conv2 = tf.Variable(tf.zeros([64]), name='b_conv2')

W_conv3 = tf.Variable(tf.zeros([3, 3, 64, 64]), name='W_conv3')
b_conv3 = tf.Variable(tf.zeros([64]), name='b_conv3')

W_fc4 = tf.Variable(tf.zeros([3136, 784]), name='W_fc4')
b_fc4 = tf.Variable(tf.zeros([784]), name='b_fc4')

W_fc5 = tf.Variable(tf.zeros([784, ACTIONS]), name='W_fc5')
b_fc5 = tf.Variable(tf.zeros([ACTIONS]), name='b_fc5')

和

saver.save(sess, './' + 'pong' + '-dqn', global_step = timestamp)

并在：

def main():
    # ////
    tf.reset_default_graph()
    imported_meta = tf.train.import_meta_graph('./' + 'pong' + '-dqn-' + '48000' + '.meta')
    imported_meta.restore(sess, tf.train.latest_checkpoint('./'))
    # ////

尝试恢复模型但出现此错误：

TypeError：无法将feed_dict键解释为Tensor：名称“save / Const：0”指的是不存在的Tensor。图中不存在“save / Const”操作。

当我尝试这个时：

 graph = tf.get_default_graph() 
 W_conv1 = graph.get_tensor_by_name("W_conv1:0")
 b_conv1 = graph.get_tensor_by_name("wb_conv1:0") 
 W_conv2 = graph.get_tensor_by_name("W_conv2:0")
 b_conv2 = graph.get_tensor_by_name("wb_conv2:0") 
 W_conv3 = graph.get_tensor_by_name("W_conv3:0")
 b_conv3 = graph.get_tensor_by_name("b_conv3:0") 
 W_fc4 = graph.get_tensor_by_name("W_fc4:0")
 b_fc4 = graph.get_tensor_by_name("b_fc4:0") 
 W_fc5 = graph.get_tensor_by_name("W_fc5:0")
 b_fc5 = graph.get_tensor_by_name("b_fc5:0")

我收到此错误：

“名称'W_conv1：0'指的是不存在的Tensor。图中不存在'W_conv1'操作。

为什么会这样？我在pygame中创建了我的游戏，我正在尝试将它连接到RL。我想确保我可以保存并加载我的进度。我只是遇到了如何保存和加载的逻辑问题。

提前致谢！

TypeError：无法将feed_dict键解释为Tensor：名称“save / Const：0”指的是不存在的Tensor

0 个答案: