mindspore-lab/mindocr

Issues

• 能否提供一个在910b上进行pp-ocr v4部署的样例？

  #698 opened 20 days ago by bltcn
  2

• 在910b，cann8.0 rc1上转换ppocrv4版本特别慢

  #701 opened 20 days ago by bltcn
  2

• 在910b上，使用pp-ocr v4进行推理报错

  #702 opened 20 days ago by bltcn
  0

• 在8卡910B3的机器上推理pp-ocrv4报错

  #700 opened 23 days ago by bltcn
  1

• 模型离线推理精度低

  #696 opened 2 months ago by adamzhg
  8

• How to do only text detection on minidocr?

  #691 opened 2 months ago by R4Ajeti
  1

• PaddleOCR转换错误

  #690 opened 2 months ago by adamzhg
  3

• When I used svtr_tiny_ch.yaml to configure training, there was a loss of nan

  #678 opened 3 months ago by zx214
  11

• Issue on running distributed training

  #687 opened 3 months ago by ThomasLimWZ
  3

• dbnet在Ascend910B3上训练速度非常慢

  #683 opened 3 months ago by zx214
  6

• The learning rate detected in the optimizer is not a Parameter type, so it is not recorded. Its type is '_IteratorLearningRate'.

  #677 opened 3 months ago by TanateT
  3

• When I used svtr_tiny.yaml to configure training, there was a loss of nan

  #670 opened 3 months ago by TanateT
  15

• 多机多卡无限等待bug

  #582 opened 4 months ago by jiangxiluning
  1

• [630][Model] DBNet backbone新增ResNet18和MobileNetV3(large0.5)支持

  #243 opened 4 months ago by HaoyangLee
  1

• 【需求】支持自定义配置，自定义字典的预测

  #611 opened 4 months ago by panxua
  2

• lanms python version mismatch

  #524 opened a year ago by chernobaevigor
  3

• ABINet部分算子需适配mindspore 2.0

  #491 opened 4 months ago by HaoyangLee
  2

• FceNet评估报错：IndexError: index 1 is out of bounds for axis 0 with size 1

  #544 opened 4 months ago by HustleOoo
  1

• RuntimeError: The 'getitem' operation does not support the type [None, Int64].

  #596 opened 9 months ago by sevennotmouse
  1

• 训练时评估验证集报错:

  #659 opened 4 months ago by GZ-Metal-Cell
  3

• E39999: Inner Error, Please contact support engineer!

  #615 opened 4 months ago by qulishen
  2

• requirements.txt 中的包 packaging需要加上版本号限制

  #470 opened 4 months ago by tacyi
  1

• master 解码性能问题

  #588 opened 10 months ago by jiangxiluning
  1

• CRNN自定义数据集存在与数据绑定的损失上溢 loss:65504

  #610 opened 7 months ago by panxua
  1

• mindspore 2.0 library error !!

  #499 opened 5 months ago by mohamedaliabid10
  1

• eval精度不一致问题

  #271 opened a year ago by VictorHe-1
  0

• MindOCR推理export.py时--model_name_or_config configs/det/dbnet/db++_r50_icdar15.yaml失败

  #630 opened 5 months ago by tacyi
  1

• 出现NPU报错

  #586 opened 5 months ago by meiyubin
  3

• No such file or directory: 'mindocr/utils/dict/ch_dict.txt'

  #585 opened 5 months ago by shirwy
  1

• mark一下，期待更好

  #568 opened 5 months ago by WenmuZhou
  0

• model.pretrained和model.backbone.pretrained同时生效，在多个yaml文件中需要修改

  #619 opened 7 months ago by tacyi
  1

• RuntimeError: ({'errCode': 'E80003', 'op_name': 'gather_nd', 'param_name': 'kernel_name', 'param_type': 'str', 'actual_type': 'bool'}, "In op[gather_nd], the parameter[kernel_name]'s type should be [str], but actually is [bool].")

  #595 opened 9 months ago by qq452655434
  4

• untimeError: For 'GatherNd', the indices[0]: [const vector][0, 409600], does not index into input_shape: [const vector][1, 409600].

  #536 opened a year ago by zzzzcl
  5

• FceNet算法单卡训练报错：IndexError: index 1 is out of bounds for axis 0 with size 1

  #542 opened a year ago by HustleOoo
  0

• Incorrect Evaluation Metrics for a Dataset Containing Images with No Text Instances

  #447 opened a year ago by ShahJahanIshaq
  0

• [630][Model] master模型支持

  #233 opened a year ago by HaoyangLee
  1

• Bug in det_base_postprocess.py

  #347 opened a year ago by HaoyangLee
  0

• PSENet doesn't support any input shape except 640x640 during training

  #333 opened a year ago by hadipash
  0

• [630][benchmark] 主流模型和数据benchmark测试

  #242 opened a year ago by HaoyangLee
  1

• [630][pipeline] lite推理C++/Python支持，性能达标

  #241 opened a year ago by HaoyangLee
  1

• update yolov4 and yolov8n deploy

  #296 opened a year ago by Ash-Lee233
  0

• Runtime error if number of training iterations is large on Ascend

  #281 opened a year ago by zhtmike
  3

• Got inf loss when training Chinese CRNN with fp32

  #283 opened a year ago by hqkate
  4

• [630][Model] paddle/pytorch生态模型10+推理支持

  #240 opened a year ago by HaoyangLee
  0

• [630][Data] 印章数据集（如SCID）支持

  #239 opened a year ago by HaoyangLee
  0

• [630][pipeline] E2E和表格类模型调研/支持

  #235 opened a year ago by HaoyangLee
  0

• [630][pipeline] 在线ckpt串联推理

  #238 opened a year ago by HaoyangLee
  0

• [630][Model] Sdmgr模型支持

  #234 opened a year ago by HaoyangLee
  0

• [630][Model] RobustScanner模型支持

  #232 opened a year ago by HaoyangLee
  0

• [630][Model] ABINet模型支持

  #231 opened a year ago by HaoyangLee
  0