|
Collections: |
|
- Name: CRNN |
|
Metadata: |
|
Training Data: OCRDataset |
|
Training Techniques: |
|
- Adadelta |
|
Epochs: 5 |
|
Batch Size: 256 |
|
Training Resources: 4x GeForce GTX 1080 Ti |
|
Architecture: |
|
- VeryDeepVgg |
|
- CRNNDecoder |
|
Paper: |
|
URL: https://arxiv.org/pdf/1507.05717.pdf |
|
Title: 'An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition' |
|
README: configs/textrecog/crnn/README.md |
|
|
|
Models: |
|
- Name: crnn_academic_dataset |
|
In Collection: CRNN |
|
Config: configs/textrecog/crnn/crnn_academic_dataset.py |
|
Metadata: |
|
Training Data: Syn90k |
|
Results: |
|
- Task: Text Recognition |
|
Dataset: IIIT5K |
|
Metrics: |
|
word_acc: 80.5 |
|
- Task: Text Recognition |
|
Dataset: SVT |
|
Metrics: |
|
word_acc: 81.5 |
|
- Task: Text Recognition |
|
Dataset: ICDAR2013 |
|
Metrics: |
|
word_acc: 86.5 |
|
Weights: https://download.openmmlab.com/mmocr/textrecog/crnn/crnn_academic-a723a1c5.pth |
|
|