def test_matchzoo():
params = Params()
config_file = 'config/qalocal.ini' # define dataset in the config
params.parse_config(config_file)
params.network_type = "anmm.ANMM"
reader = qa.setup(params)
qdnn = models.setup(params)
model = qdnn.getModel()
model.compile(loss = params.loss,
optimizer = units.getOptimizer(name=params.optimizer,lr=params.lr),
metrics=['accuracy'])
model.summary()
# generators = [reader.getTrain(iterable=False) for i in range(params.epochs)]
# q,a,score = reader.getPointWiseSamples()
# model.fit(x = [q,a],y = score,epochs = 1,batch_size =params.batch_size)
def gen():
while True:
for sample in reader.getPointWiseSamples(iterable = True):
yield sample
model.fit_generator(gen(),epochs = 2,steps_per_epoch=1000)
from tools.timer import log_time_delta
import datetime
from params import Params
from dataset import qa
from models.match import tensorflow as models
from tools import evaluation
from dataset.qa import QAHelper as helper
from tools import Logger
logger = Logger()
params = Params()
config_file = 'config/qa.ini' # define dataset in the config
params.parse_config(config_file)
reader = qa.setup(params)
#params = qa.process_embedding(reader,params)
@log_time_delta
def predict(model, sess, batch, test):
scores = []
for data in batch:
score = model.predict(sess, data)
scores.extend(score)
return np.array(scores[:len(test)])
best_p1 = 0
with tf.Graph().as_default(): # ,tf.device("/cpu:" + str(params.gpu))
# with tf.device("/cpu:0"):
