hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

delete unused code

Browse Source
This commit is contained in:
Dong Yan 2017-12-26 19:29:35 +08:00
parent 029ab199f4
commit 0c3ff3bf37
4 changed files with 29 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
AlphaGo/.gitignore vendored
View File

@ -1,5 +1,5 @@
data data
checkpoints checkpoints
checkpoints_origin random
*.log *.log
*.txt *.txt

16
AlphaGo/engine.py
View File

@ -13,8 +13,6 @@ import utils
class GTPEngine(): class GTPEngine():
def __init__(self, **kwargs): def __init__(self, **kwargs):
self.size = 9
self.komi = 6.5
try: try:
self._game = kwargs['game_obj'] self._game = kwargs['game_obj']
self._game.clear() self._game.clear()
@ -143,11 +141,9 @@ class GTPEngine():
self.disconnect = True self.disconnect = True
return None, True return None, True
def cmd_boardsize(self, args, **kwargs): def cmd_boardsize(self, board_size, **kwargs):
if args.isdigit(): if board_size.isdigit():
size = int(args) self._game.set_size(int(board_size))
self.size = size
self._game.set_size(size)
return None, True return None, True
else: else:
return 'non digit size', False return 'non digit size', False
@ -156,11 +152,9 @@ class GTPEngine():
self._game.clear() self._game.clear()
return None, True return None, True
def cmd_komi(self, args, **kwargs): def cmd_komi(self, komi, **kwargs):
try: try:
komi = float(args) self._game.set_komi(float(komi))
self.komi = komi
self._game.set_komi(komi)
return None, True return None, True
except ValueError: except ValueError:
raise ValueError("syntax error") raise ValueError("syntax error")

44
AlphaGo/play.py
View File

@ -5,6 +5,8 @@ import re
import Pyro4 import Pyro4
import time import time
import os import os
import utils
from time import gmtime, strftime
python_version = sys.version_info python_version = sys.version_info
@ -13,8 +15,6 @@ if python_version < (3, 0):
else: else:
import _pickle as cPickle import _pickle as cPickle
class Data(object): class Data(object):
def __init__(self): def __init__(self):
self.boards = [] self.boards = []
@ -45,9 +45,9 @@ if __name__ == '__main__':
# black_weight_path = "./checkpoints" # black_weight_path = "./checkpoints"
# white_weight_path = "./checkpoints_origin" # white_weight_path = "./checkpoints_origin"
if args.black_weight_path is not None and (not os.path.exists(args.black_weight_path)): if args.black_weight_path is not None and (not os.path.exists(args.black_weight_path)):
raise ValueError("Can't not find the network weights for black player.") raise ValueError("Can't find the network weights for black player.")
if args.white_weight_path is not None and (not os.path.exists(args.white_weight_path)): if args.white_weight_path is not None and (not os.path.exists(args.white_weight_path)):
raise ValueError("Can't not find the network weights for white player.") raise ValueError("Can't find the network weights for white player.")
# kill the old server # kill the old server
# kill_old_server = subprocess.Popen(['killall', 'pyro4-ns']) # kill_old_server = subprocess.Popen(['killall', 'pyro4-ns'])
@ -86,12 +86,13 @@ if __name__ == '__main__':
black_role_name = 'black' + str(args.id) black_role_name = 'black' + str(args.id)
white_role_name = 'white' + str(args.id) white_role_name = 'white' + str(args.id)
agent_v0 = subprocess.Popen( #TODO : check if we can get the output of player from the stdout, for debug convenience
black_player = subprocess.Popen(
['python', '-u', 'player.py', '--game=' + args.game, '--role=' + black_role_name, ['python', '-u', 'player.py', '--game=' + args.game, '--role=' + black_role_name,
'--checkpoint_path=' + str(args.black_weight_path), '--debug=' + str(args.debug)], '--checkpoint_path=' + str(args.black_weight_path), '--debug=' + str(args.debug)],
stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
agent_v1 = subprocess.Popen( white_player = subprocess.Popen(
['python', '-u', 'player.py', '--game=' + args.game, '--role=' + white_role_name, ['python', '-u', 'player.py', '--game=' + args.game, '--role=' + white_role_name,
'--checkpoint_path=' + str(args.white_weight_path), '--debug=' + str(args.debug)], '--checkpoint_path=' + str(args.white_weight_path), '--debug=' + str(args.debug)],
stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.STDOUT) stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
@ -99,14 +100,15 @@ if __name__ == '__main__':
server_list = "" server_list = ""
while (black_role_name not in server_list) or (white_role_name not in server_list): while (black_role_name not in server_list) or (white_role_name not in server_list):
if python_version < (3, 0): if python_version < (3, 0):
# TODO : @renyong what is the difference between those two options?
server_list = subprocess.check_output(['pyro4-nsc', 'list']) server_list = subprocess.check_output(['pyro4-nsc', 'list'])
else: else:
server_list = subprocess.check_output(['pyro4-nsc', 'list']) server_list = subprocess.check_output(['pyro4-nsc', 'list'])
print("Waiting for the server start...") print("Waiting for the server start...")
time.sleep(1) time.sleep(1)
print(server_list) print(server_list)
print("Start black player at : " + str(agent_v0.pid)) print("Start black player at : " + str(black_player.pid))
print("Start white player at : " + str(agent_v1.pid)) print("Start white player at : " + str(white_player.pid))
data = Data() data = Data()
player = [None] * 2 player = [None] * 2
@ -121,7 +123,7 @@ if __name__ == '__main__':
size = {"go":9, "reversi":8} size = {"go":9, "reversi":8}
show = ['.', 'X', 'O'] show = ['.', 'X', 'O']
evaluate_rounds = 1 evaluate_rounds = 100
game_num = 0 game_num = 0
try: try:
#while True: #while True:
@ -141,8 +143,8 @@ if __name__ == '__main__':
print "\n", print "\n",
data.boards.append(board) data.boards.append(board)
start_time = time.time() start_time = time.time()
move = player[turn].run_cmd(str(num) + ' genmove ' + color[turn] + '\n') move = player[turn].run_cmd(str(num) + ' genmove ' + color[turn])[:-1]
print(role[turn] + " : " + str(move)), print("\n" + role[turn] + " : " + str(move)),
num += 1 num += 1
match = re.search(pattern, move) match = re.search(pattern, move)
if match is not None: if match is not None:
@ -160,29 +162,23 @@ if __name__ == '__main__':
prob = prob.replace('],', ']') prob = prob.replace('],', ']')
prob = eval(prob) prob = eval(prob)
data.probs.append(prob) data.probs.append(prob)
score = player[turn].run_cmd(str(num) + ' get_score') score = player[0].run_cmd(str(num) + ' get_score')
print("Finished : {}".format(score.split(" ")[1])) print("Finished : {}".format(score.split(" ")[1]))
# TODO: generalize the player
if eval(score.split(" ")[1]) > 0: if eval(score.split(" ")[1]) > 0:
data.winner = 1 data.winner = utils.BLACK
if eval(score.split(" ")[1]) < 0: if eval(score.split(" ")[1]) < 0:
data.winner = -1 data.winner = utils.WHITE
player[0].run_cmd(str(num) + ' clear_board') player[0].run_cmd(str(num) + ' clear_board')
player[1].run_cmd(str(num) + ' clear_board') player[1].run_cmd(str(num) + ' clear_board')
file_list = os.listdir(args.data_path) file_list = os.listdir(args.data_path)
if not file_list: current_time = strftime("%Y%m%d_%H%M%S", gmtime())
data_num = 0 with open(args.data_path + current_time + ".pkl", "wb") as file:
else:
file_list.sort(key=lambda file: os.path.getmtime(args.data_path + file) if not os.path.isdir(
args.data_path + file) else 0)
data_num = eval(file_list[-1][:-4]) + 1
with open("./data/" + str(data_num) + ".pkl", "wb") as file:
picklestring = cPickle.dump(data, file) picklestring = cPickle.dump(data, file)
data.reset() data.reset()
game_num += 1 game_num += 1
except KeyboardInterrupt: except KeyboardInterrupt:
pass pass
subprocess.call(["kill", "-9", str(agent_v0.pid)]) subprocess.call(["kill", "-9", str(black_player.pid)])
subprocess.call(["kill", "-9", str(agent_v1.pid)]) subprocess.call(["kill", "-9", str(white_player.pid)])
print("Kill all player, finish all game.") print("Kill all player, finish all game.")

12
AlphaGo/player.py
View File

@ -1,8 +1,5 @@
import argparse import argparse
import time
import sys
import Pyro4 import Pyro4
from game import Game from game import Game
from engine import GTPEngine from engine import GTPEngine
@ -17,10 +14,8 @@ class Player(object):
self.engine = kwargs['engine'] self.engine = kwargs['engine']
def run_cmd(self, command): def run_cmd(self, command):
#return "inside the Player of player.py"
return self.engine.run_cmd(command) return self.engine.run_cmd(command)
if __name__ == '__main__': if __name__ == '__main__':
parser = argparse.ArgumentParser() parser = argparse.ArgumentParser()
parser.add_argument("--checkpoint_path", type=str, default=None) parser.add_argument("--checkpoint_path", type=str, default=None)
@ -29,12 +24,7 @@ if __name__ == '__main__':
parser.add_argument("--game", type=str, default=False) parser.add_argument("--game", type=str, default=False)
args = parser.parse_args() args = parser.parse_args()
if args.checkpoint_path == 'None': game = Game(name=args.game, role=args.role, checkpoint_path=eval(args.checkpoint_path), debug=eval(args.debug))
args.checkpoint_path = None
debug = False
if args.debug == "True":
debug = True
game = Game(name=args.game, role=args.role, checkpoint_path=args.checkpoint_path, debug=debug)
engine = GTPEngine(game_obj=game, name='tianshou', version=0) engine = GTPEngine(game_obj=game, name='tianshou', version=0)
daemon = Pyro4.Daemon() # make a Pyro daemon daemon = Pyro4.Daemon() # make a Pyro daemon