Releasing the model on torch.hub?

[gmberton]

Hi @amaralibey! I'm finding your model quite useful for a number of projects, but it's always a bit cumbersome to insert the model's code into other codebases. It would be very useful if the model was on torch.hub, have you considered releasing it there? It is quite simple to do and allows people to use your model with two lines of code, allowing more people to use your model and helping to spread your work!

For example I did it for CosPlace, and the trained models can be automatically downloaded from anywhere without cloning the repo or importing the model just like this

import torch
model = torch.hub.load("gmberton/cosplace", "get_trained_model", backbone="ResNet50", fc_output_dim=2048)

[jarvisyjw]

Hi, I created a fork and you can load the model with the best performance resnet50_MixVPR_4096_channels(1024)_rows(4).ckpt

import torch
model = torch.hub.load("jarvisyjw/MixVPR", 'get_trained_model', pretrained=True)

[gmberton]

This is great, thank you @jarvisyjw !