TF TensorRT misconfigured

Bắt đầu bằng cách tái hiện sự không khớp phiên bản TensorRT trong image Kaggle được tham chiếu, sử dụng các kiểm tra phiên bản được liên kết/được nạp trong Python và mẫu chuyển đổi ResNet50 tối thiểu. Kiểm tra cấu hình TensorFlow TensorRT xung quanh trt_convert.py và các gói TensorRT đã cài đặt trong container. Được coi là hoàn tất khi các phiên bản được liên kết và được nạp khớp nhau và mẫu chạy mà không gặp segmentation fault.

🐛 Bug

Tensorflow TensorRT seems to be wrongly linked.

To Reproduce

On a few recent images (including gcr.io/kaggle-gpu-images/python latest 311277776c9b 7 days ago 47.2GB) I see very different linked and loaded TensorRT libs, namely 8.4 vs 8.6.

import tensorflow.compiler as tf_cc
linked_trt_ver=tf_cc.tf2tensorrt._pywrap_py_utils.get_linked_tensorrt_version()
print(f"Linked TRT ver: {linked_trt_ver}")
loaded_trt_ver=tf_cc.tf2tensorrt._pywrap_py_utils.get_loaded_tensorrt_version()
print(f"Loaded TRT ver: {loaded_trt_ver}")
# Linked TRT ver: (8, 4, 3)
# Loaded TRT ver: (8, 6, 1)

This has been Python. Now, the system inference libraries are indeed at 8.6:

dpkg -l | grep TensorRT

Now, minimal compatibility rules are fulfilled - the loaded version more recent.

However, the linking doesn't work properly. Under these recent containers, minimal TensorRT samples crash:

import tensorflow as tf
from tensorflow.python.compiler.tensorrt import trt_convert as trt
from tensorflow.python.saved_model import signature_constants
from tensorflow.python.saved_model import tag_constants

from tensorflow.keras.applications.resnet50 import ResNet50
tf_model_dir = './models/tf_model'
model = ResNet50(include_top=50, weights='imagenet')
model.save(tf_model_dir)

converter = trt.TrtGraphConverterV2(  
   input_saved_model_dir=tf_model_dir,
)
converter.convert()

MAX_BATCH_SIZE=1 
def input_fn():
   img = tf.random.normal((MAX_BATCH_SIZE, 224,224,3),dtype=tf.float32)
   return (img, )

import faulthandler
faulthandler.enable()
converter.build(input_fn=input_fn) #SEGMENTATION FAULT can happen under missconfigured software!

Expected behavior

Align versions and make the sample code runnable.

Additional context

See the NVIDIA installation guidelines

Conditions from `tensorrt

        "Loaded TensorRT %s but linked TensorFlow against TensorRT %s. A few "
        "requirements must be met:\n"
        "\t-It is required to use the same major version of TensorRT during "
        "compilation and runtime.\n"
        "\t-TensorRT does not support forward compatibility. The loaded "
        "version has to be equal or more recent than the linked version.",