zyang-ur / onestage_grounding

A Fast and Accurate One-Stage Approach to Visual Grounding, ICCV 2019 (Oral)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Dear author, during loading your trained model, what is the cause of the error? Looking forward to your reply!

lwj01 opened this issue · comments

model_path = r'../saved_models/lstm_flickr_model.pth'

model = grounding_model.grounding_model(dataset='xxx')

state_dict = model.load_state_dict(torch.load(model_path)['state_dict'])

报错:
Missing key(s) in state_dict: "visumodel.module_list.0.conv_0.weight", "visumodel.module_list.0.batch_norm_0.weight", "visumodel.module_list.0.batch_norm_0.bias", ...
Unexpected key(s) in state_dict: "module.visumodel.module_list.0.conv_0.weight", "module.visumodel.module_list.0.batch_norm_0.weight",....