GPU device not being recognized

I have a Nvidia Quadro K1200 GPU installed in my system. I want to use tensorflow-gpu on it. I have tried every single bit that I could do for it to get recognized in deviceQuery or in device_lib.list_local_devices() in tensorflow but still no success. I have installed the follwing on my system:-

  1. Quadro Desktop/Quadro Notebook Driver Release 390 which was autodetected on Nvidia website for my gpu
  2. Visual Studio 2015 for compiling the binaries
  3. CUDA toolkit 9.0 edition Full installaation
  4. Compiled the solution for deviceQuery still it shows Fail, no CUDA devices detected on running its exe(After restart too).
  5. Downloaded cuDNN v7.1.4 Library for Windows 10 and put the extracted files in their respective folders.

Still I got no success. My GPU isn’t being listed.

Here are my nvidia-smi stats too

C:\Users\neela>nvidia-smi
Thu Jun 28 04:54:55 2018
±----------------------------------------------------------------------------+
| NVIDIA-SMI 391.33 Driver Version: 391.33 |
|-------------------------------±---------------------±---------------------+
| GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 Quadro K1200 WDDM | 00000000:02:00.0 On | N/A |
| 39% 42C P8 1W / 35W | 505MiB / 4096MiB | 4% Default |
±------------------------------±---------------------±---------------------+

±----------------------------------------------------------------------------+
| Processes: GPU Memory |
| GPU PID Type Process name Usage |
|=============================================================================|
| 0 1192 C+G Insufficient Permissions N/A |
| 0 2736 C+G …t_cw5n1h2txyewy\ShellExperienceHost.exe N/A |
| 0 3136 C+G C:\Windows\explorer.exe N/A |
| 0 7284 C+G …osoft.LockApp_cw5n1h2txyewy\LockApp.exe N/A |
| 0 8808 C+G …es (x86)\Internet Explorer\iexplore.exe N/A |
| 0 9008 C+G Insufficient Permissions N/A |
| 0 11276 C+G …dows.Cortana_cw5n1h2txyewy\SearchUI.exe N/A |
| 0 11756 C+G …2.0_x64__8wekyb3d8bbwe\WinStore.App.exe N/A |
| 0 12532 C+G …oftEdge_8wekyb3d8bbwe\MicrosoftEdge.exe N/A |
| 0 15836 C+G …6)\Google\Chrome\Application\chrome.exe N/A |
±----------------------------------------------------------------------------+

PLEASE HELP

Check that you have not disabled the GPU for CUDA use with the environment variable CUDA_VISIBLE_DEVICES.

According to both NVIDIA’s official list of supported GPUs and Wikipedia, the Quadro K1200 is a device with compute capability 5.0 and therefore definitely be supported by current versions of CUDA. This compute capability should also satisfy Tensorflow’s hardware requirements.

In my environment variables, there is no variable named CUDA_VISIBLE_DEVICES