# OpenCV DNN module is slower on GPU than on CPU (Jetson Nano)

**URL:** <https://forum.opencv.org/t/opencv-dnn-module-is-slower-on-gpu-than-on-cpu-jetson-nano/6386>\
**Category:** Python\
**Tags:** dnn, gpu, cuda, nvidia\
**Created:** [November 23, 2021, 2:41pm UTC](https://forum.opencv.org/t/opencv-dnn-module-is-slower-on-gpu-than-on-cpu-jetson-nano/6386 "2021-11-23T14:41:22Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![trojek](https://avatars.discourse-cdn.com/v4/letter/t/a88e4f/32.png) [@trojek](https://forum.opencv.org/u/trojek)\
**Post date:** [November 23, 2021, 2:41pm UTC](https://forum.opencv.org/t/opencv-dnn-module-is-slower-on-gpu-than-on-cpu-jetson-nano/6386/1 "2021-11-23T14:41:22Z")

</div>

Hi.

I play around with the OpenCV dnn module on both CPU and GPU on Jetson Nano. I make a very similar post on the Nvidia forum [Poor performance of CUDA GPU, using OpenCV DNN module - Jetson Nano - NVIDIA Developer Forums](https://forums.developer.nvidia.com/t/poor-performance-of-cuda-gpu-using-opencv-dnn-module/195897), but I think that the topic is more related to OpenCV than CUDA.

I made some tests using different super-resolution models. The results are as follow:

1. EDSR x2: CPU: timeout, GPU: timeout.
2. ESPCN x4: CPU: 0.17469215393066406 s, GPU: 10.169917821884155 s
3. FSRCNN x4: CPU: 0.12776947021484375 ,GPU: 5.2502007484436035
4. LapSRN x4: CPU: 8.098081111907959, GPU: 6.410776138305664

One can see that CPU time execution is much smaller than on GPU - which is contrary to logic. I check the resources load during the execution of both CPU and GPU versions and in the first case the CPU load was 100%, but with GPU version the load was at about 20%. It looks like dnn module doesn’t use the full power of GPU.

Why is the performance on GPU is too poor to CPU?  
Is there exist a way to decrease the execution time of the GPU version?

---

<div class="post-metadata">

**Author:** ![mshabunin](https://sea2.discourse-cdn.com/flex020/user_avatar/forum.opencv.org/mshabunin/32/15_2.png) [@mshabunin](https://forum.opencv.org/u/mshabunin)\
**Post date:** [November 23, 2021, 9:52pm UTC](https://forum.opencv.org/t/opencv-dnn-module-is-slower-on-gpu-than-on-cpu-jetson-nano/6386/2 "2021-11-23T21:52:38Z")

</div>

GPU initial setup and moving data between GPU and system memory takes time. In many cases GPU acceleration can be observed when processing large batches of data (e.g. frames of a video). Modify your test to process the same image 100 times and compare performance.

---

<div class="post-metadata">

**Author:** ![trojek](https://avatars.discourse-cdn.com/v4/letter/t/a88e4f/32.png) [@trojek](https://forum.opencv.org/u/trojek)\
**Post date:** [November 24, 2021, 10:22am UTC](https://forum.opencv.org/t/opencv-dnn-module-is-slower-on-gpu-than-on-cpu-jetson-nano/6386/3 "2021-11-24T10:22:30Z")

</div>

You are right. I executed the “upscaling” part of the code in the loop (100 times), and I got much better results using GPU than CPU (about 3x faster).

My goal is to upscale a few images (e. g. 6) with high resolution (e. g. 4000 px x 5000 px) in the shortest time (e. g. 1s per image). How can one archive such results?  
Are there any known methods? For example, split one image into a few, upscale sub-images, then merge them into one?