dexception

Hi, It is available in marian. Can it be added here ?

Yolov3-tiny 416 the default model with the default cfg file. ``` Traceback (most recent call last): File "onnx_to_tensorrt.py", line 228, in main() File "onnx_to_tensorrt.py", line 202, in main trt_outputs =...

Getting Inference time for SCRFD_500M => 31.227 millisecond vs 3.6 millisecond claimed ? how ?

14

 As you can see i ran the loop 10 times to confirm the result.  The results are way off the time given by you. Am i missing something...

Waiting for Resnet-18 based Model

Changed this line: `auto parser = nvonnxparser::createParser(*network, gLogger);` ``` #include #include #include #include #include #include #include #include #include #include "sys/time.h" #include "opencv2/opencv.hpp" #include "NvInfer.h" #include "NvOnnxParser.h" #include "NvOnnxParserRuntime.h" #include "NvOnnxConfig.h"...

This message has been posted by a fellow developer. It is not accurate.

Hi, Looking for this everywhere but no there is training option available. Please add this whenever you guys find time.

Any SSD implementation with mixnet small ?

1

SSD implementation to use it as an object detector with mixnet backbone would be an excellent option. Waiting for your response.

1. Can you add some pretrained models ? 2. Can you share the format for training on custom dataset and how to prepare the dataset ?

Training is taking too much time. How do i speed it up ?