Oier Mees

Can't evaluate pretrained model

2

Hi, when I try to evaluate the pretrained model with 'th evaluate_model.lua 'I get following error: ``` /home/meeso/torch/install/bin/luajit: /home/meeso/torch/install/share/lua/5.1/nn/Container.lua:67: In 3 module of nn.Sequential: /home/meeso/torch/install/share/lua/5.1/nn/THNN.lua:110: bad argument #8 to 'v'...

Hi, it would be very nice if you could provide pretrained models for the Visual Genome and Google-Ref datasets. Is this possible? Cheers, Oier

PointNet2 instantiation

4

Hi, I would like to instantiate a pointnet2 encoder and I am not sure how to do this. I would like to have 3 PointnetSAModules and 2 FCs. I am...

Get uncertainty

1

Hi, is it possible to compute some kind of uncertainty about the answer given for a comprehension? Like for example if you query with an ambiguous expression or you query...

How is it possible to scale up the network to handle tertiary relations instead of binary (referred and context objects)?

Deterministic sampling

2

Hi, is it possible to generate the grasp samples in a deterministic way by setting some random seed somewhere, such that for one pcd file we always get the same...

LSTM implementation

1

Hi, I wanted to ask about the LSTM implementation as it looks a bit different to the original implementation, for example it is actually not necessary to use an tf.nn.dynamic_rnn...

Second step of training is unclear

1

Hi, when I try to do the second step of the training `export SPEAKER_PATH_PREFIX=tasks/R2R/speaker/snapshots/speaker_teacher_imagenet_mean_pooled_train_iter_20000` it fails because the files available after training are speaker_teacher_imagenet_mean_pooled_train_iter_20000_enc and speaker_teacher_imagenet_mean_pooled_train_iter_20000_dec, which one should we...

How to use non-panoramic space

1

Hi, could you please describe what changes ones need to make in order to train your model with data augmentation and pragmatic inference, but without panoramic space, so normal camera...