Media-Smart/vedastr

Issues

• where is checkpoint and image path

  #92 opened 8 months ago by kavyajoshi12
  0

• Small SATRN not learning during training

  #89 opened 2 years ago by raminrahimi6970
  3

• Where is the code of CSTR?

  #91 opened 2 years ago by lc1314555
  1

• how to improve prediction for heavily rotated image and special character

  #90 opened 2 years ago by ramdhan1989
  0

• WARNING: The shape inference of prim::Constant type is missing, so it may result in wrong shape inference for the exported graph. Please consider adding it in symbolic function.

  #88 opened 2 years ago by choozhenbo
  0

• Failed to export an ONNX attribute 'onnx::Gather', since it's not constant, please try to make things (e.g., kernel size) static if possible

  #87 opened 2 years ago by choozhenbo
  1

• Vedastr communication group.

  #44 opened 4 years ago by ChaseMonsterAway
  25

• TypeError: __init__() got an unexpected keyword argument 'data_filter'

  #86 opened 2 years ago by Y-pandaman
  0

• RuntimeError: Exporting the operator grid_sampler to ONNX opset version 9 is not supported

  #85 opened 2 years ago by choozhenbo
  5

• What are the correct arguments used in openvino pytorch_to_onnx.py

  #84 opened 2 years ago by choozhenbo
  0

• TypeError: forward() takes 2 positional arguments but 3 were given

  #83 opened 2 years ago by choozhenbo
  2

• Fine-tuning with custom dataset

  #73 opened 3 years ago by chophilip21
  1

• set specific gpu_id for inference, but still use gpu 0

  #82 opened 3 years ago by Amoko
  0

• error converting model to onnx

  #81 opened 3 years ago by mrljwlm
  0

• Export model into onnx

  #68 opened 3 years ago by bharatsubedi
  3

• Pretrained model CSTR

  #80 opened 3 years ago by chuan298
  0

• what's the different between the Small-SATRN and SATRN?

  #79 opened 3 years ago by mrljwlm
  0

• Is SRN here?

  #74 opened 3 years ago by akamboj2
  1

• Integration for ABINet

  #78 opened 3 years ago by YacobBY
  0

• Can we ignore "label_input" in some models?

  #77 opened 3 years ago by GavinJiacheng
  0

• how to train the model use multi gpu on one machine?

  #76 opened 3 years ago by githublsk
  0

• OSError: image file is truncated (43 bytes not processed)

  #72 opened 3 years ago by Vietanh239
  0

• Error: __init__() got an unexpected keyword argument 'seed'

  #67 opened 3 years ago by PhamLeQuangNhat
  1

• Can't reach the score of cstr in paper

  #70 opened 3 years ago by w867066886
  7

• RuntimeError: CUDA error: device-side assert triggered

  #69 opened 3 years ago by PhamLeQuangNhat
  15

• issue when trianing my own data

  #66 opened 3 years ago by HongBo713
  6

• space and colon

  #42 opened 4 years ago by kbrajwani
  31

• When will you release the code of CSTR?

  #65 opened 3 years ago by w867066886
  1

• CSTR inference speed

  #63 opened 3 years ago by XULU42
  2

• CSTR Code

  #51 opened 3 years ago by CuongNN218
  5

• Pre trained model

  #58 opened 3 years ago by ashutoshsamal01
  1

• About Batch size

  #59 opened 3 years ago by superPangpang
  1

• CSTR process group has not been initialized

  #60 opened 3 years ago by ELDIABLO4400
  1

• Is TIA used in CSTR?

  #62 opened 3 years ago by superPangpang
  2

• I came across this mistake

  #64 opened 3 years ago by wanglibing727
  5

• training chinese dataset

  #56 opened 3 years ago by lits901
  3

• 交流群二维码过期

  #52 opened 3 years ago by yinghuozijin
  1

• Original Paper

  #53 opened 3 years ago by PrabhjotKaurGosal
  1

• What is the difference between IC15_1811 and IC15_2077？

  #55 opened 3 years ago by Brave731
  1

• Is Layer Normalization in TransformerEncoderLayer2D placed in the correct position?

  #46 opened 4 years ago by S-aiueo32
  5

• detect all words in a single image

  #50 opened 4 years ago by Auth0rM0rgan
  0

• Question about "GResNet" and "collect"

  #49 opened 4 years ago by AndiezPham
  2

• Why not use this data format？

  #48 opened 4 years ago by liuzhuang1024
  1

• Pretrained model

  #47 opened 4 years ago by jdavidd
  0

• Model performance issues

  #45 opened 4 years ago by duxiangcheng
  1

• I use your tps-resnet-bilstm-attn code to train my handwriten data，the acc is 0.729;if I use the tps-resnet-bilstm-attn code of deep-text-recognition-benchmark,the acc is 0.805.Meanwhile,the acc of small_satrn is only 0.09

  #43 opened 4 years ago by SeanLiu081
  10

• How to fine tuning with different character length

  #40 opened 4 years ago by chuan298
  15

• How to train with pretrained model

  #39 opened 4 years ago by chuan298
  1

• What is the mean of best_edit and edit parameters？

  #38 opened 4 years ago by Wzj02200059
  3

• Train with my own dataset

  #37 opened 4 years ago by CuongNN218
  1