HeChengHui

Is it possible to track using a webcam or a live camera feed as its source? Do I need to use the light version with YOLOv5s as the backbone to...

Load ONNX model

9

I managed to export some models from the model zoo into ONNX format. However, I have difficulties getting it to work with torchreid. In `torchtools.py`, instead of `torch.load()`, I added...

I am trying to evaluate some trackers on the VisDrone dataset. - https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch - https://github.com/ifzhang/FairMOT I am using their result text files to run evalMOT.m on, with the `runTrackerAllClass `line...

I recently trained a wf42m-vitB-pfc03 model using the wf42m_pfc03_40epoch_8gpu_vit_b config. It came out as 444MB. After converting to onnx using the provided [torch2onnx](https://github.com/deepinsight/insightface/blob/master/recognition/arcface_torch/torch2onnx.py) script, it came out slightly larger in...

Update SCRFD onnx InferenceSession with providers

1

Original code will give error: ValueError: This ORT build has ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider'] enabled. Since ORT 1.9, you are required to explicitly set the providers parameter when instantiating InferenceSession. For...

@Anjok07, thank you for your work and I am impressed with the mdx-net models for vocal separation. I would like to use it in real time (audio streaming in from...

[Win] Does not show GPU profiling

10

**Describe the bug** Scalene shows CPU profiling but not GPU on windows11. **To Reproduce** python 3.10.12 scalene 1.5.29 pytorch-lightning 1.8.1 torch 2.1.0.dev20230830+cu118 torchaudio 2.1.0.dev20230830+cu118 torchmetrics 0.11.4 torchvision 0.16.0.dev20230830+cu118 `scalene xx.py`...

❓ [Question] How to compile model when input is a list of tensors

10

## ❓ Question I am trying to follow the tutorial [here](https://pytorch.org/TensorRT/tutorials/serving_torch_tensorrt_with_triton.html) and am stuck at compiling the model with tensor-rt. The model i am using takes a list of tensors...

 Assume a scenario where SORT tracks by giving 2 IDs to 2 detections as shown.  now there is a new detection in blue, SORT returns tracking ID in...

With both papers released at around the same time, neither results compared with each other. Looking at the validation logs on Vggface2, it seems both performed similarly at 80k iterations....