Timeline for Siamese networks vs Semantic similarity (may be gensim)
Current License: CC BY-SA 4.0
3 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 24, 2019 at 14:44 | comment | added | Sandeep Bhutani | 1. This is my main question. In this example (kaggle.com/arpandhatt/siamese-neural-networks), the last dense network is trained on new images and passed through sigmoid to get 0 or 1. Rather than that if these 2 vectors difference is taken directly will that not work? (i.e, L1_layer = Lambda(lambda tensor:K.abs(tensor[0] - tensor[1])) .. can this not be used raw rahter than feeding to dense layer) 2. instead of taking 2 networks, can we take just 1 network and pass the 2 inputs one by one? And then calculate the difference? | |
| Oct 23, 2019 at 9:30 | review | First posts | |||
| Oct 23, 2019 at 9:56 | |||||
| Oct 23, 2019 at 9:26 | history | answered | Saandeep Sreerambatla | CC BY-SA 4.0 |