pix2text-mfr / README.md
breezedeus's picture
Update README.md
d4fb5d6 verified
|
raw
history blame
3.42 kB
---
tags:
- latex-ocr
- math-ocr
- math-formula-recognition
- mfr
- pix2text
- image-to-text
license: mit
library_name: transformers
---
# Model Card: Pix2Text-MFR
Math Formula Recognition (MFR) model from [Pix2Text (P2T)]().
## Model Details / 模型细节
This model is fine-tuned on a coin dataset using **contrastive learning** techniques, based on OpenAI's CLIP (ViT-B/32). It aims to enhance the feature extraction capabilities for **Coin** images, thus achieving more accurate image-based search functionalities. The model combines the powerful features of the Vision Transformer (ViT) with the multimodal learning capabilities of CLIP, specifically optimized for coin imagery.
这个模型是在 OpenAI 的 CLIP (ViT-B/32) 基础上,利用对比学习技术并使用硬币数据集进行微调得到的。它旨在提高硬币图像的特征提取能力,从而实现更准确的以图搜图功能。该模型结合了视觉变换器(ViT)的强大功能和 CLIP 的多模态学习能力,专门针对硬币图像进行了优化。
## Usage and Limitations / 使用和限制
- **Usage**: This model is primarily used for extracting representation vectors from coin images, enabling efficient and precise image-based searches in a coin image database.
- **Limitations**: As the model is trained specifically on coin images, it may not perform well on non-coin images.
- **用途**:此模型主要用于提取硬币图片的表示向量,以实现在硬币图像库中进行高效、精确的以图搜图。
- **限制**:由于模型是针对硬币图像进行训练的,因此在处理非硬币图像时可能效果不佳。
## Documents / 文档
- Base Model: [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32)
## Model Use / 模型使用
```python3
from PIL import Image
import requests
from transformers import CLIPProcessor, CLIPModel
model = CLIPModel.from_pretrained("breezedeus/coin-clip-vit-base-patch32")
processor = CLIPProcessor.from_pretrained("breezedeus/coin-clip-vit-base-patch32")
image_fp = "path/to/coin_image.jpg"
image = Image.open(image_fp).convert("RGB")
inputs = processor(images=image, return_tensors="pt")
img_features = model.get_image_features(**inputs)
img_features = F.normalize(img_features, dim=1)
```
## Training Data / 训练数据
The model was trained on a specialized coin image dataset. This dataset includes images of various currencies' coins.
本模型使用的是专门的硬币图像数据集进行训练。这个数据集包含了多种货币的硬币图片。
## Training Process / 训练过程
The model was fine-tuned on the OpenAI CLIP (ViT-B/32) pretrained model using a coin image dataset. The training process involved Contrastive Learning fine-tuning techniques and parameter settings.
模型是在 OpenAI 的 CLIP (ViT-B/32) 预训练模型的基础上,使用硬币图像数据集进行微调。训练过程采用了对比学习的微调技巧和参数设置。
## Performance / 性能
This model demonstrates excellent performance in coin image retrieval tasks.
该模型在硬币图像检索任务上展现了优异的性能。
## Feedback / 反馈
> Where to send questions or comments about the model.
Welcome to contact the author [Breezedeus](https://www.breezedeus.com/join-group).
欢迎联系作者 [Breezedeus](https://www.breezedeus.com/join-group) 。