From bbfa08b25b73cb348bd875d8d065443d49b6f85d Mon Sep 17 00:00:00 2001 From: Lin Manhui Date: Tue, 17 Jun 2025 21:29:18 +0800 Subject: [PATCH] [Feat] Accommodate PaddleX 3.0.2 changes (#15745) * Fix default run_mode * Bump paddlex version * Fix typo --- .../high_performance_inference.en.md | 4 ++-- .../deployment/high_performance_inference.md | 4 ++-- mkdocs.yml | 4 ++-- paddleocr/_common_args.py | 22 +++++++++++++++---- pyproject.toml | 2 +- 5 files changed, 25 insertions(+), 11 deletions(-) diff --git a/docs/version3.x/deployment/high_performance_inference.en.md b/docs/version3.x/deployment/high_performance_inference.en.md index 4d93121431..d1d5c4ebfe 100644 --- a/docs/version3.x/deployment/high_performance_inference.en.md +++ b/docs/version3.x/deployment/high_performance_inference.en.md @@ -20,7 +20,7 @@ paddleocr install_hpi_deps {device_type} The supported device types are: - `cpu`: For CPU-only inference. Currently supports Linux systems, x86-64 architecture processors, and Python 3.8-3.12. -- `gpu`: For inference using either CPU or NVIDIA GPU. Currently supports Linux systems, x86-64 architecture processors, and Python 3.8-3.12. Refer to the next subsection for detailed instructions. +- `gpu`: For inference using either CPU or NVIDIA GPU. Currently supports Linux systems, x86-64 architecture processors, and Python 3.8-3.12. If you want to use the full high-performance inference capabilities, you also need to ensure that a compatible version of TensorRT is installed in your environment. Refer to the next subsection for detailed instructions. Only one type of device dependency should exist in the same environment. For Windows systems, it is currently recommended to install within a Docker container or [WSL](https://learn.microsoft.com/en-us/windows/wsl/install) environment. @@ -48,7 +48,7 @@ pip list | grep nvidia-cuda pip list | grep nvidia-cudnn ``` -Secondly, ensure that the environment has the required TensorRT version installed. Currently, PaddleOCR only supports TensorRT 8.6.1.6. If using the official PaddlePaddle image, you can install the TensorRT wheel package with the following command: +Secondly, it is recommended to ensure that a compatible version of TensorRT is installed in the environment; otherwise, the Paddle Inference TensorRT subgraph engine will be unavailable, and the program may not achieve optimal inference performance. Currently, PaddleOCR only supports TensorRT 8.6.1.6. If using the official PaddlePaddle image, you can install the TensorRT wheel package with the following command: ```bash python -m pip install /usr/local/TensorRT-*/python/tensorrt-*-cp310-none-linux_x86_64.whl diff --git a/docs/version3.x/deployment/high_performance_inference.md b/docs/version3.x/deployment/high_performance_inference.md index a6d4245816..818b056628 100644 --- a/docs/version3.x/deployment/high_performance_inference.md +++ b/docs/version3.x/deployment/high_performance_inference.md @@ -20,7 +20,7 @@ paddleocr install_hpi_deps {设备类型} 支持的设备类型包括： - `cpu`：仅使用 CPU 推理。目前支持 Linux 系统、x86-64 架构处理器、Python 3.8-3.12。 -- `gpu`：使用 CPU 或 NVIDIA GPU 推理。目前支持 Linux 系统、x86-64 架构处理器、Python 3.8-3.12。请查看下一小节的详细说明。 +- `gpu`：使用 CPU 或 NVIDIA GPU 推理。目前支持 Linux 系统、x86-64 架构处理器、Python 3.8-3.12。如果希望使用完整的高性能推理功能，还需要确保环境中安装有符合要求的 TensorRT。请查看下一小节的详细说明。 同一环境中只应该存在一种设备类型的依赖。对于 Windows 系统，目前建议在 Docker 容器或者 [WSL](https://learn.microsoft.com/zh-cn/windows/wsl/install) 环境中安装。 @@ -48,7 +48,7 @@ pip list | grep nvidia-cuda pip list | grep nvidia-cudnn ``` -其次，需确保环境中安装有符合要求的 TensorRT。目前 PaddleOCR 仅支持 TensorRT 8.6.1.6。如果使用飞桨官方镜像，可执行如下命令安装 TensorRT wheel 包： +其次，建议确保环境中安装有符合要求的 TensorRT，否则 Paddle Inference TensorRT 子图引擎将不可用，程序可能无法取得最佳推理性能。目前 PaddleOCR 仅支持 TensorRT 8.6.1.6。如果使用飞桨官方镜像，可执行如下命令安装 TensorRT wheel 包： ```bash python -m pip install /usr/local/TensorRT-*/python/tensorrt-*-cp310-none-linux_x86_64.whl diff --git a/mkdocs.yml b/mkdocs.yml index bda1fb4a6f..efcd183430 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -109,7 +109,7 @@ plugins: PP-ChatOCRv4简介: PP-ChatOCRv4 Introduction 推理部署: Model Deploy 高性能推理: High-Performance Inference - 获取onnx模型: Obtaining ONNX Models + 获取ONNX模型: Obtaining ONNX Models 端侧部署: On-Device Deployment 服务化部署: Serving Deployment 模块列表: Module List @@ -275,7 +275,7 @@ nav: - PP-ChatOCRv4简介: version3.x/algorithm/PP-ChatOCRv4/PP-ChatOCRv4.md - 推理部署: - 高性能推理: version3.x/deployment/high_performance_inference.md - - 获取onnx模型: version3.x/deployment/obtaining_onnx_models.md + - 获取ONNX模型: version3.x/deployment/obtaining_onnx_models.md - 端侧部署: version3.x/deployment/on_device_deployment.md - 服务化部署: version3.x/deployment/serving.md - 基于Python或C++预测引擎推理: version3.x/deployment/python_and_cpp_infer.md diff --git a/paddleocr/_common_args.py b/paddleocr/_common_args.py index 626bd2d3a9..1aecece695 100644 --- a/paddleocr/_common_args.py +++ b/paddleocr/_common_args.py @@ -59,12 +59,22 @@ def prepare_common_init_args(model_name, common_args): device = common_args["device"] if device is None: device = get_default_device() - device_type, _ = parse_device(device) + device_type, device_ids = parse_device(device) + if device_ids is not None: + device_id = device_ids[0] + else: + device_id = None - init_kwargs = {"device": device} + init_kwargs = {} init_kwargs["use_hpip"] = common_args["enable_hpi"] + init_kwargs["hpi_config"] = { + "device_type": device_type, + "device_id": device_id, + } - pp_option = PaddlePredictorOption(model_name) + pp_option = PaddlePredictorOption( + model_name, device_type=device_type, device_id=device_id + ) if device_type == "gpu": if common_args["use_pptrt"]: if common_args["pptrt_precision"] == "fp32": @@ -74,13 +84,17 @@ def prepare_common_init_args(model_name, common_args): "pptrt_precision" ] pp_option.run_mode = "trt_fp16" + else: + pp_option.run_mode = "paddle" elif device_type == "cpu": enable_mkldnn = common_args["enable_mkldnn"] if enable_mkldnn: pp_option.mkldnn_cache_capacity = common_args["mkldnn_cache_capacity"] else: pp_option.run_mode = "paddle" - pp_option.cpu_threads = common_args["cpu_threads"] + pp_option.cpu_threads = common_args["cpu_threads"] + else: + pp_option.run_mode = "paddle" init_kwargs["pp_option"] = pp_option return init_kwargs diff --git a/pyproject.toml b/pyproject.toml index c2c5ad2933..7a92df8d8d 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -39,7 +39,7 @@ classifiers = [ "Topic :: Utilities", ] dependencies = [ - "paddlex[ocr,ie,multimodal]==3.0.1", + "paddlex[ocr,ie,multimodal]==3.0.2", "PyYAML>=6", "typing-extensions>=4.12", ]