Created by: Yve-Neal

按照这个文档https://github.com/PaddlePaddle/models/tree/develop/legacy/ctr一次运行完： 一： mkdir -p output; python avazu_data_processer.py --data_path train.txt --output_dir output --num_lines_to_detect 1000 --test_set_size 100 二：python train.py --train_data_path ./output/train.txt --test_data_path ./output/test.txt --data_meta_file ./output/data.meta.txt --model_type=0 后报如下错： I0225 20:16:28.711913 15929 Util.cpp:166] commandline: --use_gpu=False --trainer_count=1 INFO:paddle:dnn input dim: 61 INFO:paddle:lr input dim: 10040001 I0225 20:16:28.911039 15929 GradientMachine.cpp:94] Initing parameters.. I0225 20:16:29.801417 15929 GradientMachine.cpp:101] Init parameters done. INFO:paddle:load trainset from ./output/train.txt WARNING:paddle:Pass 0, Samples 0, Cost 0.686135, {} INFO:paddle:load testset from ./output/test.txt Traceback (most recent call last): File "train.py", line 112, in train() File "train.py", line 108, in train num_passes=args.num_passes) File "/home/anaconda2/lib/python2.7/site-packages/paddle/v2/trainer.py", line 206, in train gm=self.gradient_machine)) File "train.py", line 90, in event_handler feeding=reader.feeding_index) File "/home/opt/anaconda2/lib/python2.7/site-packages/paddle/v2/trainer.py", line 247, in test evaluator=evaluator, cost=total_cost / num_samples) ZeroDivisionError: float division by zero