problem in finetune about vsepp HOT 6 CLOSED

Not necessarily. Even if the image encoder is not being trained, dropout might help in training robust embeddings.

from vsepp.

Try learning rate 0.00002. Look at section 3.2 for more details of training.

from vsepp.

Thanks for your reply!

from vsepp.

@136823xuewei Did you succeed in getting good results using raw images and finetuning rather than using precomputed features?

@fartashf I trained on the COCO dataset without precomputed features but failed to get good results (@1 less than 1.). Using precomputed features is all good.

The learning rate is 0.00002 when training on raw images.

Could someone help me?

from vsepp.

I can still reproduce the result of the following command using the latest commit on the master:

python train.py --data_name coco --logger_name runs/X --max_violation

It takes at least 1000 iterations to reach above 1% R@1 that is expected.

By default the learning rate is 0.0002. I reproduced it using python 2.7.14 and pytorch 0.3.1. For python 3 and pytorch 1 checkout the details on their corresponding branches.

from vsepp.

if we fix the image full encoder in the first epoch and train the joint embedding model, do we need to write some code to force the image cnn encoder always in evaluation mode? i.e. no dropout and ...

from vsepp.