def showmatch(model_paths, task, randomize, hardness, num_envs, symmetric,
random_rules):
if torch.cuda.is_available():
device = torch.device("cuda:0")
else:
print("Running on CPU")
device = "cpu"
if len(model_paths) == 1:
opponents = None
elif len(model_paths) == 2:
opponents = {'player2': {'model_file': model_paths[1]}}
else:
raise Exception("Invalid args")
objective = envs.Objective(task)
policy1, _, _, _, _ = load_policy(model_paths[0], device)
eval(
policy=policy1,
num_envs=num_envs,
device=device,
objective=objective,
eval_steps=int(1e20),
opponents=opponents,
printerval=500,
randomize=randomize,
hardness=hardness,
symmetric=symmetric,
random_rules=random_rules,
)
def FUNCTION(*arg):
#ここで束縛されるargは実引数となる
#dmyargは"(x , y , z)"みたいな仮引数
if dmyarg == "nil":
lst = [pr.eval(each , scope) for each in body]
else:
s = pr.joindict({e:arg[i]for i,e in enumerate(pr.tokenize(dmyarg))},scope)
lst = [pr.eval(each , s) for each in body]
return lst.pop()
def FUNCTION(*arg):
#ここで束縛されるargは実引数となる
#dmyargは"(x , y , z)"みたいな仮引数
if dmyarg == "nil":
lst = [pr.eval(each, scope) for each in body]
else:
s = pr.joindict(
{e: arg[i]
for i, e in enumerate(pr.tokenize(dmyarg))}, scope)
lst = [pr.eval(each, s) for each in body]
return lst.pop()
def defconst(symbol , value , scope):
if not pr.issymbol(symbol):raise pr.Error(const.ERROR["NOT_SYMBL"]%(symbol))
if symbol in const.GLOBAL_VALUE:return const.GLOBAL_VALUE[symbol]
val = pr.eval(value,scope)
const.GLOBAL_VALUE[symbol] = val
return val
def defconst(symbol, value, scope):
if not pr.issymbol(symbol):
raise pr.Error(const.ERROR["NOT_SYMBL"] % (symbol))
if symbol in const.GLOBAL_VALUE: return const.GLOBAL_VALUE[symbol]
val = pr.eval(value, scope)
const.GLOBAL_VALUE[symbol] = val
return val
tokenizer = BertTokenizer.from_pretrained(args.load_pretrained_model_path)
model = Bert_TCN(args).cuda()
print(get_parameter_number(model))
if args.model_path:
model = load_model(model)
print("successfully load pre-trained model")
else:
print("no pre-trained model")
exit(0)
print("===loading test data==")
test_dataset = WeiboDataset(args.data_path, file_type='test_simplified')
test_batches = DataLoader(dataset=test_dataset,
batch_size=args.batch_size,
shuffle=False,
collate_fn=collate_fn)
print("test:length={},batch_num={}".format(test_dataset.__len__(),
len(test_batches)))
optimizer = getattr(optim, args.optim)
optimizer = optimizer(model.parameters(),
lr=args.lr,
weight_decay=args.weight_decay)
print('begin test evaluation')
test_loss, test_scores, test_predicts = eval(args, model, tokenizer,
test_batches)
write_test_predictions(test_batches, test_predicts)
model = RAMNetwork(FLAGS=FLAGS, full_summary=False)
with tf.Session() as sess:
model.saver.restore(sess, FLAGS.path + "/cp.ckpt")
start_step = model.global_step.eval(session=sess)
tf.logging.info('Evaluate model at step: %d ', start_step)
train_writer, valid_writer, test_writer, train_handle, valid_handle, test_handle = model.setup(
sess, train_data, valid_data, test_data)
Visual = Visualization(model, FLAGS)
# Test set
eval(model,
sess,
FLAGS,
valid_handle,
FLAGS.batches_per_eval_valid,
valid_writer,
prefix='VALIDATION - LAST MODEL: ')
eval(model,
sess,
FLAGS,
test_handle,
FLAGS.batches_per_eval_test,
test_writer,
prefix='TEST - LAST MODEL: ')
Visual(sess, 'test_set', test_handle)
model.saver.restore(sess, FLAGS.path + "/cp_best.ckpt")
eval(model,
sess,
def eval(*arg):
return pr.eval(arg[0] , arg[1])
"cons" :(True , (lambda x,y: apply(makelist,[x] + pr.tokenize(y))) , False),
"car" :(True , (lambda x:pr.tokenize(x)[0]) , False),
"cdr" :(True , (lambda x:apply(makelist ,pr.tokenize(x)[1:])) , False),
"list" :(True , makelist , False),
"last" :(True , last , False),
"length" :(True , (lambda x: len(pr.tokenize(x))) , False),
"init" :(True , init , False),
"map" :(True , map_ , False),
"filter" :(True , filter_ , False),
"list?" :(True , (lambda x:pr.booltolisp(pr.W_islist(x))) , False),
"atom?" :(True , (lambda x:pr.booltolisp(pr.W_isatom(x))) , False),
"symbol?" :(True , (lambda x:pr.booltolisp(pr.W_issymbol(x))) , False),
"null?" :(True , (lambda x:pr.booltolisp(pr.W_isnil(x))) , False),
"equal?" :(True , (lambda x,y: pr.booltolisp(x == y)) , False),
"print" :(True , (lambda x: show(x)) , False),
"define" :(False , define , False),
"defconst":(False , defconst , False),
"lambda" :(False , lmd , False),
"if" :(False , (lambda c,x,y,s: pr.eval(x,s) if pr.booltopy(pr.eval(c,s)) else pr.eval(y,s)) , False),
"eval" :(True , eval ,True),
"exit" :(True , fin , False)
}
def eval(*arg):
return pr.eval(arg[0], arg[1])
"and" :(True , (lambda x,y: pr.booltolisp(pr.booltopy(x) and pr.booltopy(y))) , False),
"or" :(True , (lambda x,y: pr.booltolisp(pr.booltopy(x) or pr.booltopy(y))) , False),
"not" :(True , (lambda x: pr.booltolisp(not pr.booltopy(x)) ) , False),
"cons" :(True , (lambda x,y: apply(makelist,[x] + pr.tokenize(y))) , False),
"car" :(True , (lambda x:pr.tokenize(x)[0]) , False),
"cdr" :(True , (lambda x:apply(makelist ,pr.tokenize(x)[1:])) , False),
"list" :(True , makelist , False),
"last" :(True , last , False),
"length" :(True , (lambda x: len(pr.tokenize(x))) , False),
"init" :(True , init , False),
"map" :(True , map_ , False),
"filter" :(True , filter_ , False),
"list?" :(True , (lambda x:pr.booltolisp(pr.W_islist(x))) , False),
"atom?" :(True , (lambda x:pr.booltolisp(pr.W_isatom(x))) , False),
"symbol?" :(True , (lambda x:pr.booltolisp(pr.W_issymbol(x))) , False),
"null?" :(True , (lambda x:pr.booltolisp(pr.W_isnil(x))) , False),
"equal?" :(True , (lambda x,y: pr.booltolisp(x == y)) , False),
"print" :(True , (lambda x: show(x)) , False),
"define" :(False , define , False),
"defconst":(False , defconst , False),
"lambda" :(False , lmd , False),
"if" :(False , (lambda c,x,y,s: pr.eval(x,s) if pr.booltopy(pr.eval(c,s)) else pr.eval(y,s)) , False),
"eval" :(True , eval ,True),
"exit" :(True , fin , False)
}