CUDA out of memory

[suriya030]

While running the pre trained model code in Colab/local device getting the error of ' CUDA out of memory '

[suriya030]

I even tried to increase attention stride to 4 , at max I can infer result on google Colab 2 images without completely filling the gpu .

[mli0603]

Hi @suriya030

The memory consumption depends on various factors. Likely your input image is too high resolution. I assume you are not using the KITTI images by default.

To run on high res images, you can

• Increase the attention stride as you did. Higher strides may help.
• Use the lightweight implementation in the branch here