PaddlePaddle / PaddlePaddle/FastDeploy

OCR的REC模型,能用RCNN的吗,比如rec_r50_fpn_srn

Open
#2,575 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.7k
Forks
756
Avg merge
19h 28m
Merged PRs (30d)
4

Description

我只需要REC模型

OCR的REC模型,能用RCNN的吗
比如rec_r50_fpn_srn

这边只有PP-OCR
使用报错

[INFO] fastdeploy/runtime/backends/paddle/paddle_backend.cc(29)::fastdeploy::PaddleBackend::BuildOption Will inference_precision float32
[INFO] fastdeploy/runtime/runtime.cc(286)::fastdeploy::Runtime::CreatePaddleBackend     Runtime initialized with Backend::PDINFER in Device::GPU.
[ERROR] fastdeploy/runtime/backends/paddle/paddle_backend.cc(392)::fastdeploy::PaddleBackend::Infer     [PaddleBackend] Size of inputs(1) should keep same with the inputs of this model(5).
[ERROR] fastdeploy/vision/ocr/ppocr/recognizer.cc(121)::fastdeploy::vision::ocr::Recognizer::BatchPredict       Failed to inference by runtime.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the input-count error in fastdeploy/runtime/backends/paddle/paddle_backend.cc and the failure reported by fastdeploy/vision/ocr/ppocr/recognizer.cc. Compare the five inputs expected by rec_r50_fpn_srn with the recognizer's single input, then establish whether this model is supported and document a clear outcome.

Written by the indexing model from the issue text.

Assessment

Domain
computer-vision
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.