tensorflow: version 1.2 doesn't show CUDA and cuDNN information

System information

• Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
• OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 16.04
• TensorFlow installed from (source or binary): pip install tensorflow-gpu
• TensorFlow version (use command below): (‘v1.2.0-rc2-21-g12f033d’, ‘1.2.0’)
• CUDA/cuDNN version: CUDA 8.0, cuDNN 5.1
• GPU model and memory: GTX 970M, 3GB

Describe the problem

In previous version, after importing tensorflow like import tensorflow as tf following output will be shown:

>>> import tensorflow as tf;
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcublas.so.7.5 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcudnn.so.5.1 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcufft.so.7.5 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:111] successfully opened CUDA library libcurand.so.7.5 locally

However, after I installed CUDA and cuDNN, and then installed Tensorflow v1.2, I found there is NO output for import tensorflow as tf in python. And I cannot check whether gpu successfully uses CUDA or cuDNN. I have checked my GPU as follows and GPU works well. I have tried the method in #566 to adjust TF_CPP_MIN_LOG_LEVEL, but it seems have no effect. I suggest it would be great to include CUDA and cuDNN info when importing tensorflow.

>>> import tensorflow as tf
>>> sess = tf.Session()
2017-06-20 00:24:38.111017: 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.
2017-06-20 00:24:38.111060: 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.
2017-06-20 00:24:38.111074: 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.
2017-06-20 00:24:38.111086: 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.
2017-06-20 00:24:38.111097: 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.
2017-06-20 00:24:38.215890: 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
2017-06-20 00:24:38.216159: I tensorflow/core/common_runtime/gpu/gpu_device.cc:940] Found device 0 with properties: 
name: GeForce GTX 970M
major: 5 minor: 2 memoryClockRate (GHz) 1.038
pciBusID 0000:01:00.0
Total memory: 2.95GiB
Free memory: 2.63GiB
2017-06-20 00:24:38.216174: I tensorflow/core/common_runtime/gpu/gpu_device.cc:961] DMA: 0 
2017-06-20 00:24:38.216180: I tensorflow/core/common_runtime/gpu/gpu_device.cc:971] 0:   Y 
2017-06-20 00:24:38.216191: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1030] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GeForce GTX 970M, pci bus id: 0000:01:00.0)