Anurag Dixit

Signed-off-by: Anurag Dixit # Description Currently, the code base for torch.fx.passes.pass_manager does not work with Jetson AGX platform. Hence, causing failure to import torch_tensorrt on Jetson AGX with Build artifact...

Segregate the cpu name for aarch64-linux and aarch64-qnx

1

We need to use separate cpu name for aarch64-linux and aarch64-qnx in order to prevent the libraries from clubbing with each other.

feat: Adding an example for semantic segmentation

1

# Description This PR focuses on semantic segmentation using VGG16-Unet network on ADE20K dataset Fixes # (issue) ## Type of change Please delete options that are not relevant and/or add...

chore: Increasing torch_version deps in setup

1

Signed-off-by: Anurag Dixit # Description Bumping the range check for torch version in setup.py Fixes # (issue) ## Type of change Please delete options that are not relevant and/or add...

feat: Fixed conv1d converter when weights are Tensor

8

# Description This PR enables the conv1d -> conv2d converter mapping work when the weights are Tensor. PS: Kernel tensor is also unsqueezed when the filterDims are unsqueezed for conv1d...

fix: Fix deconv kernel channel num_output_maps where wts are ITensor

1

# Description Please include a summary of the change and which issue is fixed. Please also include relevant motivation and context. List any dependencies that are required for this change....