radeonwu / tensorrt_tx2_20fps Goto Github PK

i have followed your steps and i am getting 2 fps not 10 as your output

edit
i got 3 after overclocking

I keep getting a segmentation fault when it begins parsing the prototxt file. Do you know which prototxt file i need to use for faster rcnn?

cause i see there are no special difference between origianl TensorRT FasterRCNN and this one.
and i get 5fps using the original TensorRT FasterRCNN

can i know the reason?

@radeonwu Hi can i have few queries
1.Can i run faster rcnn using tensorflow / tensor rt on the tx2 board
2. should i use pycaffe-frcnn to run the following models
3. i need to run frcnn+resnet on tx2 board

Thanks in advance

Hi, great job on setting up Faster-RCNN with TensorRT! Are you also planning on doing the same for YOLO and SSD? :) And also what fps are you currently getting when running sampleFasterRCNN?

Hi, sorry, I don't know if it is necessary to open an issue for this. But I have the repo compiled but when I launched the command I obtain:

sudo ./sample_fasterRCNN --video=/home/nvidia/Videos/1.mp4
Begin parsing model...
End parsing model...
Begin building engine...
Segmentation fault (core dumped)

Thanks for your help.

Begin parsing model...
End parsing model...
Begin building engine...
Segmentation fault (core dumped)