Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Model] Support PP-OCRv4 pipeline #1913

Merged
merged 78 commits into from
May 11, 2023
Merged

Conversation

linyangshi
Copy link
Contributor

PR types(PR类型)

Description

linyangshi and others added 30 commits March 15, 2023 03:55
add paddledetection to benchmark
@DefTruth DefTruth self-requested a review May 8, 2023 06:03
@DefTruth DefTruth changed the title update ppocr_v4 [Model] Support PP-OCRv4 pipeline May 10, 2023
public:
/** \brief Set up the detection model path, classification model path and recognition model path respectively.
*
* \param[in] det_model Path of detection model, e.g ./ch_PP-OCRv3_det_infer
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

参数说明,ch_PP-OCRv3_det_infer改成ch_PP-OCRv4_det_infer,其他同理

PPOCRv4(fastdeploy::vision::ocr::DBDetector* det_model,
fastdeploy::vision::ocr::Recognizer* rec_model)
: PPOCRv3(det_model, rec_model) {
// The only difference between v2 and v3
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

v3 -> v4

logging.warning(
"DEPRECATED: fd.vision.ocr.PPOCRSystemv4 is deprecated, "
"please use fd.vision.ocr.PPOCRv4 instead.")
super(PPOCRSystemv3, self).__init__(det_model, cls_model, rec_model)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里为什么是super(PPOCRSystemv3, self),而不是super(PPOCRSystemv4, self)

@@ -63,6 +63,26 @@ def vis_perception(im_data,
score_threshold, line_size, font_size)


def vis_perception(im_data,
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里有一份重复的vis_perception定义

@@ -140,6 +140,10 @@ download_fd_model_zxvf yolov8_m_500e_coco.tgz
download_fd_model_zxvf yolov8_n_500e_coco.tgz
download_fd_model_zxvf picodet_l_320_coco_lcnet.tgz
download_fd_model_zxvf yolov7_x_300e_coco.tgz
download_fd_model_zxvf ppyoloe_crn_l_300e_coco.tgz
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这个PR为什么会多出benchmark_ppyolov8的修改,应该是只修改ocrv4

rec_params_file,
rec_label_file,
runtime_option=rec_option)
model = fd.vision.ocr.PPOCRv3(
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

这里应该是fd.vision.ocr.PPOCRv3

@DefTruth
Copy link
Collaborator

LGTM

@DefTruth DefTruth merged commit 643f41e into PaddlePaddle:develop May 11, 2023
DefTruth added a commit that referenced this pull request May 11, 2023
* 添加paddleclas模型

* 更新README_CN

* 更新README_CN

* 更新README

* update get_model.sh

* update get_models.sh

* update paddleseg models

* update paddle_seg models

* update paddle_seg models

* modified test resources

* update benchmark_gpu_trt.sh

* add paddle detection

* add paddledetection to benchmark

* modified benchmark cmakelists

* update benchmark scripts

* modified benchmark function calling

* modified paddledetection documents

* upadte getmodels.sh

* add PaddleDetectonModel

* reset examples/paddledetection

* resolve conflict

* update pybind

* resolve conflict

* fix bug

* delete debug mode

* update checkarch log

* update trt inputs example

* Update README.md

* add ppocr_v4

* update ppocr_v4

* update ocr_v4

* update ocr_v4

* update ocr_v4

* update ocr_v4

---------

Co-authored-by: DefTruth <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants