Я получаю следующую ошибку при развертывании оптимизированной модели TF-TRT в Tensorflow: обслуживание в док-контейнере.
: E tensorflow_serving/core/aspired_versions_manager.cc:358]
Servable {name: trt-frcnn version: 1} cannot be loaded:
Not found: Op type not registered 'TRTEngineOp' in binary running on c181d915422c.
Make sure the Op and Kernel are registered in the binary running in this process.
Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
Вот командная строка
docker run -t --rm --name trt-frcnn \
-p 9000:8500 \
-v "/home/yilrr/tf-serving/trt-frcnn-opf/versions/:/models/trt-frcnn" \
-e MODEL_NAME=trt-frcnn \
-t tensorflow/serving:latest-gpu
Кажется, тензорный поток: обслуживание не поддерживает узел 'TRTEngineOp', верно?