tf_to_trt_image_classification with custom model

Robotics & Edge Computing Jetson & Embedded Systems Jetson TX2
1

Hello everyone!

I wanted to feed a custom model (built with TensorFlow) to the converter and the classifier example here:

I have tried to do transfer learning on a pretrained VGG19 network (without top layers). After converting the model to TensorRT I have noticed (in part) substantial differences in the results when comparing TensorFlow and TensorRT. I have posted my example here:

https://devtalk.nvidia.com/default/topic/1032763/gpu-accelerated-libraries/deviating-results-with-tensorrt/

Has anyone tried something similar on the Jetson TX2?

Greetings,
Mario

2

Hi,

We have run VGG19 with TensorRT before but didn’t find any accuracy problem.
Before investigation, could you help to check if the input of TensorFlow and TensorRT is identical?

Thanks.

3

Hello!

Thanks for your reply! I have built a complete example to compare the results of TensorFlow (Keras), TensorRT (Python) and the image classification example (TensorRT/C++) here:

The output of inferencing on the (in each case the same) example pictures can be seen here:

Log output of “test_keras.py”:

Log output of “test_trt.py”:

Log output of “test_classifier.py”:

You will notice that there are not only differences in percentage (which could be neglected), but also in the predicted class itself (which is obviously a problem).

Please tell me what I did wrong.

Greetings,
Mario

4

Hi,

The input data of Keras and TensorRT are different.
It’s recommended to use the same python module for preprocessing(ex. ImageDataGenerator) and then compare the results.

Thanks.