def do_eval(data_path, model_name='mymodel', use_gpu=False):
place = fluid.CUDAPlace(0) if use_gpu else fluid.CPUPlace()
with fluid.dygraph.guard(place):
model = MyNet()
model_state_dict, _ = fluid.load_dygraph(
os.path.join(MODEL_PATH, model_name))
model.load_dict(model_state_dict)
model.eval()
eval_loader = load_data(data_path, mode='eval')
avg_acc_set = []
avg_loss_set = []
for _, data in enumerate(eval_loader()):
x_data, y_data = data
img = fluid.dygraph.to_variable(x_data)
label = fluid.dygraph.to_variable(y_data)
predict, avg_acc = model(img, label)
loss = fluid.layers.cross_entropy(input=predict, label=label)
avg_loss = fluid.layers.mean(loss)
avg_acc_set.append(float(avg_acc.numpy()))
avg_loss_set.append(float(avg_loss.numpy()))
#计算多个batch的平均损失和准确率
avg_acc_val_mean = np.array(avg_acc_set).mean()
avg_loss_val_mean = np.array(avg_loss_set).mean()
print('loss={}, acc={}'.format(avg_loss_val_mean, avg_acc_val_mean))
def start_test():
'''
测试
'''
# 初始化网络并加载预训练模型
myNet = MyNet().to("cuda:0")
myNet.eval()
with torch.no_grad():
input = input.to("cuda:0")
# 若想推理加速，在精度接受范围内img\model手动half()为FP16，然后只能GPU推理
# input=input.half()
# myNet=myNet.half()
feature = myNet(input)
class Detector:
def __init__(self, net_path, board_size, n):
self.device = "cuda" if torch.cuda.is_available() else "cpu"
self.net = MyNet().to(self.device)
self.net.load_state_dict(torch.load(net_path))
# self.board_size = args.board_size
# self.n = args.number
self.number_playout = args.n_playout
self.env = GameState(board_size, n)
self.net.eval()
self.mcts_player = Player(policy=self.policy,
number_playout=1000,
is_self_play=False,
print_detail=True)
def policy(self, env):
# 获取可用动作 15*15=225
action_avail = env.action_avail
# 获得当前状态
state = torch.from_numpy(env.get_state).unsqueeze(0).to(self.device)
# 放入神经网络得到预测的log动作概率以及当前状态的胜率
log_action_probs, value = self.net(state)
# 把 log 动作概率转换为动作概率并过滤不可用动作
act_probs = torch.exp(
log_action_probs).detach().cpu().numpy().flatten()
act_probs = zip(action_avail, act_probs[action_avail])
value = value.item()
# 返回动作概率，当前局面价值
return act_probs, value
def detect(self):
while True:
action = None
# 当玩家切换到人机以及游戏未结束时，人机使用MCTS算法得到最优动作
if self.env.current_player == 1 and not self.env.pause:
action = self.mcts_player.get_action(self.env.game)
self.env.step(action)
