Error:
RuntimeError: CUDA out of memory.Tried to allocate 48.00 MiB (GPU 0; 2.00 GiB total capacity; 1001.96 MiB already allocated; 36.14 MiB free; 1.12 GiB reserved in total by PyTorch)

Solution:

C:\Users\hp>nvidia-smi
'nvidia-smi' is not an internal or external command, nor a runnable program
or batch file.

C:\Users\hp>cd C:\Program Files\NVIDIA Corporation\NVSMI

C:\Program Files\NVIDIA Corporation\NVSMI>nvidia-smi
Sun Oct 24 19:31:25 2021
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 462.80       Driver Version: 462.80       CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name            TCC/WDDM | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  GeForce GTX 1050   WDDM  | 00000000:01:00.0 Off |                  N/A |
| N/A   42C    P8    N/A/ N/A |     70MiB/ 2048MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A      4248    C+G   ...bbwe\Microsoft.Photos.exe    N/A      |
+-----------------------------------------------------------------------------+

C:\Program Files\NVIDIA Corporation\NVSMI>taskkill -PID 4248 -F
成功: 已终止 PID 为 4248 的进程。

C:\Program Files\NVIDIA Corporation\NVSMI>nvidia-smi
Sun Oct 24 19:38:39 2021
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 462.80       Driver Version: 462.80       CUDA Version: 11.2     |
|-------------------------------+----------------------+----------------------+
| GPU  Name            TCC/WDDM | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  GeForce GTX 1050   WDDM  | 00000000:01:00.0 Off |                  N/A |
| N/A   40C    P8    N/A/ N/A |     70MiB/ 2048MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

C:\Program Files\NVIDIA Corporation\NVSMI>

Read More:

• [Solved] RuntimeError: CUDA error: out of memory
• Node Memory Overflow: FATAL ERROR: Reached heap limit Allocation failed – JavaScript heap out of memory
• TensorRT model quantization error: Error Code 1: Cuda Runtime (an illegal memory access was encountered)
• RuntimeError: implement_array_function method already has a docstring(Pycharm install package error)
• [Solved] RuntimeError: CUDA error: invalid device ordinal
• [Solved] Runtimeerror: CUDA error: device side assert triggered
• How to Solve Git error: out of memory
• Solve Error: call_and_retry_last allocation failed – javascript heap out of memory
• [Solved] RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)`
• [Solved] CUDA error：-UserWarning: CUDA initialization: CUDA unknown error
• [Solved] NPM run build package error: Ineffective mark-compacts near heap limit Allocation failed – JavaScript heap out of memory
• [Solved] torch Do Targer Detection Error: RuntimeError: CUDA error: device-side assert triggered
• [Solved] Build Error Ineffective mark-compacts near heap limit Allocation failed – JavaScript heap out of memory
• Cuda Runtime error (38) : no CUDA-capable device is detected
• [Solved] UserWarning: CUDA initialization: CUDA unknown error
• TensorFlow-gpu Error: failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected
• CUDA_ERROR_SYSTEM_DRIVER_MISMATCH [How to Solve]
• [Solved] matlab Error: CUDA_ERROR_SYSTEM_NOT_READY
• Error 1 error MSB3721: Command ““C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v9.0\bin\nvcc.exe” -genco
• How to Solve Pycharm SQL Union Error