def infer():
args = parse_args()
print(args)
if args.use_gpu == 1:
place = fluid.CUDAPlace(0)
else:
place = fluid.CPUPlace()
inference_scope = fluid.Scope()
test_files = [
os.path.join(args.test_data_dir, x)
for x in os.listdir(args.test_data_dir)
]
criteo_dataset = CriteoDataset()
test_reader = paddle.batch(criteo_dataset.test(test_files),
batch_size=args.batch_size)
startup_program = fluid.framework.Program()
test_program = fluid.framework.Program()
cur_model_path = os.path.join(args.model_output_dir,
'epoch_' + args.test_epoch)
with fluid.scope_guard(inference_scope):
with fluid.framework.program_guard(test_program, startup_program):
loss, auc, data_list, auc_states = eval('network_conf.' +
args.model_name)(
args.embedding_size,
args.num_field,
args.num_feat,
args.layer_sizes_dnn,
args.act, args.reg,
args.layer_sizes_cin)
exe = fluid.Executor(place)
feeder = fluid.DataFeeder(feed_list=data_list, place=place)
fluid.io.load_persistables(
executor=exe,
dirname=cur_model_path,
main_program=fluid.default_main_program())
for var in auc_states: # reset auc states
set_zero(var.name, scope=inference_scope, place=place)
loss_all = 0
num_ins = 0
for batch_id, data_test in enumerate(test_reader()):
loss_val, auc_val = exe.run(test_program,
feed=feeder.feed(data_test),
fetch_list=[loss.name, auc.name])
num_ins += len(data_test)
loss_all += loss_val * len(data_test)
logger.info('TEST --> batch: {} loss: {} auc_val: {}'.format(
batch_id + 1, loss_all / num_ins, auc_val))
print(
'The last log info is the total Logloss and AUC for all test data. '
)
def infer():
args = parse_args()
place = fluid.CPUPlace()
inference_scope = fluid.core.Scope()
filelist = [
"%s/%s" % (args.data_path, x) for x in os.listdir(args.data_path)
]
from criteo_reader import CriteoDataset
criteo_dataset = CriteoDataset()
criteo_dataset.setup(args.sparse_feature_dim)
exe = fluid.Executor(place)
train_thread_num = 10
whole_filelist = [
"raw_data/part-%d" % x for x in range(len(os.listdir("raw_data")))
]
test_files = whole_filelist[int(0.8 * len(whole_filelist)
):int(0.85 * len(whole_filelist))]
#file_groups = [whole_filelist[i:i+train_thread_num] for i in range(0, len(whole_filelist), train_thread_num)]
def set_zero(var_name):
param = inference_scope.var(var_name).get_tensor()
param_array = np.zeros(param._get_dims()).astype("int64")
param.set(param_array, place)
epochs = 20
for i in range(epochs):
cur_model_path = args.model_path + "/epoch" + str(i + 1) + ".model"
with fluid.scope_guard(inference_scope):
[inference_program, feed_target_names, fetch_targets] = \
fluid.io.load_inference_model(cur_model_path, exe)
auc_states_names = ['_generated_var_2', '_generated_var_3']
for name in auc_states_names:
set_zero(name)
test_reader = criteo_dataset.infer_reader(test_files, 1000, 100000)
for batch_id, data in enumerate(test_reader()):
loss_val, auc_val = exe.run(inference_program,
feed=data2tensor(data, place),
fetch_list=fetch_targets)
print("train_pass_%d, test_pass_%d\t%f" % (i - 1, i, auc_val))