search

zhang-pengyu / ADRNet

code and results for 'Learning Adaptive Attribute-Driven Representation for Real-Time RGB-T Tracking'
45 stars 4 forks source link

How to multi-step train the model? #6

Open Tianlu-Zhang opened 3 years ago

Tianlu-Zhang commented 3 years ago

In the paper, this model adopts a multi-step training strategy, which consists of three steps. But I can't find how to use train_ADRNet.py for multi-step training? Could you give me some suggestions?

zhang-pengyu commented 3 years ago

Sorry for late response. The code cannot conduct multi-step training automatically. You can manually set the corresponding datasets and updated layers in train_ADRNet.py. I will also refine the code to support the training strategy step by step.

DZSYUNNAN commented 2 years ago

How can I manually set up the corresponding dataset and updated layers?

zhang-pengyu commented 2 years ago

@DZSYUNNAN The update layer can be set in train_ADRNet.py line249 (ft_layers) and the custom dataset path can be added in line 36 with the instruction of attribute-specific dataset generation. In model.py Line 347 - 545 provide various types of network loading method.