def test(full_dataset, state_name):
# load model and use weights we saved before.
model = MyModel()
model.load_state_dict(
torch.load(f'mymodel_{state_name}.pth', map_location='cpu'))
model.eval()
criterion = RMSLELoss()
# convert dataframe to tensor
inputs = full_dataset.test[full_dataset.col].astype(float).values
inputs = torch.tensor(inputs).float()
# predict
outputs = model(inputs)
# get labels
labels = full_dataset.test_target.values
# RMSLE Loss
loss = criterion(outputs, torch.from_numpy(labels))
test_loss = sqrt(loss / len(full_dataset.test))
print(f'Testing Loss: {test_loss:.6f}')
#save the result
result = full_dataset.test["id"].to_frame()
result.insert(1, "visitors_pred", outputs.detach().numpy())
result.insert(2, "visitors_actual", labels)
result.to_csv(f'result_{state_name}.csv', index=False)
def test():
# load model and use weights we saved before.
model = MyModel()
model.load_state_dict(torch.load('mymodel.pth', map_location='cpu'))
model.eval()
# load testing data
data = pd.read_csv('test.csv', encoding='utf-8')
label_col = [
'Input_A6_024', 'Input_A3_016', 'Input_C_013', 'Input_A2_016',
'Input_A3_017', 'Input_C_050', 'Input_A6_001', 'Input_C_096',
'Input_A3_018', 'Input_A6_019', 'Input_A1_020', 'Input_A6_011',
'Input_A3_015', 'Input_C_046', 'Input_C_049', 'Input_A2_024',
'Input_C_058', 'Input_C_057', 'Input_A3_013', 'Input_A2_017'
]
# ================================================================ #
# if do some operations with training data,
# do the same operations to the testing data in this block
data = data.fillna(0)
# ================================================================ #
# convert dataframe to tensor, no need to rewrite
inputs = data.values
inputs = torch.tensor(inputs)
# predict and save the result
result = pd.DataFrame(columns=label_col)
outputs = model(inputs.float())
for i in range(len(outputs)):
tmp = outputs[i].detach().numpy()
tmp = pd.DataFrame([tmp], columns=label_col)
result = pd.concat([result, tmp], ignore_index=True)
result.to_csv('result.csv', index=False)
def predict(dim,
names,
weight,
batch_size,
pretrain_model_path,
model_types=None):
print('-' * 100)
print('multi-models begin predicting ...')
print('-' * 100)
# read test data
test_file = '/kaggle/input/quora-question-pairs/test.csv.zip'
# data
test_df = pd.read_csv(test_file)
test_ids = test_df['test_id'].values.tolist()
result_prob_tmp = torch.zeros((len(test_ids), 2))
# load model
for i, name in enumerate(names):
# 3.17 add
weight_ = weight[i]
#model_path = '../model/' + name + '.pkl'
output_model_file = os.path.join('output', name + '.pkl')
state = torch.load(output_model_file)
# 3.10 add
model_type = model_types[i]
if model_type == 'mlp':
test_iter = MyDataset(file=test_file,
is_train=False,
pretrain_model_path=pretrain_model_path[i])
test_iter = get_dataloader(test_iter,
batch_size,
shuffle=False,
drop_last=False)
model = MyModel(dim=dim[i],
pretrain_model_path=pretrain_model_path[i])
elif model_type == 'cnn':
test_iter = MyDataset(file=test_file,
is_train=False,
pretrain_model_path=pretrain_model_path[i])
test_iter = get_dataloader(test_iter,
batch_size,
shuffle=False,
drop_last=False)
model = MyTextCNNModel(dim=dim[i],
pretrain_model_path=pretrain_model_path[i])
elif model_type == 'rcnn':
test_iter = MyDataset(file=test_file,
is_train=False,
pretrain_model_path=pretrain_model_path[i])
test_iter = get_dataloader(test_iter,
batch_size,
shuffle=False,
drop_last=False)
model = MyRCNNModel(dim=dim[i],
pretrain_model_path=pretrain_model_path[i])
model.to(device)
model.load_state_dict(state['model_state'])
model.eval()
print('-' * 20, 'model', i, '-' * 20)
print('load model:%s, loss:%.4f, e:%d, lr:%.7f, time:%d' %
(name, state['loss'], state['e'], state['lr'], state['time']))
# predict
with torch.no_grad():
j = 0
for batch in tqdm(test_iter):
batch = [b.cuda() for b in batch]
out = model(batch, task='eval')
out = out.cpu() # gpu -> cpu
if j == 0:
tmp = out # 初始化 tmp
else:
tmp = torch.cat([tmp, out], dim=0) # 将之后的预测结果拼接到 tmp 中
j += 1
# 当前 模型预测完成
print('model', i, 'predict finished!\n')
# 3.17 按权重融合
result_prob_tmp += (weight_ / len(names)) * tmp
# 删除模型
del model
gc.collect()
time.sleep(1)
# 3.10 当前融合策略：prob 简单的取 avg
_, result = torch.max(result_prob_tmp, dim=-1)
result = result.numpy()
# 3.16 update: label 0的prob 大于 3，就认为是 label=0
# with open('tmp.txt', 'w', encoding='utf-8') as f:
# for r in result_prob_tmp:
# f.write(str(r) + '\n')
# save result
df = pd.DataFrame()
df['test_id'] = test_ids
df['is_duplicate'] = result
df.to_csv("submission.csv", encoding='utf-8', index=False)
