[目前，我正在为RTS游戏（确切地说是《魔兽争霸III》）开发一种AI。我正在使用TFlearn教模型如何独自玩游戏。我正在以这种方式收集数据：
[image array in grayscale] = [x-axis position of action, y-axis position of action, tokenized type of action]
因此，实际数据看起来像这样：
[[[36]
[39]
[38]
...
[12]
[48]
[65]]
[[30]
[48]
[ 0]
...
[34]
[49]
[ 8]]
[[28]
[29]
[23]
...
[93]
[38]
[53]]
...
[[ 0]
[ 0]
[ 0]
...
[ 0]
[ 0]
[ 4]]
[[ 0]
[ 0]
[ 0]
...
[ 0]
[ 0]
[ 0]]
[[ 0]
[ 0]
[ 0]
...
[60]
[19]
[43]]]=[1, 1, 35]
并且这意味着，在图像阵列（灰度）上显示情况的情况下，应将鼠标押注在1-x和1-y位置，并进行适当的操作（鼠标操作或键盘按下操作，具体取决于未标记的字符）值）。
尽管如此，我对适当的模型拟合存在问题。我有30000帧，对于模型来说，正确学习似乎太少了，因为在拟合模型后进行预测的情况下，它总是给出相同的输出：
[1,1,0]
我几乎可以肯定，这是因为学习的取景框数量很少。我正在尝试学习一个大约有60个动作的模型，并且屏幕上的更改不太引人注目，因此这组数据确实很难。尽管如此，我想问一问在这种情况下是否还有其他方法可以改善模型的学习。我尝试过：
这是我获取数据的方式：
import os
import cv2
import mss
import pyWinhook as pyHook
import pythoncom
import numpy as np
def get_screen():
with mss.mss() as sct:
screen = np.array(sct.grab((0, 0, 1366, 768)))
screen = cv2.cvtColor(screen, cv2.COLOR_BGR2GRAY)
screen = cv2.resize(screen, (136, 76))
return screen
def get_data():
# file names for training data arrays
file_name = 'training_data.npy'
copy_file_name = 'training_data_copy.npy'
# deciding if previous file with data is saved. If yes, it is opened. If not it's created
if os.path.isfile(file_name):
print('File exists, loading previous data!')
print(os.path.realpath(file_name))
training_data = list(np.load(file_name, allow_pickle=True))
np.save(copy_file_name, training_data)
else:
print('File does not exist, starting fresh!')
training_data = []
# saving data after acquiring 2500 sets of inputs and screenshots
def save_data(screen, output):
training_data.append([screen, output])
if len(training_data) % 2500 == 0:
print(len(training_data))
np.save(file_name, training_data)
print("Frames taken: " + str(len(training_data)))
index = len(training_data) - 1
print(training_data[index])
# getting inputs and screen on mouse event
def OnMouseEvent(event):
action = event.MessageName
screen = get_screen()
output = [event.Position, 0]
if action == 'mouse move':
output[1] = 'move'
elif action == 'mouse left down':
output[1] = 'left'
elif action == 'mouse right down':
output[1] = 'right'
save_data(screen, output)
return True
# getting inputs and screen on keyboard event
def OnKeyboardEvent(event):
if event == 'Delete':
np.save(file_name, training_data)
print("Save and exit")
exit()
screen = get_screen()
output = [(1,1), event.Key]
ctrl_pressed = pyHook.GetKeyState(pyHook.HookConstants.VKeyToID('VK_CONTROL'))
shift_pressed = pyHook.GetKeyState(pyHook.HookConstants.VKeyToID('VK_SHIFT'))
try:
if ctrl_pressed and int(pyHook.HookConstants.IDToName(event.KeyID)) in range(10):
output[1] = 'bind' + event.Key
except ValueError:
pass
try:
if shift_pressed and int(pyHook.HookConstants.IDToName(event.KeyID)) in range(10):
output[1] = 'add' + event.Key
except ValueError:
pass
save_data(screen, output)
return True
# create a hook manager
hm = pyHook.HookManager()
# watch for all mouse events
hm.MouseLeftDown = OnMouseEvent
hm.MouseRightDown = OnMouseEvent
#hm.MouseMove = OnMouseEvent
hm.KeyUp = OnKeyboardEvent
# set the hook
hm.HookMouse()
hm.HookKeyboard()
# wait forever
try:
pythoncom.PumpMessages()
except KeyboardInterrupt:
pass
# looping getting data
while True:
pass
这是我的模型配置：
import tflearn
from tflearn.layers.conv import conv_2d, max_pool_2d
from tflearn.layers.core import input_data, dropout, fully_connected
from tflearn.layers.estimator import regression
from tflearn.layers.normalization import local_response_normalization
import tensorflow as tf
def trainingmodel(width, height, lr):
network = input_data(shape=[None, width, height, 1], name='input')
network = conv_2d(network, 96, 11, strides=4, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 256, 5, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = conv_2d(network, 384, 3, activation='relu')
network = conv_2d(network, 256, 3, activation='relu')
network = max_pool_2d(network, 3, strides=2)
network = local_response_normalization(network)
network = fully_connected(network, 4096, activation='tanh')
network = dropout(network, 0.25)
network = fully_connected(network, 3, activation='softmax')
sgd = tflearn.optimizers.SGD(learning_rate=0.01, lr_decay=0.96, decay_step=100)
network = regression(network, optimizer='adam',
loss='categorical_crossentropy',
learning_rate=lr, name='targets')
model = tflearn.DNN(network, checkpoint_path='model_training_model',
max_checkpoints=1, tensorboard_verbose=2, tensorboard_dir='log')
return model
我不确定使用图片完全可以实现您想做的事情。我已经看到这适用于超级马里奥兄弟，但WC3是一种更为复杂的方案。您需要模型中每个角色的每个动作的图片，才能得出正确的结论。
您的模型可能无法处理未显示给模型的情况（以类似方式）。您可以尝试使用模板匹配为角色提取运动，并在（x，y）位置上而不是在CNN图像上教授模型。