Sruthikesh Surineni comments

Repositories
Issues
Comments

Results 2 comments of


                                            Sruthikesh Surineni

Failed to export an ONNX attribute, since it's not constant, please try to make things (e.g., kernel size) static if possible

Facing the same issue with torchvision mobilenet. The issue is in onnx._optimize_trace is there a solution for this? resnet_50 and googlenet worked fine, some networks have this issue

CUDA Out of Memory

what are the flags for constraining GPU memory via the evaluator.evaluate API? even with 8x80GB GPUs i'm running out of memory even with flag HFLM max_memory_per_gpu="60GB". any idea how to...