mirror of
https://github.com/open-mmlab/mmocr.git
synced 2025-06-03 21:54:47 +08:00
0a1787d6bc
* base refactor * update config * modify implementation of nrtr * add config file * add mask * add operation order * fix contiguous bug * update config * fix pytest * fix pytest * update readme * update readme and metafile * update docstring * fix norm cfg and dict size * rm useless * use mmocr builder instead * update pytest * update * remove useless * fix ckpt name * fix path * include all config file into pytest * update inference * Update test_recog_config.py
87 lines
2.2 KiB
YAML
87 lines
2.2 KiB
YAML
Collections:
|
|
- Name: NRTR
|
|
Metadata:
|
|
Training Data: OCRDataset
|
|
Training Techniques:
|
|
- Adam
|
|
Epochs: 6
|
|
Batch Size: 6144
|
|
Training Resources: 48x GeForce GTX 1080 Ti
|
|
Architecture:
|
|
- CNN
|
|
- NRTREncoder
|
|
- NRTRDecoder
|
|
Paper:
|
|
URL: https://arxiv.org/pdf/1806.00926.pdf
|
|
Title: 'NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition'
|
|
README: configs/textrecog/nrtr/README.md
|
|
|
|
Models:
|
|
- Name: nrtr_r31_1by16_1by8_academic
|
|
In Collection: NRTR
|
|
Config: configs/textrecog/nrtr/nrtr_r31_1by16_1by8_academic.py
|
|
Metadata:
|
|
Training Data:
|
|
- SynthText
|
|
- Syn90k
|
|
Results:
|
|
- Task: Text Recognition
|
|
Dataset: IIIT5K
|
|
Metrics:
|
|
word_acc: 94.7
|
|
- Task: Text Recognition
|
|
Dataset: SVT
|
|
Metrics:
|
|
word_acc: 87.3
|
|
- Task: Text Recognition
|
|
Dataset: ICDAR2013
|
|
Metrics:
|
|
word_acc: 94.3
|
|
- Task: Text Recognition
|
|
Dataset: ICDAR2015
|
|
Metrics:
|
|
word_acc: 73.5
|
|
- Task: Text Recognition
|
|
Dataset: SVTP
|
|
Metrics:
|
|
word_acc: 78.9
|
|
- Task: Text Recognition
|
|
Dataset: CT80
|
|
Metrics:
|
|
word_acc: 85.1
|
|
Weights: https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_r31_1by16_1by8_academic_20211124-f60cebf4.pth
|
|
|
|
- Name: nrtr_r31_1by8_1by4_academic
|
|
In Collection: NRTR
|
|
Config: configs/textrecog/nrtr/nrtr_r31_1by8_1by4_academic.py
|
|
Metadata:
|
|
Training Data:
|
|
- SynthText
|
|
- Syn90k
|
|
Results:
|
|
- Task: Text Recognition
|
|
Dataset: IIIT5K
|
|
Metrics:
|
|
word_acc: 95.2
|
|
- Task: Text Recognition
|
|
Dataset: SVT
|
|
Metrics:
|
|
word_acc: 90.0
|
|
- Task: Text Recognition
|
|
Dataset: ICDAR2013
|
|
Metrics:
|
|
word_acc: 94.0
|
|
- Task: Text Recognition
|
|
Dataset: ICDAR2015
|
|
Metrics:
|
|
word_acc: 74.1
|
|
- Task: Text Recognition
|
|
Dataset: SVTP
|
|
Metrics:
|
|
word_acc: 79.4
|
|
- Task: Text Recognition
|
|
Dataset: CT80
|
|
Metrics:
|
|
word_acc: 88.2
|
|
Weights: https://download.openmmlab.com/mmocr/textrecog/nrtr/nrtr_r31_1by8_1by4_academic_20211123-e1fdb322.pth
|