def main():
cuda = torch.cuda.is_available()
if cuda:
print('Device: {}'.format(torch.cuda.get_device_name(0)))
json_params_file = sys.argv[1]
with open(json_params_file, "r") as json_file:
params = json.load(json_file)
print(params)
if HYPERPARAM_MODE == params['mode']:
hyperparam_log_file = open('cnn_hyperparam_optimization.txt', 'w')
hyperparam_log_file.write(
'batch_size,dims,lr,best_epoch,best_f1,last_f1\n')
best_model_params = None
best_model_f1 = -1
base_params = params.copy()
del base_params['mode']
param_grid = ParameterGrid(base_params)
for search_params in param_grid:
print('Fitting model with params:', search_params)
siamese_model = CNNModel(search_params, cuda)
siamese_model.fit()
hyperparam_log_file.write('{},{},{},{},{},{}\n'.format(
search_params['batch_size'], search_params['dims'],
search_params['lr'], siamese_model.best_epoch,
siamese_model.best_f1, siamese_model.current_f1))
if siamese_model.best_f1 > best_model_f1:
best_model_f1 = siamese_model.best_f1
best_model_params = search_params
print('Best model params! F1:{}'.format(best_model_f1),
best_model_params)
hyperparam_log_file.close()
elif params['mode'] == 'EVAL_MODE':
siamese_model = CNNModel(params, cuda)
siamese_model.eval()
else:
siamese_model = CNNModel(params, cuda)
siamese_model.fit()
loss = loss_func(logits, labels)
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_loss += loss.data.item()
print("\tEpoch %d, total loss: %f" % (epoch, total_loss))
train_finish_time = time.time()
train_overall_time = train_finish_time - start_time
# Evaluate
print("Evaluating ...")
model.eval()
predicts = []
golds = []
with torch.no_grad():
for idx, batch in enumerate(tqdm(test_iter, desc="Iteration")):
inputs, labels = batch.sent, batch.label
inputs = inputs.to(device)
logits = model(inputs)
predict = torch.argmax(logits, dim=1).data.cpu().numpy()
predicts += list(predict)
golds += list(labels.data.cpu().numpy())
precision, recall, f1 = F1(predicts, golds)
print("Precision: %f, Recall: %f, F1: %f" % (precision, recall, f1))