DeepImageSearch

Changelogs:

• The entire code has been updated. Now you have the option to choose from over 500 feature extraction models, including ViT (Vision Transformers).
• Annoy has been removed due to indexing restrictions.
• FAISS is now being used for faster indexing and reindexing of new images.
• Various major issues have been fixed.
• The documentation has been updated.
• GPU support has been added.

DeepImageSearch

Changelog:

• Removed the TensorFlow codebase and added Torchvision for improved performance and ease of use.
• Replaced the VGG16 model with the VIT model for feature extraction, resulting in improved accuracy and faster processing times.
• Updated "plot_similar_images" function to allow users to specify how many similar images they want to print and also to print the input image.
• Fixed bugs that were causing errors in certain edge cases.
• Updated README.md file to reflect the changes made and to provide more comprehensive documentation.

DeepImageSearch

v_14

Update setup.py

DeepImageSearch

v_13

Update README.md

DeepImageSearch

v_12

Update README.md

DeepImageSearch

v_11

Update setup.py

DeepImageSearch

v_10

Update setup.py

DeepImageSearch

v_05

Update README.md