def __init__(self, game_config, device):
self.training = False
self.game_config = game_config
self.is_e2e = game_config['rl-train']['e2e']
self.doc_threshold = game_config['global']['guess_thre']
self.force_guess = game_config['global']['force_guess']
self.max_turns = game_config['global']['max_turns']
# initial config
self.turn_i = 1
self.act_his = []
self.cand_docs = None
self.cand_names = []
self.dialog_level_doc_dist = None
self.dialog_level_act_dist = None
# device
self.enable_cuda = torch.cuda.is_available()
self.device = device
# state module
self.state_module = self.get_state_module().to(self.device)
# policy module
self.policy_module = self.get_policy_module().to(self.device)
self.load_parameters()
logger.info('Filter-Module Params=%d' % count_parameters(self.state_module))
logger.info('Diff-Module Params=%d' % count_parameters(self.policy_module))
# optimizer
self.optimizer = None
# NLG with template
template_path = game_config['dataset']['agent_template_path']
self.nl_template = NLTemplate(template_path)
def __init__(self, config_file="/mnt/sdb/cjm/Match-LSTM/config/id19.yaml"):
logger.info('------------MODEL TEST INPUT--------------')
logger.info('loading config file...')
#self.global_config = read_config("config/id19.yaml")
self.global_config = read_config(config_file)
# set random seed
seed = self.global_config['global']['random_seed']
torch.manual_seed(seed)
torch.set_grad_enabled(
False) # make sure all tensors below have require_grad=False
# set default gpu
os.environ["CUDA_VISIBLE_DEVICES"] = str(
self.global_config['test']["gpu_id"])
enable_cuda = self.global_config['test']['enable_cuda']
self.device = torch.device("cuda" if enable_cuda else "cpu")
if torch.cuda.is_available() and not enable_cuda:
logger.warning(
"CUDA is avaliable, you can enable CUDA in config file")
elif not torch.cuda.is_available() and enable_cuda:
raise ValueError(
"CUDA is not abaliable, please unable CUDA in config file")
logger.info('reading squad dataset...')
self.dataset = SquadDataset(self.global_config)
logger.info('constructing model...')
model_choose = self.global_config['global']['model']
dataset_h5_path = self.global_config['data']['dataset_h5']
if model_choose == 'base':
model = BaseModel(
dataset_h5_path,
model_config=read_config('config/base_model.yaml'))
elif model_choose == 'match-lstm':
model = MatchLSTM(dataset_h5_path)
elif model_choose == 'match-lstm+':
model = MatchLSTMPlus(
dataset_h5_path,
self.global_config['preprocess']['use_domain_tag'])
elif model_choose == 'r-net':
model = RNet(dataset_h5_path)
elif model_choose == 'm-reader':
model = MReader(dataset_h5_path)
else:
raise ValueError('model "%s" in config file not recoginized' %
model_choose)
model = model.to(self.device)
model.eval() # let training = False, make sure right dropout
logging.info('model parameters count: %d' % count_parameters(model))
# load model weight
logger.info('loading model weight...')
model_weight_path = self.global_config['data']['model_path']
is_exist_model_weight = os.path.exists(model_weight_path)
assert is_exist_model_weight, "not found model weight file on '%s'" % model_weight_path
weight = torch.load(model_weight_path,
map_location=lambda storage, loc: storage)
if enable_cuda:
weight = torch.load(
model_weight_path,
map_location=lambda storage, loc: storage.cuda())
model.load_state_dict(weight, strict=False)
self.model = model
self.nlp = spacy.load('en')
self.metadata = {
k: v.tolist()
for k, v in self.dataset.meta_data.items()
}
def main():
logger.info('------------MODEL TEST INPUT--------------')
logger.info('loading config file...')
global_config = read_config()
# set random seed
seed = global_config['global']['random_seed']
torch.manual_seed(seed)
torch.set_grad_enabled(False) # make sure all tensors below have require_grad=False
logger.info('reading squad dataset...')
dataset = SquadDataset(global_config)
logger.info('constructing model...')
model_choose = global_config['global']['model']
dataset_h5_path = global_config['data']['dataset_h5']
if model_choose == 'base':
model = BaseModel(dataset_h5_path,
model_config=read_config('config/base_model.yaml'))
elif model_choose == 'match-lstm':
model = MatchLSTM(dataset_h5_path)
elif model_choose == 'match-lstm+':
model = MatchLSTMPlus(dataset_h5_path)
elif model_choose == 'r-net':
model = RNet(dataset_h5_path)
elif model_choose == 'm-reader':
model = MReader(dataset_h5_path)
else:
raise ValueError('model "%s" in config file not recoginized' % model_choose)
model.eval() # let training = False, make sure right dropout
logging.info('model parameters count: %d' % count_parameters(model))
# load model weight
logger.info('loading model weight...')
model_weight_path = global_config['data']['model_path']
is_exist_model_weight = os.path.exists(model_weight_path)
assert is_exist_model_weight, "not found model weight file on '%s'" % model_weight_path
weight = torch.load(model_weight_path, map_location=lambda storage, loc: storage)
model.load_state_dict(weight, strict=False)
# manual input qa
context = "In 1870, Tesla moved to Karlovac, to attend school at the Higher Real Gymnasium, where he was " \
"profoundly influenced by a math teacher Martin Sekuli\u0107.:32 The classes were held in German, " \
"as it was a school within the Austro-Hungarian Military Frontier. Tesla was able to perform integral " \
"calculus in his head, which prompted his teachers to believe that he was cheating. He finished a " \
"four-year term in three years, graduating in 1873.:33 "
question1 = "What language were classes held in at Tesla's school?"
answer1 = ["German"]
question2 = "Who was Tesla influenced by while in school?"
answer2 = ["Martin Sekuli\u0107"]
question3 = "Why did Tesla go to Karlovac?"
answer3 = ["attend school at the Higher Real Gymnasium", 'to attend school']
# change here to select questions
question = question1
answer = answer1[0]
# preprocess
nlp = spacy.load('en')
context_doc = DocText(nlp, context, global_config['preprocess'])
question_doc = DocText(nlp, question, global_config['preprocess'])
context_doc.update_em(question_doc)
question_doc.update_em(context_doc)
context_token = context_doc.token
question_token = question_doc.token
context_id_char = to_long_tensor(dataset.sentence_char2id(context_token))
question_id_char = to_long_tensor(dataset.sentence_char2id(question_token))
context_id, context_f = context_doc.to_id(dataset.meta_data)
question_id, question_f = question_doc.to_id(dataset.meta_data)
bat_input = [context_id, question_id, context_id_char, question_id_char, context_f, question_f]
bat_input = [x.unsqueeze(0) if x is not None else x for x in bat_input]
out_ans_prop, out_ans_range, vis_param = model.forward(*bat_input)
out_ans_range = out_ans_range.numpy()
start = out_ans_range[0][0]
end = out_ans_range[0][1] + 1
out_answer_id = context_id[start:end]
out_answer = dataset.sentence_id2word(out_answer_id)
logging.info('Predict Answer: ' + ' '.join(out_answer))
# to show on visdom
s = 0
e = 48
x_left = vis_param['match']['left']['alpha'][0, :, s:e].numpy()
x_right = vis_param['match']['right']['alpha'][0, :, s:e].numpy()
x_left_gated = vis_param['match']['left']['gated'][0, :, s:e].numpy()
x_right_gated = vis_param['match']['right']['gated'][0, :, s:e].numpy()
draw_heatmap_sea(x_left,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-left.png',
bottom=0.45)
draw_heatmap_sea(x_right,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-right.png',
bottom=0.45)
enable_self_match = False
if enable_self_match:
x_self_left = vis_param['self']['left']['alpha'][0, s:e, s:e].numpy()
x_self_right = vis_param['self']['right']['alpha'][0, s:e, s:e].numpy()
draw_heatmap_sea(x_self_left,
xlabels=context_token[s:e],
ylabels=context_token[s:e],
answer=answer,
save_path='data/test-self-left.png',
inches=(11, 11),
bottom=0.2)
draw_heatmap_sea(x_self_right,
xlabels=context_token[s:e],
ylabels=context_token[s:e],
answer=answer,
save_path='data/test-self-right.png',
inches=(11, 11),
bottom=0.2)
def main():
logger.info('------------MODEL TEST INPUT--------------')
logger.info('loading config file...')
# manual set
global_config = read_config('config/global_config.yaml')
# set random seed
seed = global_config['global']['random_seed']
torch.manual_seed(seed)
torch.set_grad_enabled(
False) # make sure all tensors below have require_grad=False
logger.info('reading dataset...')
dataset = Dataset(global_config)
logger.info('constructing model...')
dataset_h5_path = global_config['data']['dataset_h5']
model = MatchLSTMPlus(dataset_h5_path)
model.eval() # let training = False, make sure right dropout
logging.info('model parameters count: %d' % count_parameters(model))
model_rerank = None
rank_k = global_config['global']['rank_k']
if global_config['global']['enable_rerank']:
model_rerank = ReRanker(dataset_h5_path)
model_rerank.eval()
logging.info('rerank model parameters count: %d' %
count_parameters(model_rerank))
# load model weight
logger.info('loading model weight...')
model_weight_path = global_config['data']['model_path']
is_exist_model_weight = os.path.exists(model_weight_path)
assert is_exist_model_weight, "not found model weight file on '%s'" % model_weight_path
weight = torch.load(model_weight_path,
map_location=lambda storage, loc: storage)
model.load_state_dict(weight, strict=False)
if global_config['global']['enable_rerank']:
rerank_weight_path = global_config['data']['rerank_model_path']
assert os.path.exists(
rerank_weight_path
), "not found rerank model weight file on '%s'" % rerank_weight_path
logger.info('loading rerank model weight...')
weight = torch.load(rerank_weight_path,
map_location=lambda storage, loc: storage)
model_rerank.load_state_dict(weight, strict=False)
context = "《战国无双3》（）是由光荣和ω-force开发的战国无双系列的正统第三续作。本作以三大故事为主轴，分别是以武田信玄等人为主的《关东三国志》，织田信长等人为主的《战国三杰》，石田三成等人为主的《关原的年轻武者》，丰富游戏内的剧情。此部份专门介绍角色，欲知武器情报、奥义字或擅长攻击类型等，请至战国无双系列1.由于乡里大辅先生因故去世，不得不寻找其他声优接手。从猛将传 and Z开始。2.战国无双 编年史的原创男女主角亦有专属声优。此模式是任天堂游戏谜之村雨城改编的新增模式。本作中共有20张战场地图（不含村雨城），后来发行的猛将传再新增3张战场地图。但游戏内战役数量繁多，部分地图会有兼用的状况，战役虚实则是以光荣发行的2本「战国无双3 人物真书」内容为主，以下是相关介绍。（注：前方加☆者为猛将传新增关卡及地图。）合并本篇和猛将传的内容，村雨城模式剔除，战国史模式可直接游玩。主打两大模式「战史演武」&「争霸演武」。系列作品外传作品"
question1 = "《战国无双3》是由哪两个公司合作开发的？"
answer1 = ['光荣和ω-force']
question2 = '男女主角亦有专属声优这一模式是由谁改编的？'
answer2 = ['村雨城', '任天堂游戏谜之村雨城']
question3 = '战国史模式主打哪两个模式？'
answer3 = ['「战史演武」&「争霸演武」']
# change here to select questions
question = question2
answer = answer2[0]
# preprocess
preprocess_config = global_config['preprocess']
context_doc = DocTextCh(context, preprocess_config)
question_doc = DocTextCh(question, preprocess_config)
link_char = ''
# mpl.rcParams['font.sans-serif'] = ['Microsoft YaHei']
mpl.rcParams['font.sans-serif'] = ['SimHei']
context_doc.update_em(question_doc)
question_doc.update_em(context_doc)
context_token = context_doc.token
question_token = question_doc.token
context_id_char = None
question_id_char = None
if preprocess_config['use_char']:
context_id_char = to_long_tensor(
dataset.sentence_char2id(context_token))
question_id_char = to_long_tensor(
dataset.sentence_char2id(question_token))
context_id, context_f = context_doc.to_id(dataset.meta_data)
question_id, question_f = question_doc.to_id(dataset.meta_data)
bat_input = [
context_id, question_id, context_id_char, question_id_char, context_f,
question_f
]
bat_input = [x.unsqueeze(0) if x is not None else x for x in bat_input]
# predict
out_ans_prop, out_ans_range, vis_param = model.forward(*bat_input)
if model_rerank is not None:
cand_ans_range = beam_search(out_ans_prop, k=rank_k)
cand_score, out_ans_range = model_rerank(bat_input[0], bat_input[1],
cand_ans_range)
out_ans_range = out_ans_range.numpy()
start = out_ans_range[0][0]
end = out_ans_range[0][1] + 1
out_answer_id = context_id[start:end]
out_answer = dataset.sentence_id2word(out_answer_id)
logging.info('Predict Answer: ' + link_char.join(out_answer))
# to show on visdom
s = 0
e = 48
x_left = vis_param['match']['left']['alpha'][0, :, s:e].numpy()
x_right = vis_param['match']['right']['alpha'][0, :, s:e].numpy()
x_left_gated = vis_param['match']['left']['gated'][0, :, s:e].numpy()
x_right_gated = vis_param['match']['right']['gated'][0, :, s:e].numpy()
draw_heatmap_sea(x_left,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-left.png',
bottom=0.2)
draw_heatmap_sea(x_right,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-right.png',
bottom=0.2)
def main():
logger.info('------------MODEL TEST INPUT--------------')
logger.info('loading config file...')
global_config = read_config()
# set random seed
seed = global_config['global']['random_seed']
torch.manual_seed(seed)
torch.set_grad_enabled(
False) # make sure all tensors below have require_grad=False
logger.info('reading squad dataset...')
dataset = SquadDataset(global_config)
logger.info('constructing model...')
model_choose = global_config['global']['model']
dataset_h5_path = global_config['data']['dataset_h5']
if model_choose == 'base':
model = BaseModel(dataset_h5_path,
model_config=read_config('config/base_model.yaml'))
elif model_choose == 'match-lstm':
model = MatchLSTM(dataset_h5_path)
elif model_choose == 'match-lstm+':
model = MatchLSTMPlus(dataset_h5_path)
elif model_choose == 'r-net':
model = RNet(dataset_h5_path)
elif model_choose == 'm-reader':
model = MReader(dataset_h5_path)
else:
raise ValueError('model "%s" in config file not recoginized' %
model_choose)
model.eval() # let training = False, make sure right dropout
logging.info('model parameters count: %d' % count_parameters(model))
# load model weight
logger.info('loading model weight...')
model_weight_path = global_config['data']['model_path']
is_exist_model_weight = os.path.exists(model_weight_path)
assert is_exist_model_weight, "not found model weight file on '%s'" % model_weight_path
weight = torch.load(model_weight_path,
map_location=lambda storage, loc: storage)
model.load_state_dict(weight, strict=False)
# manual input qa
context = "In 1870, Tesla moved to Karlovac, to attend school at the Higher Real Gymnasium, where he was " \
"profoundly influenced by a math teacher Martin Sekuli\u0107.:32 The classes were held in German, " \
"as it was a school within the Austro-Hungarian Military Frontier. Tesla was able to perform integral " \
"calculus in his head, which prompted his teachers to believe that he was cheating. He finished a " \
"four-year term in three years, graduating in 1873.:33 "
question1 = "What language were classes held in at Tesla's school?"
answer1 = ["German"]
question2 = "Who was Tesla influenced by while in school?"
answer2 = ["Martin Sekuli\u0107"]
question3 = "Why did Tesla go to Karlovac?"
answer3 = [
"attend school at the Higher Real Gymnasium", 'to attend school'
]
# change here to select questions
question = question1
answer = answer1[0]
# preprocess
nlp = spacy.load('en')
context_doc = DocText(nlp, context, global_config['preprocess'])
question_doc = DocText(nlp, question, global_config['preprocess'])
context_doc.update_em(question_doc)
question_doc.update_em(context_doc)
context_token = context_doc.token
question_token = question_doc.token
context_id_char = to_long_tensor(dataset.sentence_char2id(context_token))
question_id_char = to_long_tensor(dataset.sentence_char2id(question_token))
context_id, context_f = context_doc.to_id(dataset.meta_data)
question_id, question_f = question_doc.to_id(dataset.meta_data)
bat_input = [
context_id, question_id, context_id_char, question_id_char, context_f,
question_f
]
bat_input = [x.unsqueeze(0) if x is not None else x for x in bat_input]
out_ans_prop, out_ans_range, vis_param = model.forward(*bat_input)
out_ans_range = out_ans_range.numpy()
start = out_ans_range[0][0]
end = out_ans_range[0][1] + 1
out_answer_id = context_id[start:end]
out_answer = dataset.sentence_id2word(out_answer_id)
logging.info('Predict Answer: ' + ' '.join(out_answer))
# to show on visdom
s = 0
e = 48
x_left = vis_param['match']['left']['alpha'][0, :, s:e].numpy()
x_right = vis_param['match']['right']['alpha'][0, :, s:e].numpy()
x_left_gated = vis_param['match']['left']['gated'][0, :, s:e].numpy()
x_right_gated = vis_param['match']['right']['gated'][0, :, s:e].numpy()
draw_heatmap_sea(x_left,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-left.png',
bottom=0.45)
draw_heatmap_sea(x_right,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-right.png',
bottom=0.45)
enable_self_match = False
if enable_self_match:
x_self_left = vis_param['self']['left']['alpha'][0, s:e, s:e].numpy()
x_self_right = vis_param['self']['right']['alpha'][0, s:e, s:e].numpy()
draw_heatmap_sea(x_self_left,
xlabels=context_token[s:e],
ylabels=context_token[s:e],
answer=answer,
save_path='data/test-self-left.png',
inches=(11, 11),
bottom=0.2)
draw_heatmap_sea(x_self_right,
xlabels=context_token[s:e],
ylabels=context_token[s:e],
answer=answer,
save_path='data/test-self-right.png',
inches=(11, 11),
bottom=0.2)
def main():
logger.info('------------Match-LSTM TEST INPUT--------------')
logger.info('loading config file...')
global_config = read_config()
# set random seed
seed = global_config['model']['global']['random_seed']
torch.manual_seed(seed)
torch.no_grad() # make sure all tensors below have require_grad=False
logger.info('reading squad dataset...')
dataset = SquadDataset(global_config)
logger.info('constructing model...')
model = MatchLSTMModel(global_config)
model.eval() # let training = False, make sure right dropout
logging.info('model parameters count: %d' % count_parameters(model))
# load model weight
logger.info('loading model weight...')
model_weight_path = global_config['data']['model_path']
is_exist_model_weight = os.path.exists(model_weight_path)
assert is_exist_model_weight, "not found model weight file on '%s'" % model_weight_path
weight = torch.load(model_weight_path,
map_location=lambda storage, loc: storage)
model.load_state_dict(weight, strict=False)
# manual input qa
context = "In 1870, Tesla moved to Karlovac, to attend school at the Higher Real Gymnasium, where he was " \
"profoundly influenced by a math teacher Martin Sekuli\u0107.:32 The classes were held in German, " \
"as it was a school within the Austro-Hungarian Military Frontier. Tesla was able to perform integral " \
"calculus in his head, which prompted his teachers to believe that he was cheating. He finished a " \
"four-year term in three years, graduating in 1873.:33 "
question1 = "What language were classes held in at Tesla's school?"
answer1 = ["German"]
question2 = "Who was Tesla influenced by while in school?"
answer2 = ["Martin Sekuli\u0107"]
question3 = "Why did Tesla go to Karlovac?"
answer3 = [
"attend school at the Higher Real Gymnasium", 'to attend school'
]
# change here to select questions
question = question1
answer = answer1[0]
# preprocess
context_token = nltk.word_tokenize(context)
question_token = nltk.word_tokenize(question)
a = np.array(context_token)
context_id = dataset.sentence_word2id(context_token)
question_id = dataset.sentence_word2id(question_token)
context_id_char = dataset.sentence_char2id(context_token)
question_id_char = dataset.sentence_char2id(question_token)
context_var, question_var, context_var_char, question_var_char = [
to_long_tensor(x).unsqueeze(0)
for x in [context_id, question_id, context_id_char, question_id_char]
]
out_ans_prop, out_ans_range, vis_param = model.forward(
context_var, question_var, context_var_char, question_var_char)
out_ans_range = out_ans_range.cpu().data.numpy()
start = out_ans_range[0][0]
end = out_ans_range[0][1] + 1
out_answer_id = context_id[start:end]
out_answer = dataset.sentence_id2word(out_answer_id)
logging.info('Predict Answer: ' + ' '.join(out_answer))
# to show on visdom
s = 0
e = 48
x_left = vis_param['match']['left'][0, :, s:e].cpu().data.numpy()
x_right = vis_param['match']['right'][0, :, s:e].cpu().data.numpy()
draw_heatmap_sea(x_left,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-left.png',
bottom=0.45)
draw_heatmap_sea(x_right,
xlabels=context_token[s:e],
ylabels=question_token,
answer=answer,
save_path='data/test-right.png',
bottom=0.45)
if global_config['model']['interaction']['enable_self_match']:
x_self_left = vis_param['self']['left'][0, s:e, s:e].cpu().data.numpy()
x_self_right = vis_param['self']['right'][0, s:e,
s:e].cpu().data.numpy()
draw_heatmap_sea(x_self_left,
xlabels=context_token[s:e],
ylabels=context_token[s:e],
answer=answer,
save_path='data/test-self-left.png',
inches=(11, 11),
bottom=0.2)
draw_heatmap_sea(x_self_right,
xlabels=context_token[s:e],
ylabels=context_token[s:e],
answer=answer,
save_path='data/test-self-right.png',
inches=(11, 11),
bottom=0.2)
'loss'] == 'wgan' and discriminator_loss_hyperparams == 'wgan'
# Initialize generator, discriminator and RoI generator
generator = Generator(**config.gen_hyperparams)
discriminator = Discriminator(dis_n_features, is_wgan, noise_hyperparams)
roi = RoI(image_size, locals()[roi_function], len(train_data))
roi_loader = DataLoader(roi,
batch_size=batch_size,
shuffle=False,
num_workers=5)
from utils.functions import count_parameters
if print_summary:
print('Generator:')
count_parameters(generator)
#summary(generator, [(gen_n_input, 1, 1), (1, 64, 64)], device='cpu')
print('Discriminator')
count_parameters(discriminator)
#summary(discriminator, (3, 64, 64), device='cpu')
# Initialize weights
if chkpname_dis == None and chkpname_gen == None:
generator.apply(weights_init)
discriminator.apply(weights_init)
# Optimizers
optimizer_G = torch.optim.Adam([{
'params': generator.parameters()
}, {
'params': discriminator.q_net.parameters()