search

ucbdrive / hd3

Code for Hierarchical Discrete Distribution Decomposition for Match Density Estimation (CVPR 2019)
BSD 3-Clause "New" or "Revised" License
204 stars 31 forks source link

encoder probelm in the train.py #13

Closed bbidong closed 5 years ago

bbidong commented 5 years ago

Hi, in the model training, we need to initialize the weights from a pretrained model via --pretrain , if the encoder is dla, i can obtain pretrained model by download_models.sh in the model zoo. But if I want to train a new model whose encoder is vgg, there is not pretrained model in model zoo , and what should I do ??

yzcjtr commented 5 years ago

Just randomly initialize the model weights. I think there wouldn't be significant differences in terms of the final performance. Or you can find a pretrained VGG model elsewhere and write your customized vgg.py which is compatible with that model.