topdu commited on
Commit
b990c80
·
verified ·
1 Parent(s): 19c2cbf

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -37,16 +37,16 @@ Download all Configs, Models, and Logs from [HuggingFace Model](https://huggingf
37
  | Model | Training Data | IC13<br/>857 | SVT | IIIT5k<br/>3000 | IC15<br/>1811 | SVTP | CUTE80 | Avg | Config&Model&Log |
38
  | :------: | :----------------------------------------------------------: | :----------: | :--: | :-------------: | :-----------: | :--: | :----: | :---: | :-----------------------------------------------------------------------: |
39
  | MDiff4STR-B | Synthetic datasets (MJ+ST) | 98.1 |95.8 |98.2| 88.1 |91.6 |96.9 |94.81| [HuggingFace Model](https://huggingface.co/topdu/MDiff4STR/tree/main/mdiff4str_base_syn) |
40
- | MDiff4STR-S | [Union14M-L-Filter](../../../docs/svtrv2.md#dataset-details) | 99.0 |98.3 |98.4 |90.2 |94.9 |97.6 |96.38 | [HuggingFace Model](https://huggingface.co/topdu/MDiff4STR/tree/main/mdiff4str_small) |
41
- | MDiff4STR-B | [Union14M-L-Filter](../../../docs/svtrv2.md#dataset-details) | 99.2 |98.3 |99.1 |91.6 |97.1 |98.6 |97.30 | [HuggingFace Model](https://huggingface.co/topdu/MDiff4STR/tree/main/mdiff4str_base) |
42
 
43
  - Test on Union14M-L benchmark from [Union14M](https://github.com/Mountchicken/Union14M/).
44
 
45
  | Model | Traing Data | Curve | Multi-<br/>Oriented | Artistic | Contextless | Salient | Multi-<br/>word | General | Avg | Config&Model&Log |
46
  | :------: | :----------------------------------------------------------: | :---: | :-----------------: | :------: | :---------: | :-----: | :-------------: | :-----: | :---: | :---------------------: |
47
  | MDiff4STR-B | Synthetic datasets (MJ+ST) | 79.8 |30.2 |64.0 |68.2 |80.8 |66.9 |67.4 |65.33| Same as the above table |
48
- | MDiff4STR-S | [Union14M-L-Filter](../../../docs/svtrv2.md#dataset-details) | 91.8 |94.0 |80.2 |85.1 |87.3 |84.8 |85.9 |87.03 | Same as the above table |
49
- | MDiff4STR-B | [Union14M-L-Filter](../../../docs/svtrv2.md#dataset-details) | 93.7 |94.4 |82.1 |86.1 |87.7 |88.3 |86.8 |88.44 | Same as the above table |
50
 
51
 
52
  - Training and test on Chinese dataset, from [Chinese Benckmark](https://github.com/FudanVI/benchmarking-chinese-text-recognition).
@@ -79,7 +79,7 @@ pip install -r requirements.txt
79
 
80
  ### Dataset Preparation
81
 
82
- Referring to [Downloading Datasets](../../../docs/svtrv2.md#downloading-datasets)
83
 
84
  ### Training
85
 
 
37
  | Model | Training Data | IC13<br/>857 | SVT | IIIT5k<br/>3000 | IC15<br/>1811 | SVTP | CUTE80 | Avg | Config&Model&Log |
38
  | :------: | :----------------------------------------------------------: | :----------: | :--: | :-------------: | :-----------: | :--: | :----: | :---: | :-----------------------------------------------------------------------: |
39
  | MDiff4STR-B | Synthetic datasets (MJ+ST) | 98.1 |95.8 |98.2| 88.1 |91.6 |96.9 |94.81| [HuggingFace Model](https://huggingface.co/topdu/MDiff4STR/tree/main/mdiff4str_base_syn) |
40
+ | MDiff4STR-S | [Union14M-L-Filter](https://github.com/Topdu/OpenOCR/blob/mdiff/docs/svtrv2.md#dataset-details) | 99.0 |98.3 |98.4 |90.2 |94.9 |97.6 |96.38 | [HuggingFace Model](https://huggingface.co/topdu/MDiff4STR/tree/main/mdiff4str_small) |
41
+ | MDiff4STR-B | [Union14M-L-Filter](https://github.com/Topdu/OpenOCR/blob/mdiff/docs/svtrv2.md#dataset-details) | 99.2 |98.3 |99.1 |91.6 |97.1 |98.6 |97.30 | [HuggingFace Model](https://huggingface.co/topdu/MDiff4STR/tree/main/mdiff4str_base) |
42
 
43
  - Test on Union14M-L benchmark from [Union14M](https://github.com/Mountchicken/Union14M/).
44
 
45
  | Model | Traing Data | Curve | Multi-<br/>Oriented | Artistic | Contextless | Salient | Multi-<br/>word | General | Avg | Config&Model&Log |
46
  | :------: | :----------------------------------------------------------: | :---: | :-----------------: | :------: | :---------: | :-----: | :-------------: | :-----: | :---: | :---------------------: |
47
  | MDiff4STR-B | Synthetic datasets (MJ+ST) | 79.8 |30.2 |64.0 |68.2 |80.8 |66.9 |67.4 |65.33| Same as the above table |
48
+ | MDiff4STR-S | [Union14M-L-Filter](https://github.com/Topdu/OpenOCR/blob/mdiff/docs/svtrv2.md#dataset-details) | 91.8 |94.0 |80.2 |85.1 |87.3 |84.8 |85.9 |87.03 | Same as the above table |
49
+ | MDiff4STR-B | [Union14M-L-Filter](https://github.com/Topdu/OpenOCR/blob/mdiff/docs/svtrv2.md#dataset-details) | 93.7 |94.4 |82.1 |86.1 |87.7 |88.3 |86.8 |88.44 | Same as the above table |
50
 
51
 
52
  - Training and test on Chinese dataset, from [Chinese Benckmark](https://github.com/FudanVI/benchmarking-chinese-text-recognition).
 
79
 
80
  ### Dataset Preparation
81
 
82
+ Referring to [Downloading Datasets](https://github.com/Topdu/OpenOCR/blob/mdiff/docs/svtrv2.md#downloading-datasets)
83
 
84
  ### Training
85