Christina-Young-NVIDIA

Results 14 comments of Christina-Young-NVIDIA

❓ [Question] Expected isITensor() to be true but got false Requested ITensor from Var, however Var type is c10::IValue

Bo needs to ask user to try with latest codebase.

🐛 [Bug] Cannot convert any detection model from torchvision nor detectron

Model / feature request.

🐛 [Bug] DETR network conversion failed

This is a model feature request - whether or not we will support this model.

🐛 [Bug] conv2d of sum results in "Expected orig_dims.nbDims > 2 to be true but got false. Unable to create convolution layer from node"

Bo can check on whether this is still an issue.

🐛 [Bug] Segmentation Fault When Trying to Quantize ResNet50 model

We think this is fixed. Dheeraj to check.

🐛 [Bug] Segmentation Fault When Trying to Quantize ResNet50 model

@ivan94fi have you been able to check? We would like to close this out.

🐛 [Bug] timm_efficientnet non-pretrained+fp32 returns incorrect result

Bo needs to ask user to see if they are experiencing issue with latest codebase.

❓ [Question] How do you fix "broadcast dimensions must be conformable"?

Naren needs to ask user to retest with latest codebase.

🐛 [Bug] aten::add does not convert with dynamic batch

This now working, it just needs to be tested.

✨[Feature] Support auto data type transformation between int64 <-> int32

Duplicate of TensorRT #1546. Is this already support in the current codebase? Bo needs to confirm that we can close this issue.