can you details the procedure to reproduce the result? ex how to generate the meta file?

[SeekPoint]

mldl@mldlUB1604:/ub16_prj/neural_qa$ ll
total 121340
drwxrwxr-x 7 mldl mldl 4096 8月 1 00:29 ./
drwxrwxrwx 76 mldl mldl 4096 7月 31 18:52 ../
drwxrwxr-x 8 mldl mldl 4096 7月 16 23:19 .git/
drwxrwxr-x 4 mldl mldl 4096 8月 1 00:13 neural_qa/
-rw-rw-r-- 1 mldl mldl 943 7月 16 23:19 README.md
drwxrwxr-x 3 mldl mldl 4096 7月 16 23:19 src_modified_pl/
-rw-rw-r-- 1 mldl mldl 60746287 8月 1 00:28 v1.0.2.zip
drwxrwxr-x 5 mldl mldl 4096 8月 1 00:24 WikiTableQuestions/
-rw-rw-r-- 1 mldl mldl 34200611 5月 25 19:57 WikiTableQuestions-0.5-compact.zip
drwxrwxr-x 7 mldl mldl 4096 2月 16 09:39 WikiTableQuestions-1.0.2/
-rw-rw-r-- 1 mldl mldl 29267445 8月 1 00:24 WikiTableQuestions-1.0.2-compact.zip
mldl@mldlUB1604:/ub16_prj/neural_qa$

mldl@mldlUB1604:/ub16_prj/neural_qa$ cd neural_qa/
mldl@mldlUB1604:/ub16_prj/neural_qa/neural_qa$ python3 main.py

Parameters:
ALLOW_SOFT_PLACEMENT=True
ARCHITECTURE=5
BATCH_SIZE=100
CHECKPOINT_EVERY=500
DEV_SAMPLE_PERCENTAGE=0.1
DROPOUT_KEEP_PROB=0.8
EMBEDDING_DIM=200
EMBEDDING_DIM_CHAR=30
EVALUATE_EVERY=500
FILTER_SIZES=2,4,6,8
FILTER_SIZES_CHAR=1,2,3
FILTER_SIZES_LAYER_TWO=3,5,7,9
GLOVE=None
IS_TRAINING=False
L2_REG_LAMBDA=0.0
LEARNING_RATE=0.0007
LOG_DEVICE_PLACEMENT=True
LOSS_FUNCTION=maxmargin
MARGIN=2.0
MODEL_PATH=
NUM_EPOCHS=200
NUM_FILTERS=172
NUM_FILTERS_CHAR=64
NUM_FILTERS_LAYER_TWO=64
NUM_NEURONS_FC=500
NUM_NEURONS_FC_2=500
NUM_NEURONS_FC_3=600
RATIO_NEG_POS=1
RATIO_TRAINING_DATA=1
RNN_HIDDEN_SIZE=350
RNN_NUM_LAYERS=1
TARGET_LAMBDA=1.0
TESTING_DATA_PATH=./data/example.tsv
TESTING_FILE=evaluator_input.tsv
TRAINING_DATA_PATH=./data/example.tsv
VALIDATION_DATA_PATH=./data/validation_example.txt
VOCAB_PATH=./vocab
WORD2VEC=None

start initial load
initial load done
Questions to train: NONE
Questions to test 513
Vocabulary Size: 6542
Seq length: 1000
test with
2017-08-01 00:32:58.644080: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 00:32:58.644105: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 00:32:58.644111: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 00:32:58.644116: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 00:32:58.644120: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
2017-08-01 00:32:58.736731: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:893] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2017-08-01 00:32:58.737027: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties:
name: GeForce GTX 950M
major: 5 minor: 0 memoryClockRate (GHz) 1.124
pciBusID 0000:01:00.0
Total memory: 3.95GiB
Free memory: 3.69GiB
2017-08-01 00:32:58.737044: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0
2017-08-01 00:32:58.737049: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0: Y
2017-08-01 00:32:58.737061: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 950M, pci bus id: 0000:01:00.0)
Device mapping:
/job:localhost/replica:0/task:0/gpu:0 -> device: 0, name: GeForce GTX 950M, pci bus id: 0000:01:00.0
2017-08-01 00:32:58.752520: I tensorflow/core/common_runtime/direct_session.cc:265] Device mapping:
/job:localhost/replica:0/task:0/gpu:0 -> device: 0, name: GeForce GTX 950M, pci bus id: 0000:01:00.0

Traceback (most recent call last):
File "main.py", line 745, in
saver = tf.train.import_meta_graph(model_path + ".meta")
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/training/saver.py", line 1679, in import_meta_graph
meta_graph_def = meta_graph.read_meta_graph_file(meta_graph_or_file)
File "/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/meta_graph.py", line 402, in read_meta_graph_file
raise IOError("File %s does not exist." % filename)
OSError: File .meta does not exist.
mldl@mldlUB1604:~/ub16_prj/neural_qa/neural_qa$