An open API service indexing awesome lists of open source software.

https://github.com/robmarkcole/artist-classification-with-ml

Train an "off-the-shelf" deep image network with color images of Impressionist paintings from the web (Seurat, Signac, Monet, Degas, Renoir, ...) for classification of both artist and simple subject matter
https://github.com/robmarkcole/artist-classification-with-ml

Last synced: about 1 year ago
JSON representation

Train an "off-the-shelf" deep image network with color images of Impressionist paintings from the web (Seurat, Signac, Monet, Degas, Renoir, ...) for classification of both artist and simple subject matter

Awesome Lists containing this project

README

          

# artist-classification-with-ML
Goal: Train an "off-the-shelf" deep image network with color images of Impressionist paintings from the web (Seurat, Signac, Monet, Degas, Renoir, ...) for classification of both artist and simple subject matter (as conveyed by titles). Examine the internal representations and perform statistical tests to see if artists are "best" recognized by low-level features (color, brush stroke, "style") or high-level representations (subjects). (I and I'm sure others are eager to see the net's internal representations for art.)

## Datasets
* https://www.kaggle.com/ikarus777/best-artworks-of-all-time

## References
* [IBM article](https://developer.ibm.com/patterns/classify-art-using-tensorflow-model/) and [code](https://github.com/IBM/tensorflow-kubernetes-art-classification)
* https://magenta.tensorflow.org/ -> An open source research project exploring the role of machine learning as a tool in the creative process. Mostly music focus?
* [Article: Neural Style Transfer: Creating Art with Deep Learning using tf.keras and eager execution](https://medium.com/tensorflow/neural-style-transfer-creating-art-with-deep-learning-using-tf-keras-and-eager-execution-7d541ac31398)