Comments (26)
from paddleocr.
但是这个识别效果有问题,是不是不能直接改为32位,希望解答一下
from paddleocr.
from paddleocr.
可以提供一下config文件的信息吗
from paddleocr.
可以提供一下config文件的信息吗
Global:
use_gpu: false
epoch_num: 600
log_smooth_window: 20
print_batch_step: 10
save_model_dir: ./output/pgnet_r50_vd_seal_run/
save_epoch_step: 300
eval_batch_step:
- 0
- 400
cal_metric_during_train: false
pretrained_model: ./pretrain_models/train_step1/best_accuracy
checkpoints: null
save_inference_dir: null
use_visualdl: false
infer_img: null
valid_set: totaltext
save_res_path: ./output/pgnet_r50_vd_totaltext/predicts_pgnet.txt
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
character_type: EN
max_text_length: 50
max_text_nums: 10
tcl_len: 64
load_static_weights: false
Architecture:
model_type: e2e
algorithm: PGNet
Transform: null
Backbone:
name: ResNet
layers: 50
Neck:
name: PGFPN
Head:
name: PGHead
Loss:
name: PGLoss
tcl_bs: 32
max_text_length: 50
max_text_nums: 10
pad_num: 6623
Optimizer:
name: Adam
beta1: 0.9
beta2: 0.999
lr:
name: Cosine
learning_rate: 0.001
warmup_epoch: 50
regularizer:
name: L2
factor: 5.0e-05
PostProcess:
name: PGPostProcess
score_thresh: 0.5
mode: fast
Metric:
name: E2EMetric
mode: A
gt_mat_dir: ./train_data/total_text/gt
character_dict_path: ppocr/utils/ppocr_keys_v1.txt
main_indicator: f_score_e2e
Train:
dataset:
name: PGDataSet
data_dir: ./train_data/
label_file_list:- ./train_data/label_2_rotate_transform_final.txt
- ./train_data/label_3_rotate_transform_final.txt
ratio_list: - 1.0
- 1.0
transforms: - DecodeImage:
img_mode: BGR
channel_first: false - E2ELabelEncodeTrain: null
- PGProcessTrain:
batch_size: 5
min_crop_size: 24
min_text_size: 4
max_text_size: 512 - KeepKeys:
keep_keys:- images
- tcl_maps
- tcl_label_maps
- border_maps
- direction_maps
- training_masks
- label_list
- pos_list
- pos_mask
loader:
shuffle: true
drop_last: true
batch_size_per_card: 5
num_workers: 16
Eval:
dataset:
name: PGDataSet
data_dir: ./train_data/
label_file_list:
- ./train_data/label_test.txt
transforms: - DecodeImage:
img_mode: BGR
channel_first: false - E2ELabelEncodeTest:
character_dict_path: ppocr/utils/ppocr_keys_v1.txt - DetResizeForTest:
image_shape:- 512
- 512
padding: true
- ToCHWImage: null
- KeepKeys:
keep_keys:- image
- shape
- polys
- texts
- ignore_tags
- img_id
loader:
shuffle: false
drop_last: false
batch_size_per_card: 1
num_workers: 2
profiler_options: null
from paddleocr.
from paddleocr.
可以提供一下config文件的信息吗
有哪些地方需要调整吗
from paddleocr.
目前看来,有点像head网络初始化有问题,因为我看字典使用的是ppocr_keys_v1.txt,它里面共有6623个字符,你可以往这方面考虑一下
from paddleocr.
目前看来,有点像head网络初始化有问题,因为我看字典使用的是ppocr_keys_v1.txt,它里面共有6623个字符,你可以往这方面考虑一下
我是直接下载整个模型文件下来的,里面有相关的模型和配置文件,但是没有相关字典,这种怎么处理呢
from paddleocr.
目前看来,有点像head网络初始化有问题,因为我看字典使用的是ppocr_keys_v1.txt,它里面共有6623个字符,你可以往这方面考虑一下
from paddleocr.
可以直接用训练权重里提供的config.yml 文件试下
from paddleocr.
可以直接用训练权重里提供的config.yml 文件试下
from paddleocr.
from paddleocr.
from paddleocr.
或者你们那有最新的吗,可以私发我一下,我换上去试试
from paddleocr.
也可以看看目前这个文件和你们现在最新文件的差异
from paddleocr.
可以直接用训练权重里提供的config.yml 文件试下
后续怎么处理呢
from paddleocr.
这边会记录一下,尝试复现问题
from paddleocr.
这边会记录一下,尝试复现问题
图中是两份config在推理环节可能比较重要的差异,可以看一下
如果有进展的话可以跟我说一下,需要远程控制的话,我这边可以协助复现,因为这个跟我们后续的一个排期计划比较相关,有劳了,感谢!
from paddleocr.
训练和推理使用了不同的配置吗? 看到字典不同应该是导致参数无法加载最主要的问题。 如果使用了ic15_dict.txt 训练,请同样使用这个ic15_dict.txt推理。
另外:训练和推理的配置文件应保持一致
from paddleocr.
训练和推理使用了不同的配置吗? 看到字典不同应该是导致参数无法加载最主要的问题。 如果使用了ic15_dict.txt 训练,请同样使用这个ic15_dict.txt推理。 另外:训练和推理的配置文件应保持一致
我没有进行训练,图中左侧的是打码拉下来后e2e的默认配置文件,图中右侧才是印章模型配套的config,目前这个config中的训练和推理用的txt是一致的。目前是打算直接使用模型和配套的config,现象是使用下载下来的模型和配置文件会有报错。
from paddleocr.
目前看来,有点像head网络初始化有问题,因为我看字典使用的是ppocr_keys_v1.txt,它里面共有6623个字符,你可以往这方面考虑一下
可以提供一下这个模型和config的下载地址,我这边尝试复现一下
from paddleocr.
from paddleocr.
怎么发过去呢,要不加一下微信
…
---原始邮件--- 发件人: @.> 发送时间: 2024年4月25日(周四) 晚上6:53 收件人: @.>; 抄送: @.@.>; 主题: Re: [PaddlePaddle/PaddleOCR] paddleOCR运行印章比对模型报错 (Issue #11986) 目前看来,有点像head网络初始化有问题,因为我看字典使用的是ppocr_keys_v1.txt,它里面共有6623个字符,你可以往这方面考虑一下 可以提供一下这个模型和config的下载地址,我这边尝试复现一下 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: @.***>
贴个链接就好
from paddleocr.
from paddleocr.
已线下沟通,此处close
from paddleocr.
Related Issues (20)
- 混贴票据识别 HOT 1
- ch_PP-OCRv4_rec_svtr_large.yml训练导出的模型,使用predict_rec.py预测宽度比较大的图片时出现(InvalidArgument) Broadcast dimension mismatch HOT 4
- server模型推理出错(core dumped) HOT 3
- How to find rotated image.
- 长文本行识别,偶尔会出现单个字符被识别成2个相同字符的错误,比如,只有一个"一",识别成2个了,怎样改善? HOT 5
- Notice of PPOCRLabel and StyleText Project Migration HOT 5
- 表格识别内容没有正常转义 '<' '>'
- ppocrv4 det 微调 HOT 1
- svtr yml用来训练,爆显存,batch_size=1也不行 HOT 2
- How to recognize the digital numbers in the rectangle box with paddleocr? HOT 1
- Error about ppocrlabel, when start ppocrlabl HOT 2
- pdf扫描件表格识别不准确,如何优化? HOT 7
- cudaErrorInitializationError at ../paddle/phi/backends/gpu/cuda/cuda_info.cc:178 HOT 5
- PP-ChatOCRv2-common 默认的提示词规则是什么样的呢?以及数据微调格式
- paddleocr 在华为910b的npu上跑很慢且只跑了一张卡 HOT 2
- 报错-非法指令 coredump HOT 4
- OCR system producing no output when run on GPU HOT 3
- Using multiple dictionaries with paddleocr HOT 6
- 编译安装paddle-custom-npu-0.0.0后使用paddleocr特别慢 HOT 1
- 按照教程将SER+RE串联执行,代码报错 argument 'x' (position 0) must be list of Tensors, but got empty list HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from paddleocr.