The detected image size couldn't larger than 300x300 in sampleUFFSSD in TensorRT-5.0.0.10?

AI & Data Science Deep Learning (Training & Inference) TensorRT
#1

I change the fixed_shape_resizer of ssd_indeption_v2 from 300x300 into 600x600 and trained my dataset. When I use model to detected image with the size 1280x720 in tensorrt, it’s return the following result:

Begin parsing model…
End parsing model…
Begin building engine…
End building engine…
Num batches 2
Data Size 5529600
*** deserializing
input_c: 3 input_h: 1280 input_w: 720
Cuda failure: 11Aborted (core dumped)

I have changed the INPUT_H and INPUT_W value in BatBatchStreamPPM.h file. If I detect the image smaller than 600x600, there is no error. Does this mean that the size of the picture should not exceed 600x600?

The version of tensorrt I use is TensorRT-5.0.0.10.

Can anyone help me?

Thanks!

#2

Hello,

To help us debug, can you please share a repro package containing the source, model, and dataset that exhibit the error you are seeing?

But generally, if the data prep is expecting 600x600, and you pass it larger sizes, the behavior is undefined.