Open Mingyuan1997 opened 1 year ago
Please try to use the "batched_predict" function with a small bsize, e.g. bsize =500.
Thanks for your response. My issue is even worse. Even I run one demo input and the cuda gets out of memory.
And the cuda memory budget is still quite limited for batch_predict with a small bsize with rdn model. Especially on high-resolution images
I tried an input image 1920x1080, scale x2, rdn model always out of memory
Do you have a value of expected cuda memory allocated of your code base with repsect to input image size. I tried with 3090 and it's always out of my cuda memory. Thanks!