Tomasz Kornuta

Consider actually NOT stopping when "converged", this will require dividing loss_stop into two parameters: - loss_threshold (DEFAULT: 1e-5) - indicating the threshold - loss_stop (DEFAULT: True or False?) - indicating...

Investigate why two validation runs on the same model return slightly different statistics

2

*validation with batch of size 1* - works perfectly *validation with batch of size 10* - from time to time returns values that differ First I was thinking that the...

Reorganize helpers/workers

2

General idea is to reproduce "tiny helpful apps", like e.g. index_splitter OR... grid workers(!)

Move generate_feature_maps_file() from CLEVR to GenerateFeatureMaps

3

In order to enable reproducible VIGIL experiments, and make CLEVR a lighter class: Move most of the complexity of CLEVR.generate_feature_maps_file() to GenerateFeatureMaps\

Grid Trainers/Testers on GPU have hardcoded sleep time (currently 3s). This is motivated by the fact that cuda-gpupick picks a free GPU only by checking the contexts running on a...

**Describe the bug** Currently, all workers assume that they are executed from the mi-prometheus main directory. Along with setup.py we open the possibility to execute the mip-* workers from any...

Python Package Index (PyPI)