Keras-Image-Embeddings-using-Contrastive-Loss

Image to Embedding projection in multi-dimentional vector space.
Implementation in keras and tensorflow for custom data.
Batch all triplet loss for one-shot/few-shot learning.
Triplet is generated for One-shot learning using augmentation between anchor and positive.

Requirements:

tensorflow = 2.4.1,
tensorflow-gpu = 2.4.1,
Keras = 2.2.4,
imgaug = 0.4.0,
numpy >= 1.19.5,
pandas >= 1.1.3,
opencv-contrib-python >= 4.5.1.48,
opencv-python >= 4.4.0.44

GitHub

View Github