PaddleX/3.0-rc/pipeline_deploy/high_performance_inference

[giscus[bot]]

PaddleX/3.0-rc/pipeline_deploy/high_performance_inference

https://paddlepaddle.github.io/PaddleX/3.0-rc/pipeline_deploy/high_performance_inference.html

[moment-NEW]

我想问一下，似乎paddleX要求aiofiles>=24.1.0,但是我又能看到最高aiofiles<24.0的gradio应用发布在paddlepaddle上...这是怎么回事？

[mzzya]

pipeline_name: OCR

text_type: general

use_doc_preprocessor: False
use_textline_orientation: False

hpi_config:
auto_paddle2onnx: True
backend: onnxruntime

Serving:
visualize: False

SubPipelines:
DocPreprocessor:
pipeline_name: doc_preprocessor
use_doc_orientation_classify: True
use_doc_unwarping: True
SubModules:
DocOrientationClassify:
module_name: doc_text_orientation
model_name: PP-LCNet_x1_0_doc_ori
model_dir: null
DocUnwarping:
module_name: image_unwarping
model_name: UVDoc
model_dir: null

SubModules:
TextDetection:
module_name: text_detection
model_name: PP-OCRv5_server_det
model_dir: null
limit_side_len: 64
limit_type: min
max_side_limit: 2000
thresh: 0.3
box_thresh: 0.6
unclip_ratio: 1.5
TextLineOrientation:
module_name: textline_orientation
model_name: PP-LCNet_x1_0_textline_ori
model_dir: null
batch_size: 1
TextRecognition:
module_name: text_recognition
model_name: PP-OCRv5_server_rec
model_dir: null
batch_size: 1
score_thresh: 0.0

使用 paddlex-hps:paddlex3.0.3-gpu 报 No inference backend and configuration could be suggested. Reason: Inference backend 'onnxruntime' is unavailable.