fudannlp16
ValueError: prefix tensor must be either a scalar or vector, but saw tensor: Tensor("Placeholder:0", dtype=int32)
ub16c9@ub16c9-gpu:~/ub16_prj/KeyPhrase-Extraction$ python main.py
len(train_data) 70484
len(valid_data) 7832
len(test_data) 33541
len(vocab) 240058
Train started!
2018-11-14 09:30:16.762768: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2018-11-14 09:30:16.917598: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:898] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
2018-11-14 09:30:16.918011: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1212] Found device 0 with properties:
name: GeForce GTX 1080 Ti major: 6 minor: 1 memoryClockRate(GHz): 1.6575
pciBusID: 0000:01:00.0
totalMemory: 10.92GiB freeMemory: 10.42GiB
2018-11-14 09:30:16.918040: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1312] Adding visible gpu devices: 0
2018-11-14 09:30:17.675964: I tensorflow/core/common_runtime/gpu/gpu_device.cc:993] Creating TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 10081 MB memory) -> physical GPU (device: 0, name: GeForce GTX 1080 Ti, pci bus id: 0000:01:00.0, compute capability: 6.1)
Traceback (most recent call last):
File "main.py", line 186, in
