OCR-SAM icon indicating copy to clipboard operation
OCR-SAM copied to clipboard

Combining MMOCR with Segment Anything & Stable Diffusion. Automatically detect, recognize and segment text instances, with serval downstream tasks, e.g., Text Removal and Text Inpainting

Results 10 OCR-SAM issues
Sort by recently updated
recently updated
newest added

作者,您好! 请问一下,方便告诉我OCR-SAM中Erasing:DBNet++ + SAM + Latent-Diffusion / Stable Diffusion这部分模型预训练权重所使用的训练数据吗?只需要知道出处即可,谢谢您!

Consider a document ocr combined with llm?

![1759a3ae3d494825b6801711e1c69cd](https://github.com/yeungchenwa/OCR-SAM/assets/92440323/29ca4a12-e4cc-46bc-8750-c710f4582dbd) ![2925c3878e0c55d0b0849bbd3f2e7de](https://github.com/yeungchenwa/OCR-SAM/assets/92440323/9214e23f-cc5e-492f-92b0-abf3be042acd) ![939360a417a0a62a095f4d94fe3073a](https://github.com/yeungchenwa/OCR-SAM/assets/92440323/e0c6e20d-8c16-4caa-b006-6e0d5f002f2b) when following the operations: (ocr-sam) PS D:\Python\text_removal\OCR-SAM> python mmocr_sam_inpainting.py ` >> --img_path "D:\Python\text_removal\OCR-SAM\image_test\images_in\13196_4.jpg" ` >> --outdir "D:\Python\text_removal\OCR-SAM\image_test\images_out" ` >> --device cuda ` >> --sam_checkpoint "D:\Python\text_removal\OCR-SAM\checkpoints\sam\sam_vit_h_4b8939.pth" ` >>...

如何将模型部署在mac上面,目前尝试这方面工作,将SAM-StableDiffusion+文本检测/文本识别模型部署在mac。

This project appears to include StableDiffusion's WebUI. However, I would like to use the latest version of the WebUI. Is there a separate way to port only the core functionality...

why the picture is blurry after erasing origin picture ![image](https://github.com/yeungchenwa/OCR-SAM/assets/138200513/43de6f11-564a-4ab2-9d2b-1ae076539cc3) erasied pic ![image](https://github.com/yeungchenwa/OCR-SAM/assets/138200513/64b7bb54-8efc-414c-9153-860fa2d6fc10)

Hi, We are unable to scale from 1024, even when loading a bigger GPU MEM, we get OOM. Is this solveable? Thank you

非常感谢您的分享! 请问本项目中的OCR是case sensitive的吗?

请问一下,SAM for Text文本检测部分的预训练权重的训练数据可以说一下出处和大概的训练细节吗? 感谢解答,谢谢!