Amar3tto commented on code in PR #37186: URL: https://github.com/apache/beam/pull/37186#discussion_r3201590069
########## sdks/python/apache_beam/examples/inference/pytorch_image_object_detection.py: ########## @@ -0,0 +1,563 @@ +# +# 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. +# + +"""This pipeline performs object detection using an open-source PyTorch +TorchVision detection model (e.g., Faster R-CNN ResNet50 FPN) on GPU. + +It reads image URIs from a GCS input file, decodes and preprocesses images, +runs batched GPU inference via RunInference, post-processes detection outputs, +and writes results to BigQuery. + +The pipeline targets stable and reproducible performance measurements for +GPU inference workloads (no right-fitting; fixed batch size). +""" + +import argparse +import io +import json +import logging +import threading +import time +from typing import Any +from typing import Dict +from typing import Iterable +from typing import List +from typing import Optional +from typing import Sequence +from typing import Tuple + +import apache_beam as beam +from apache_beam.io.filesystems import FileSystems +from apache_beam.ml.inference.base import KeyedModelHandler +from apache_beam.ml.inference.base import PredictionResult +from apache_beam.ml.inference.base import RunInference +from apache_beam.ml.inference.pytorch_inference import PytorchModelHandlerTensor +from apache_beam.options.pipeline_options import PipelineOptions +from apache_beam.options.pipeline_options import SetupOptions +from apache_beam.options.pipeline_options import StandardOptions +from apache_beam.runners.runner import PipelineResult +from apache_beam.transforms import window + +from google.cloud import pubsub_v1 +import torch +import PIL.Image as PILImage + +# ============ Utility & Preprocessing ============ + + +def now_millis() -> int: + return int(time.time() * 1000) + + +def read_gcs_file_lines(gcs_path: str) -> Iterable[str]: + """Reads text lines from a GCS file.""" + with FileSystems.open(gcs_path) as f: + for line in f.read().decode("utf-8").splitlines(): + yield line.strip() + + +def load_image_from_uri(uri: str) -> bytes: + with FileSystems.open(uri) as f: + return f.read() + + +def decode_to_tens( + image_bytes: bytes, + resize_shorter_side: Optional[int] = None) -> torch.Tensor: + """Decode bytes -> RGB PIL -> optional resize -> float tensor [0..1], CHW. + + Note: TorchVision detection models apply their own normalization internally. + """ + with PILImage.open(io.BytesIO(image_bytes)) as img: + img = img.convert("RGB") + + if resize_shorter_side and resize_shorter_side > 0: + w, h = img.size + # Resize so that shorter side == resize_shorter_side, keep aspect ratio. + if w < h: + new_w = resize_shorter_side + new_h = int(h * (resize_shorter_side / float(w))) + else: + new_h = resize_shorter_side + new_w = int(w * (resize_shorter_side / float(h))) + img = img.resize((new_w, new_h)) + + import numpy as np + arr = np.asarray(img).astype("float32") / 255.0 # H,W,3 in [0..1] + arr = np.transpose(arr, (2, 0, 1)) # CHW + return torch.from_numpy(arr) + + +def sha1_hex(s: str) -> str: + import hashlib + return hashlib.sha1(s.encode("utf-8")).hexdigest() + + +# ============ DoFns ============ + + +class RateLimitDoFn(beam.DoFn): Review Comment: Removed -- 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]
