Open Arjunvankani opened 1 year ago
Hello,
I think you missunderstood the goal of this package. This package is for "person-reid" - person re-identification. Therefore using visual Neural-Nets to compress information about people and re-identifying those in unseen data.
LSTM and RNN are mostly used for language and other sequence based models, even though not only. If you want to use a recurrent model on the generated re-ids you can simply use default pytorch models on the returned re-id vectors/embeddings, according to your likings.
Iff you have an Idea of using RNNs for reid, feel free to add a code draft or paper, perhaps someone can help you implement it.
Here I found many codes like resnet18, inception, and OSNET, i am requesting you LSTM and RNN be very popular nowadays, they can achieve good accuracy, could you make a code for that??