block.bootstrap.pytorch

block.bootstrap.pytorch copied to clipboard

How to get output of VRD?

1

Hi @Cadene @pushkalkatara @cdancette @Hediby I was able to run the evaluation on test dataset and get the statistics. Now, I wish to actually see the VRD ouput, ie, the...

fomalhaut-b

Hello and thanks for this very nice job. I want to ask if the code could be refactored and use Distributed Data Parallel instead of Data Parallel. Or if you...

dimvarsamis

Hi @Cadene I used downloaded the block pretrained module but didnt download any dataset. Still got the same output. How do I get this to run on custom data? Also,...

fomalhaut-b

DinghaoXi

external/VQA not in the pip package

1

The external/VQA module is not included in the pip package

cdancette

I try to download the TDIUC feature by http://data.lip6.fr/cadene/block/tdiuc/extract_rcnn/2018-04-27_bottom-up-attention_fixed_36.tar, but the spped is to slow, can you help me? THANKS

yanxinzju

The code about get the image features!

2

Hi Cadene, Thank you open the source.But I face the problem about download the feature files, It's very slow to download,about 100 k/s. So can you share the code about...

haoopan

The question about KLD loss

1

Excuse me again! When I use the KLDivLoss as the criterion in ./block/models/criterions/kl_divergence.py rather than crossentropy, I get the loss is 0 and the acc is worse , as following...

haoopan

Can't create view.html

1

hi, do i need to create logs.json in advance？

xywhat

Is it possible to share the feature extraction code? If it is not available, can you describe what model you used or where you got a feature extraction reference code?...

g0kul6