Olivier Valery
Olivier Valery
First, you hardware configuration seems quite good. When we work with any 3d network, it is important. For the training configuration, I remember that I used 3 GPU, so it...
do not include this layer in the module you restore via model.load_state_dict(...)
Hi @developer888891, For the prediction code, you just need to run the train.py with the arg "eval_only" example: python train.py --eval_only True --resume True --config configs/config.json -g 0 For the...
Thanks for your help.
I used 4 1080TI GPU. I would like to remind you something important. In contrast to RGB images, videos require significantly more space. 1 batch = size of the batch...
Hi @AkshayMath1 1. I would advice you to use panda (the python library) to filter the label you want (don't worry it is not very hard ;) ). 2. To...
Thanks a lot for your quick reply. I understand that using Group Pruning method allows us to synchronize the number of channel that are pruned within a group in order...
In fact, I am a bit confused how to remove an entire group.
Hi @otaviojacobi, I read the contrastive-unpaired-translation paper you are planning to use (by the way, thanks I didn't know it). For the training configuration, I basically used the one described...
I am the original author of this tutorial, but the technique that is used is not mine and have been implemented by other researchers. Your question is very interesting and...