HeChengHui

@luisfmnunes Would like to check if you also faced having extra background appearing in the final cropped image as compared to the bounding box given by FaceAnalysis.

@javiabellan Possible for you to share your code for face recognition?

@javiabellan > 3\. Infer face recognizer (IResNet50-WebFace-600K) could you perhaps point me to any reference code? I tried doing ``` handler = insightface.model_zoo.get_model("w600k_r50.onnx", providers=['CUDAExecutionProvider']) handler.prepare(ctx_id=0) handler.compute_sim(ref, ref) ``` where `ref`...

@nttstar is `normed_embedding` still being used? it is returning me `None` when doing the following ``` app = FaceAnalysis(name='antelope', allowed_modules=['detection'], providers=['CUDAExecutionProvider']) app.prepare(ctx_id=0, det_size=(640, 640), det_thresh=0.3) for probe_face in probe_faces: probe_emb...

Might be python version on linux. I got the same error on py3.10, but is gone using py3.8.

@emeryberger  `pynvml==11.4.1`

@emeryberger ``` import torch import torch.nn as nn import torch.optim as optim # Check if GPU is available device = torch.device("cuda" if torch.cuda.is_available() else "cpu") print(device) # Define a sample...

@emeryberger Thank you for the update. However, it seems like the problem still persist. I have tried running the code above just using `scalene code.py` on 2 machines and no...

@emeryberger `Scalene version 1.5.31.1 (2023.09.15)` [profile.zip](https://github.com/plasma-umass/scalene/files/12655220/profile.zip)

@narendasan I am following the `input_signature` guide from [here](https://pytorch.org/TensorRT/ts/getting_started_with_python_api.html). However, i am still getting an error. ``` # i have tried both input_signature = ( torch_tensorrt.Input(shape=[1, 3, 256, 256], dtype=torch.float),...