| | --- |
| | tags: |
| | - image-classification |
| | - timm |
| | - chart |
| | - charts |
| | - fintwit |
| | - stocks |
| | - crypto |
| | library_name: timm |
| | license: mit |
| | datasets: |
| | - StephanAkkerman/crypto-charts |
| | - StephanAkkerman/stock-charts |
| | - StephanAkkerman/fintwit-images |
| | language: |
| | - en |
| | metrics: |
| | - accuracy |
| | - f1 |
| | - precision |
| | - recall |
| | pipeline_tag: image-classification |
| | base_model: timm/efficientnet_b0.ra_in1k |
| | --- |
| | # Chart Recognizer |
| |
|
| | chart-recognizer is a finetuned model for classifying images. It uses efficientnet as its base model, making it a fast and small model. |
| | This model is trained on my own dataset of financial charts posted on Twitter, which can be found here [StephanAkkerman/fintwit-charts](https://huggingface.co/datasets/StephanAkkerman/fintwit-charts). |
| |
|
| | ## Intended Uses |
| |
|
| | chart-recognizer is intended for classifying images, mainly images posted on social media. |
| |
|
| | ## Dataset |
| |
|
| | chart-recognizer has been trained on my own dataset. So far I have not been able to find another image dataset about financial charts. |
| | - [StephanAkkerman/crypto-charts](https://huggingface.co/datasets/StephanAkkerman/crypto-charts): 4,880 images. |
| | - [StephanAkkerman/stock-charts](https://huggingface.co/datasets/StephanAkkerman/stock-charts): 5,203 images. |
| | - [StephanAkkerman/fintwit-images](https://huggingface.co/datasets/StephanAkkerman/fintwit-images): 4,579 images. |
| |
|
| | ## More Information |
| |
|
| | For a comprehensive overview, including the training setup and analysis of the model, visit the [chart-recognizer GitHub repository](https://github.com/StephanAkkerman/chart-recognizer). |
| |
|
| | ## Usage |
| |
|
| | Using [HuggingFace's transformers library](https://huggingface.co/docs/transformers/index) the model can be converted into a pipeline for image classification. |
| |
|
| | ```python |
| | from transformers import pipeline |
| | |
| | # Create a sentiment analysis pipeline |
| | pipe = pipeline( |
| | "image-classification", |
| | model="StephanAkkerman/chart-recognizer", |
| | ) |
| | |
| | # Get the predicted sentiment |
| | print(pipe(image)) |
| | ``` |
| |
|
| | ## Citing & Authors |
| |
|
| | If you use chart-recognizer in your research, please cite me as follows: |
| |
|
| | ``` |
| | @misc{chart-recognizer, |
| | author = {Stephan Akkerman}, |
| | title = {chart-recognizer: A Specialized Image Model for Financial Charts}, |
| | year = {2024}, |
| | publisher = {GitHub}, |
| | journal = {GitHub repository}, |
| | howpublished = {\url{https://github.com/StephanAkkerman/chart-recognizer}} |
| | } |
| | ``` |
| |
|
| | ## License |
| |
|
| | This project is licensed under the MIT License. See the [LICENSE](https://choosealicense.com/licenses/mit/) file for details. |
