roatienza deep-text-recognition-benchmark issues

roatienza / deep-text-recognition-benchmark

PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)

Apache License 2.0

293 stars 59 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

error in custom data

#45 MahmoudElsayedMahmoud opened 1 month ago
2
Predict `model.pth`

#44 minhduc01168 opened 1 month ago
2
Onnx conversion code trained model

#43 Shivashankarar opened 6 months ago
0
Update train.py

#42 casperthuis opened 7 months ago
0
About Training time.

#41 DemissieDaniel closed 7 months ago
0
timm==0.4.5 ModuleNotFoundError: No module named 'timm.models.layers.patch_embed'

#40 sh1man closed 11 months ago
1
Requirement Patch: Update torchvision Version in requirements.txt

#39 wodeyuzhou closed 1 year ago
1
Train loss is 0.0000 at every iteration

#38 Ashish0091 opened 1 year ago
1
About the speed of the model in Table 4 of the paper

#37 lexiaoyuan closed 1 year ago
4
Available Model weights.

#36 schreiterjp opened 1 year ago
1
ONNX

#35 centurions opened 2 years ago
2
CTC error

#34 LeeBronOff23 opened 2 years ago
1
continue to train

#33 LeeBronOff23 opened 2 years ago
0
train error

#32 chungluensing opened 2 years ago
1
Rand Aug

#31 fmobrj opened 2 years ago
1
quantification

#30 centurions opened 2 years ago
0
pretrained-model loading with errors

#29 Ao-Lee closed 2 years ago
12
about input channels of vitstr

#28 Name-Lessx opened 2 years ago
1
when i follow train.sh: line 6: --SequenceModeling: command not found

#27 felix115 opened 2 years ago
1
Question about [GO] and [s]

#26 sparrow0629 closed 2 years ago
1
How to calculate Top-5 accuracy?

#25 penghusile opened 2 years ago
0
How to draw the attention map of ViTSTR?

#24 lexiaoyuan closed 2 years ago
1
Code refactoring(model.py, dataset.py) and add backslash to commands in README.md

#23 oikosohn closed 2 years ago
0
Code refactoring for dataset.py and dataset.py.

#22 oikosohn closed 2 years ago
0
CUDA out of memory.

#21 penghusile opened 2 years ago
1
Poor performance on some images

#20 dudeperf3ct closed 3 years ago
1
A question about [GO[ token

#19 zhaiyukun closed 3 years ago
2
Demo.py

#18 Preethse opened 3 years ago
3
Did you compare the result of CTC loss and cross entropy loss ?

#17 Jiakui opened 3 years ago
0
About the parameter `--valid_data` in the training command mentioned in README.md

#16 lexiaoyuan closed 2 years ago
1
About input size

#15 terryoo closed 3 years ago
2
Is there any performance comparison with clovaai/deep-text-recognition-benchmark

#14 LLC opened 3 years ago
1
why don't you normalize the images?

#13 cuongdxk57 opened 3 years ago
3
Update test.py

#12 engincindoruk closed 3 years ago
0
model state loading issue

#11 rouarouatbi closed 3 years ago
3
Training on Japanese data

#10 Preethse closed 3 years ago
4
about ACC

#9 YuNaruto opened 3 years ago
2
I have a question

#8 daeing opened 3 years ago
9
Training from scratch, w/o using Pretrained DeiT?

#7 mandal4 opened 3 years ago
3
Is the network suit for long-text recognition?

#6 WudiJoey opened 3 years ago
6
a question about ViTSTR

#5 Danee-wawawa opened 3 years ago
2
What is the meaning of 'delta' in plot_error.py? Is it the subtraction between previous model and ViTSTR-Base?

#4 huihui0000 opened 3 years ago
4
About the difference between the number of training iters in the paper and this Repo

#3 superPangpang closed 3 years ago
3
AttributeError: 'NoneType' object has no attribute 'eval'

#2 momei123 closed 3 years ago
1
Trained model?

#1 zobeirraisi closed 3 years ago
1