Jeff Hoang comments

Results 18 comments of


                                            Jeff Hoang

Converted YOLOv3 model has the same size as before

me too

infer.py results in same parts predicted twice

Hello @rajat-008. Could you please tell me, where to get openpose model. I want to run infer.py also

Can you add inference script?

hi @peteryuX . i has follow your code many time and it is beatiful work. i am not familiar with tf-2 and i has a same question how to do...

how to create your lfw aligned 112x112 dataset?

thank for your advice.

How to export the insightface mxnet model to onnx model which is same as the onnx model given to download.

hi @sky186 @flazerain have you fixed problem above? i also try to convert arcface LResNet100E-IR [mxnet](https://github.com/deepinsight/insightface/wiki/Model-Zoo) to onnx by using [convert_onnx.py](https://github.com/deepinsight/insightface/tree/master/deploy). Then, it seem that, i got error with PRelu...

Is there any mehtod for converting mobilenet0.25 to TensorRT engine?

hello @gan3sh500 can you share your onnx2tensorrt conversion?

Is there any mehtod for converting mobilenet0.25 to TensorRT engine?

@QuantumLiu why and where is tensorrt Retinaface in tensorrt >7.1?

[YOLOV7-QAT] Cannot convert onnx to trt engine

This is the full log ``` &&&& RUNNING TensorRT.trtexec [TensorRT v8500] # /usr/src/tensorrt/bin/trtexec --onnx=qat_models/trained_qat/pgie/1/qat.onnx --int8 --fp16 --workspace=1024000 --minShapes=images:4x3x416x416 --optShapes=images:4x3x416x416 --maxShapes=images:4x3x416x416 [12/04/2023-09:06:56] [W] --workspace flag has been deprecated by --memPoolSize flag....

Cannot run inference video

i change type of aligned_norm from uint8 to float32 and it work I use inference_model_993_quant.tflite model. But why is it so slow? embedding time is suround 0.40273499488830566s My CPU is...

Cannot run inference video

i find out that invoke() takes up so much time. Do you have any solution?