All Projects → sanku-lib → image_triplet_loss

sanku-lib / image_triplet_loss

Licence: other
Image similarity using Triplet Loss

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to image triplet loss

finetuner
Finetuning any DNN for better embedding on neural search tasks
Stars: ✭ 442 (+481.58%)
Mutual labels:  triplet-loss, siamese-network
pytorch-siamese-triplet
One-Shot Learning with Triplet CNNs in Pytorch
Stars: ✭ 74 (-2.63%)
Mutual labels:  triplet-loss, siamese-network
Siamese Triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
Stars: ✭ 2,564 (+3273.68%)
Mutual labels:  triplet-loss, siamese-network
Signature-verification-using-deep-learning
Using SigComp'11 dataset for signature verification
Stars: ✭ 54 (-28.95%)
Mutual labels:  triplet-loss, siamese-network
TorchBlocks
A PyTorch-based toolkit for natural language processing
Stars: ✭ 85 (+11.84%)
Mutual labels:  triplet-loss, siamese-network
triplet-loss-pytorch
Highly efficient PyTorch version of the Semi-hard Triplet loss ⚡️
Stars: ✭ 79 (+3.95%)
Mutual labels:  triplet-loss
Siamese-Recurrent-Architectures
Usage of Siamese Recurrent Neural network architectures for semantic textual similarity
Stars: ✭ 19 (-75%)
Mutual labels:  siamese-network
FaceRecog
Realtime Facial recognition system using Siamese neural network
Stars: ✭ 47 (-38.16%)
Mutual labels:  siamese-network
one-shot-steel-surfaces
One-Shot Recognition of Manufacturing Defects in Steel Surfaces
Stars: ✭ 29 (-61.84%)
Mutual labels:  siamese-network
farm-animal-tracking
Farm Animal Tracking (FAT)
Stars: ✭ 19 (-75%)
Mutual labels:  siamese-network
Offline-Signature-Verification
Implemented two papers for offline signature verification. Both use different deep learning techniques - Convolutional network and Siamese network.
Stars: ✭ 24 (-68.42%)
Mutual labels:  siamese-network
RankNet
Learning to Rank from Pair-wise data
Stars: ✭ 40 (-47.37%)
Mutual labels:  siamese-network
img classification deep learning
No description or website provided.
Stars: ✭ 19 (-75%)
Mutual labels:  image-similarity
MHCLN
Deep Metric and Hash Code Learning Network for Content Based Retrieval of Remote Sensing Images
Stars: ✭ 30 (-60.53%)
Mutual labels:  triplet-loss
EfficientWord-Net
OneShot Learning-based hotword detection.
Stars: ✭ 78 (+2.63%)
Mutual labels:  siamese-network
facenet-pytorch-glint360k
A PyTorch implementation of the 'FaceNet' paper for training a facial recognition model with Triplet Loss using the glint360k dataset. A pre-trained model using Triplet Loss is available for download.
Stars: ✭ 186 (+144.74%)
Mutual labels:  triplet-loss
image-similarity-using-deep-ranking
🖼️ 𝖀𝖓𝖔𝖋𝖋𝖎𝖈𝖎𝖆𝖑 PyTorch implementation of "Learning Fine-grained Image Similarity with Deep Ranking" (arXiv:1404.4661)
Stars: ✭ 130 (+71.05%)
Mutual labels:  image-similarity
Facial-Recognition-Using-FaceNet-Siamese-One-Shot-Learning
Implementation of Facial Recognition System Using Facenet based on One Shot Learning Using Siamese Networks
Stars: ✭ 104 (+36.84%)
Mutual labels:  siamese-network
street2shopTriplet
Challenge the customer to shop task with tripletNet
Stars: ✭ 14 (-81.58%)
Mutual labels:  triplet-loss
One-Shot-Learning-with-Siamese-Networks
Implementation of One Shot Learning using Convolutional Siamese Networks on Omniglot Dataset
Stars: ✭ 129 (+69.74%)
Mutual labels:  siamese-network

Triplet Loss for Image Similarity using tensorflow

This repository is an implementation of following "medium" story: Image similarity using Triplet Loss

Requirements

  • Python 3
  • Pip 3
  • Tensorflow
  • Matplotlib
  • Requests

Environment Setup

Execute requirements.txt to install dependency packages

pip install -r requirements.txt

Training

  1. Download Training Dataset by executing download_dataset.py
python download_dataset.py
  1. To train
python train_triplets.py 

Prediction

Run Prediction.ipynb using Jupyter notebook to look into Prediction code.

Prediction.ipynb
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].