azhurkevich commented on code in PR #22131: URL: https://github.com/apache/beam/pull/22131#discussion_r929448863
########## sdks/python/apache_beam/ml/inference/tensorrt_inference.py: ########## @@ -0,0 +1,281 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +# pytype: skip-file + +import logging +import sys +from typing import Any +from typing import Dict +from typing import Iterable +from typing import Optional +from typing import Sequence +from typing import Tuple + +import numpy as np + +import tensorrt as trt +from apache_beam.io.filesystems import FileSystems +from apache_beam.ml.inference.base import ModelHandler +from apache_beam.ml.inference.base import PredictionResult +from cuda import cuda + +TRT_LOGGER = trt.Logger(trt.Logger.INFO) + +logging.basicConfig(level=logging.INFO) +logging.getLogger("TensorRTEngineHandlerNumPy").setLevel(logging.INFO) +log = logging.getLogger("TensorRTEngineHandlerNumPy") + + +def _load_engine(engine_path): + file = FileSystems.open(engine_path, 'rb') + runtime = trt.Runtime(TRT_LOGGER) + engine = runtime.deserialize_cuda_engine(file.read()) + assert engine + return engine + + +def _load_onnx(onnx_path): + builder = trt.Builder(TRT_LOGGER) + network = builder.create_network( + flags=1 << int(trt.NetworkDefinitionCreationFlag.EXPLICIT_BATCH)) + parser = trt.OnnxParser(network, TRT_LOGGER) + with FileSystems.open(onnx_path) as f: + if not parser.parse(f.read()): + log.error("Failed to load ONNX file: %s", onnx_path) + for error in range(parser.num_errors): + log.error(parser.get_error(error)) + sys.exit(1) + return network, builder + + +def _build_engine(network, builder): + config = builder.create_builder_config() + runtime = trt.Runtime(TRT_LOGGER) + plan = builder.build_serialized_network(network, config) + engine = runtime.deserialize_cuda_engine(plan) + builder.reset() + return engine + + +def _validate_inference_args(inference_args): + """Confirms that inference_args is None. + + TensorRT engines do not need extra arguments in their execute_v2() call. + However, since inference_args is an argument in the RunInference interface, + we want to make sure it is not passed here in TensorRT's implementation of + RunInference. + """ + if inference_args: + raise ValueError( + 'inference_args were provided, but should be None because TensorRT ' + 'engines do not need extra arguments in their execute_v2() call.') + + +def ASSERT_DRV(args): Review Comment: Noted, will adjust in next commit -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
