Update README.md
Browse files
README.md
CHANGED
|
@@ -45,20 +45,19 @@ resources/
|
|
| 45 |
|
| 46 |
</pre>
|
| 47 |
|
| 48 |
-
## 📘 ⚠️Manual download required⚠️
|
| 49 |
- `resources/weight/ocr/solo.pth`
|
| 50 |
-
- Please download this weight from the official [Deeosolo](https://github.com/ViTAE-Transformer/DeepSolo) implementation.
|
| 51 |
-
|
| 52 |
- `resources/weight/ocr/masktextspotterv3.pth`
|
| 53 |
-
- Please download this weight from the official [MaskTextSpotterV3](https://github.com/MhLiao/MaskTextSpotterV3) implementation.
|
| 54 |
-
[[link](https://drive.google.com/file/d/1XQsikiNY7ILgZvmvOeUf9oPDG4fTp0zs/view)]
|
| 55 |
- `resources/data/arial_unicode_ms.ttf`
|
| 56 |
- Since the Arial font cannot be redistributed, please obtain it through your operating system or another legal source. As an alternative, you may use an open font such as Liberation Sans (resources/data/LiberationSans-Regular.ttf). However, please note that we have observed a drop of 1–2 points in OCR accuracy on the Mario-Eval benchmark when using AnyText with Liberation Sans under our best configuration.
|
| 57 |
|
| 58 |
## 📘 Dataset details
|
| 59 |
|
| 60 |
- `weight/`
|
| 61 |
-
-
|
| 62 |
- **ocr/**: Models for OCR detection/recognition.
|
| 63 |
- **text_eraser/**: Inpainting or erasure modules for removing text.
|
| 64 |
- **text_editor/**: Models for rendering text into images.
|
|
@@ -67,7 +66,7 @@ resources/
|
|
| 67 |
|
| 68 |
|
| 69 |
- `data/marioevalbench/`
|
| 70 |
-
- The dataset containing prompts and reference images for evaluating Type-R
|
| 71 |
- **hfds/**: includes prompts, augmented prompts, and images of the Mario-Eval Benchmark
|
| 72 |
|
| 73 |
|
|
|
|
| 45 |
|
| 46 |
</pre>
|
| 47 |
|
| 48 |
+
## 📘 ⚠️Manual download required data⚠️
|
| 49 |
- `resources/weight/ocr/solo.pth`
|
| 50 |
+
- Please download this weight from the official [Deeosolo](https://github.com/ViTAE-Transformer/DeepSolo) implementation.[[link](https://onedrive.live.com/?redeem=aHR0cHM6Ly8xZHJ2Lm1zL3UvcyFBaW1CZ1lWN0pqVGxnY2Q5d2k0MzJ1aXRNZ1RNLXc%5FZT1manVKYm0&cid=E534267B85818129&id=E534267B85818129%2125597&parId=E534267B85818129%2125575&o=OneUp)]
|
| 51 |
+
- This weight has ViTAEv2-S as its backbone and is trained on `Synth150K+Total-Text+MLT17+IC13+IC15+TextOCR`.
|
| 52 |
- `resources/weight/ocr/masktextspotterv3.pth`
|
| 53 |
+
- Please download this weight from the official [MaskTextSpotterV3](https://github.com/MhLiao/MaskTextSpotterV3) implementation. [[link](https://drive.google.com/file/d/1XQsikiNY7ILgZvmvOeUf9oPDG4fTp0zs/view)]
|
|
|
|
| 54 |
- `resources/data/arial_unicode_ms.ttf`
|
| 55 |
- Since the Arial font cannot be redistributed, please obtain it through your operating system or another legal source. As an alternative, you may use an open font such as Liberation Sans (resources/data/LiberationSans-Regular.ttf). However, please note that we have observed a drop of 1–2 points in OCR accuracy on the Mario-Eval benchmark when using AnyText with Liberation Sans under our best configuration.
|
| 56 |
|
| 57 |
## 📘 Dataset details
|
| 58 |
|
| 59 |
- `weight/`
|
| 60 |
+
- This dicrectory contains pretrained weights used for various modules in the Type-R pipeline
|
| 61 |
- **ocr/**: Models for OCR detection/recognition.
|
| 62 |
- **text_eraser/**: Inpainting or erasure modules for removing text.
|
| 63 |
- **text_editor/**: Models for rendering text into images.
|
|
|
|
| 66 |
|
| 67 |
|
| 68 |
- `data/marioevalbench/`
|
| 69 |
+
- The dataset containing prompts and reference images for evaluating Type-R
|
| 70 |
- **hfds/**: includes prompts, augmented prompts, and images of the Mario-Eval Benchmark
|
| 71 |
|
| 72 |
|