Is it still possible to use the text encoder to generate a vector from sentence ?

[AtiChetsurakul]

I would Like to ask that are there a way to access to the text encoder for this model or I can just simply use the encoder directly from CLIP at the same Model type. BTW, I am so sory for creating an issue; It quite confuse to find your text encoder in the code.

[AtiChetsurakul]

Another question kurb, If I would like the use the MSMT weight to test on the other dataset (EG market1501) can I just manually make the model like this?

with the cfg dataset seting on Market-1501

• Running script CUDA_VISIBLE_DEVICES=0 python test_clipreid.py --config_file configs/person/vit_clipreid.yml TEST.WEIGHT 'MSMT_weight_ViT-B-16_60.pth'

  • Starting at Line 41

    
    train_loader, train_loader_normal, val_loader, num_query, num_classes, camera_num, view_num = make_dataloader(cfg)

  model = make_model(cfg, num_class=1041, camera_num=15, view_num = view_num) model.load_param(cfg.TEST.WEIGHT)