torch2trt
torch2trt copied to clipboard
An easy to use PyTorch to TensorRT converter
Adds support for converting models tracing on CPU rather than GPU
Hi there, I notice that the einsum converter can only handle the case: torch.einsum(eq, x, y) while not the case: torch.einsum(eq, [x, y]).
when use torch2trt convert the torch.eq, error occurs. `mm = torch.eq(mm, 0.)` mm is tensor and mm.shape = [3136, 1, 3, 3] File "/media/cfs/torch2trt-master/examples/inpainting/model.py", line 329, in forward mm =...
Currently, `add_trt_constant` assumes dim > 1 for input tensors (where the 1st dimension is probably assumed to be the batch dimension). However, there are situations where we may use one...
Hi, I upgraded L4T versions from 32.2.1 to the latest release 32.4.3, which has me upgrading from PyTorch 1.3 to PyTorch 1.6.0 and TensorRT 6 to TensorRT 7.1.3. I believe...
hi, I'm trying to run pointpillar on tensorRT, and I am confused about its performance.  the structure of my model are the same as this onnx graph,...
Hi, I am trying to run the Keypoint R-CNN in NVIDIA Deepstream. I think to do that I need to convert pytorch model to a TRT model. The Pytorch model...
I'm trying to convert this model: `model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)` This is the code of the conversion: ``` model = torch.load('/path/to/model/trained_model.pt') model.eval() device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu') #dummy input...
I use torch2trt to convert a trained model. It output below messages. ``` Warning: Encountered known unsupported method torch.nn.functional.has_torch_function_unary Warning: Encountered known unsupported method torch.nn.functional.silu Warning: Encountered known unsupported method...