def main():
timer = Timer()
timer.start('Load word2vec models...')
vocab = load_vocab(config.VOCAB_DATA)
embeddings = get_trimmed_w2v_vectors(config.W2V_DATA)
timer.stop()
timer.start('Load data...')
train = process_data(opt.train, vocab)
if opt.val is not None:
if opt.val != '1vs9':
validation = process_data(opt.val, vocab)
else:
validation, train = train.one_vs_nine()
else:
validation = None
if opt.test is not None:
test = process_data(opt.test, vocab)
else:
test = None
timer.stop()
timer.start('Build model...')
model = CnnModel(embeddings=embeddings)
model.build()
timer.stop()
timer.start('Train model...')
epochs = opt.e
batch_size = opt.b
early_stopping = True if opt.p != 0 else False
patience = opt.p
pre_train = opt.pre if opt.pre != '' else None
model_name = opt.name
model.train(
model_name,
train=train,
validation=validation,
epochs=epochs,
batch_size=batch_size,
early_stopping=early_stopping,
patience=patience,
cont=pre_train,
)
timer.stop()
if test is not None:
timer.start('Test model...')
preds = model.predict(test, model_name)
labels = test.labels
p, r, f1, _ = precision_recall_fscore_support(labels,
preds,
average='binary')
print('Testing result:P=\t{}\tR={}\tF1={}'.format(p, r, f1))
timer.stop()
def main():
timer = Timer()
timer.start('Load word2vec models...')
vocab = load_vocab(config.VOCAB_DATA)
embeddings = get_trimmed_w2v_vectors(config.W2V_DATA)
timer.stop()
timer.start('Build model...')
model = CnnModel(embeddings=embeddings)
model.build()
model.restore_session(opt.pre)
timer.stop()
# Define app
app = Flask(__name__)
CORS(app)
@app.route('/process', methods=['POST'])
def process():
data = request.get_json()
try:
words = [[
vocab[w] if w in vocab else vocab['$UNK$']
for w in parse_raw_data(s)
] for s in data['input']]
test = Dataset(words=words)
except:
test = None
abort(400)
job_id = timer.start('Process {} example'.format(len(data['input'])))
y_pred = model.predict(test, opt.pre, pred_class=False)
ret = {'output': [i.tolist() for i in y_pred]}
timer.stop(job_id)
return jsonify(ret)
app.run()