我目前正在为 openai 开发 AI，我正在尝试传递收集到的随机数据以制作神经网络模型，然后使用该模型创建新数据。当我尝试使用新的训练数据制作另一个模型时，它不会让 e 创建一个新模型并给出一个
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'input_1/X' with dtype float
[[Node: input_1/X = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]].
我的代码：
import gym
import random
import numpy as np
import tensorflow as tf
import tflearn
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
from statistics import median, mean
from collections import Counter
import matplotlib.pyplot as plt
env = gym.make("CartPole-v1")
env.reset()#restarts the enviroment
epoch = 5
LR = 2e-4
max_score = 500
number_of_training_games = 100
generations = 3
training_scores = []
random_gen_score = []
def create_random_training_data():
x = 0
accepted_training_data = []
scores_and_data = []
array_of_scores = []
for i in range(number_of_training_games):
score = 0
prev_observation = []
training_data = []
for _ in range(max_score):
action = env.action_space.sample()
observation, reward, done, info = env.step(action)
if len(prev_observation) > 0:
training_data.append([prev_observation, action])
prev_observation = observation
score += reward
if done:
array_of_scores.append(score)
break
for i in training_data:
scores_and_data.append([score,i[0],i[1]])
# reset enviroment
env.reset()
training_scores = array_of_scores
for data in scores_and_data:
if data[0] > median(array_of_scores):
if data[2] == 1:
output = [0,1]
elif data[2] == 0:
output = [1,0]
accepted_training_data.append([data[1], output])
return accepted_training_data
def training_model(sample_data):
inputs = np.array([i[0] for i in sample_data]).reshape(-1,4,1)
correct_output = [i[1] for i in sample_data]
model = neural_network(input_size = len(inputs[0]))
model.fit({'input': inputs}, {'targets': correct_output}, n_epoch=epoch , snapshot_step=500, show_metric=True, run_id='openai_learning')
print(input)
return model
def neural_network(input_size):
# this is where our observation data will go
network = input_data(shape=[None, input_size, 1], name = 'input')
# our neural networks
network = fully_connected(network, 128, activation = 'relu')
#dropout is used to drop randon nodes inorder to reduce over training
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation = 'relu')
network = dropout(network, 0.8)
network = fully_connected(network, 512, activation = 'relu')
network = dropout(network, 0.8)
network = fully_connected(network, 256, activation = 'relu')
network = dropout(network, 0.8)
network = fully_connected(network, 128, activation = 'relu')
network = dropout(network, 0.8)
# this is the output
network = fully_connected(network, 2, activation = 'softmax')
network = regression(network, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')
model = tflearn.DNN(network, tensorboard_dir='log')
return model
def run_generation():
random_sample_data = []
trained_data = []
for i in range(generations):
if len(random_sample_data) ==0:
random_sample_data = create_random_training_data()
model1 = training_model(random_sample_data)
else:
trained_data = one_generation(model1)
model2 = training_model(trained_data)
return model2
def one_generation(model):
accepted_training_data = []
scores_and_data = []
array_of_scores = []
for i in range(number_of_training_games):
score = 0
prev_observation = []
training_data = []
for _ in range(max_score):
if len(prev_observation) == 0:
action = env.action_space.sample()
else:
action = np.argmax(model.predict(prev_observation.reshape(-1,len(prev_observation),1))[0])
observation, reward, done, info = env.step(action)
if len(prev_observation) > 0:
training_data.append([prev_observation, action])
prev_observation = observation
score += reward
if done:
array_of_scores.append(score)
break
for i in training_data:
scores_and_data.append([score,i[0],i[1]])
# reset enviroment
env.reset()
for data in scores_and_data:
if data[0] > median(array_of_scores):
if data[2] == 1:
output = [0,1]
elif data[2] == 0:
output = [1,0]
accepted_training_data.append([data[1], output])
return accepted_training_data
def testing():
scores = []
model = run_generation()
for _ in range(100):
score = 0
game_memory = []
prev_obs = []
env.reset()
for _ in range(max_score):
env.render()
#first move is going to be random
if len(prev_obs)==0:
action = random.randrange(0,2)
else:
action = np.argmax(model.predict(prev_obs.reshape(-1,len(prev_obs),1))[0])
#records actions
new_observation, reward, done, info = env.step(action)
prev_obs = new_observation
game_memory.append([new_observation, action])
score+=reward
if done: break
scores.append(score)
#print('Average training Score:',sum(training_scores)/len(training_scores))
print('Average Score:',sum(scores)/len(scores))
print (scores)
testing()
错误：
Traceback (most recent call last):
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1039, in _do_call
return fn(*args)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1021, in _run_fn
status, run_metadata)
File "/anaconda/lib/python3.6/contextlib.py", line 89, in __exit__
next(self.gen)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status
pywrap_tensorflow.TF_GetCode(status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'input_1/X' with dtype float
[[Node: input_1/X = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 259, in <module>
testing()
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 219, in testing
model = run_generation()
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 148, in run_generation
model2 = training_model(trained_data)
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 92, in training_model
model.fit({'input': inputs}, {'targets': correct_output}, n_epoch=epoch , snapshot_step=500, show_metric=True, run_id='openai_learning')
File "/anaconda/lib/python3.6/site-packages/tflearn/models/dnn.py", line 215, in fit
callbacks=callbacks)
File "/anaconda/lib/python3.6/site-packages/tflearn/helpers/trainer.py", line 336, in fit
show_metric)
File "/anaconda/lib/python3.6/site-packages/tflearn/helpers/trainer.py", line 777, in _train
feed_batch)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 778, in run
run_metadata_ptr)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 982, in _run
feed_dict_string, options, run_metadata)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1032, in _do_run
target_list, options, run_metadata)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1052, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: You must feed a value for placeholder tensor 'input_1/X' with dtype float
[[Node: input_1/X = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]
Caused by op 'input_1/X', defined at:
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 259, in <module>
testing()
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 219, in testing
model = run_generation()
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 148, in run_generation
model2 = training_model(trained_data)
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 90, in training_model
model = neural_network(input_size = len(inputs[0]))
File "/Users/Duncan/Desktop/ai projects/evolutionDNN.py", line 100, in neural_network
network = input_data(shape=[None, input_size, 1], name = 'input')
File "/anaconda/lib/python3.6/site-packages/tflearn/layers/core.py", line 81, in input_data
placeholder = tf.placeholder(shape=shape, dtype=dtype, name="X")
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/array_ops.py", line 1507, in placeholder
name=name)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/ops/gen_array_ops.py", line 1997, in _placeholder
name=name)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 768, in apply_op
op_def=op_def)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2336, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/anaconda/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1228, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'input_1/X' with dtype float
[[Node: input_1/X = Placeholder[dtype=DT_FLOAT, shape=[], _device="/job:localhost/replica:0/task:0/cpu:0"]()]]