Spaces:
Sleeping
Sleeping
| Collections: | |
| - Name: SAR | |
| Metadata: | |
| Training Data: OCRDataset | |
| Training Techniques: | |
| - Adam | |
| Training Resources: 8x NVIDIA A100-SXM4-80GB | |
| Epochs: 5 | |
| Batch Size: 3072 | |
| Architecture: | |
| - ResNet31OCR | |
| - SAREncoder | |
| - ParallelSARDecoder | |
| Paper: | |
| URL: https://arxiv.org/pdf/1811.00751.pdf | |
| Title: 'Show, Attend and Read:A Simple and Strong Baseline for Irregular Text Recognition' | |
| README: configs/textrecog/sar/README.md | |
| Models: | |
| - Name: sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real | |
| Alias: SAR | |
| In Collection: SAR | |
| Config: configs/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real.py | |
| Metadata: | |
| Training Data: | |
| - ICDAR2011 | |
| - ICDAR2013 | |
| - ICDAR2015 | |
| - COCO text | |
| - IIIT5K | |
| - SynthText | |
| - SynthAdd | |
| - Syn90k | |
| Results: | |
| - Task: Text Recognition | |
| Dataset: IIIT5K | |
| Metrics: | |
| word_acc: 0.9533 | |
| - Task: Text Recognition | |
| Dataset: SVT | |
| Metrics: | |
| word_acc: 0.8841 | |
| - Task: Text Recognition | |
| Dataset: ICDAR2013 | |
| Metrics: | |
| word_acc: 0.9369 | |
| - Task: Text Recognition | |
| Dataset: ICDAR2015 | |
| Metrics: | |
| word_acc: 0.7602 | |
| - Task: Text Recognition | |
| Dataset: SVTP | |
| Metrics: | |
| word_acc: 0.8326 | |
| - Task: Text Recognition | |
| Dataset: CT80 | |
| Metrics: | |
| word_acc: 0.9028 | |
| Weights: https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real/sar_resnet31_parallel-decoder_5e_st-sub_mj-sub_sa_real_20220915_171910-04eb4e75.pth | |
| - Name: sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real | |
| In Collection: SAR | |
| Config: configs/textrecog/sar/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real.py | |
| Metadata: | |
| Training Data: | |
| - ICDAR2011 | |
| - ICDAR2013 | |
| - ICDAR2015 | |
| - COCO text | |
| - IIIT5K | |
| - SynthText | |
| - SynthAdd | |
| - Syn90k | |
| Results: | |
| - Task: Text Recognition | |
| Dataset: IIIT5K | |
| Metrics: | |
| word_acc: 0.9553 | |
| - Task: Text Recognition | |
| Dataset: SVT | |
| Metrics: | |
| word_acc: 0.8717 | |
| - Task: Text Recognition | |
| Dataset: ICDAR2013 | |
| Metrics: | |
| word_acc: 0.9409 | |
| - Task: Text Recognition | |
| Dataset: ICDAR2015 | |
| Metrics: | |
| word_acc: 0.7737 | |
| - Task: Text Recognition | |
| Dataset: SVTP | |
| Metrics: | |
| word_acc: 0.8093 | |
| - Task: Text Recognition | |
| Dataset: CT80 | |
| Metrics: | |
| word_acc: 0.8924 | |
| Weights: https://download.openmmlab.com/mmocr/textrecog/sar/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real/sar_resnet31_sequential-decoder_5e_st-sub_mj-sub_sa_real_20220915_185451-1fd6b1fc.pth | |