Muhammad Haritsah Mukhlis
Muhammad Haritsah Mukhlis
I managed to quantize the model using [NVIDIA/pytorch-quantization](https://github.com/NVIDIA/TensorRT/tree/main/tools/pytorch-quantization). From my experiments, the accuracy drop is around 3%, gpu memory only reduced by 10% and the speed (PTQ->TensorRT-FP16-INT8) is close to...
> > I've solved the issue on lightning==2.1.3 . When rewriting any epoch_end function, if you log, just make sure that the tensor is on gpu device. If you initialize...
You can attach the additional `nn.Module` to the onnx exporter as and it will be processed by [ConvertableCompletePipelineModel](https://github.com/Deci-AI/super-gradients/blob/7907c486d1a0bb479c68590ffd5bc8478f9f18b8/src/super_gradients/training/models/conversion.py#LL211C22-L211C54) Example code: ```python= import torch import torch.nn as nn class PatchDeepStreamOutput(nn.Module): def...
@LukeAI , Is the error appear when exporting the model or after exporting/inferencing the model?
I think it'll be fine, it's just a warning
Nice information. I previously use yolov6 which also has the same [end2end](https://github.com/meituan/YOLOv6/blob/main/yolov6/models/end2end.py) to add `EfficientNMS_TRT`. But I've never done that because despite the warnings, the model works perfectly.
> can confirm no segfaults! no idea why it's different. I think its because you're forcing to rename the nodes without telling the graph that the nodes have changed (I...
@LukeAI You should add `class_agnostic` as the parameter in `forward` and `symbolic` functions and modify the `TRT_NMS.apply()` arguments as needed. ``` def forward( .... .... class_agnostic=1) def symbolic( .... .......
It has something to do with torch/pytorch-quantization internal libraries as mentioned in [#issues/2964](https://github.com/NVIDIA/TensorRT/issues/2964). I also had this problem but i got it working by using `torch==1.11.0`, I have to downgrade...
I had the same problem, different onnx output result from yolo_nas pretrained coco and yolo_nas trained on custom dataset. @NatanBagrov @BloodAxe ``` net = models.get(Models.YOLO_NAS_S, pretrained_weights="coco") -> tested with street...