Skip to content
No description, website, or topics provided.
Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
MLPs.py
README.md
conv.py
main.py
model.py
monster_trainer_generator.py
subset_sum_generator.py
treasure_generator.py
util.py

README.md

Pytorch implementation for abstract reasoning tasks - [What Can Neural Networks Reason About?]

File Descriptions

All files ending in *generator.py generate a type of dataset for a given task (e.g. subset-sum, Monster trainer, etc):

The tasks described in our experiment section corresponds to the following subtype IDs (IDs are authors' favorite random numbers):

Furthest pair: subtype 0

Maximum value difference: subtype 2

Monster trainer: subtype 15

Subset sum: subtype 12

Requirements

Usage

For Tasks Furthest pair and Maximum value difference:

Use $ python treasure_generator.py --K=6 --n_objects=20 --coord_size=8 --age_range=100 --coord_range=20 to generate the animal world dataset

and $ python main.py --model=$MODEL_NAME --K=6 --n_objects=25 --coord_size=8 --age_range=100 --coord_range=20 --data=$DATA_FILE.pickle --subtype=0/2
to train.

For other tasks, the usage is similar and please refer to the documentation in each data generator file and main.py for more details.

You can’t perform that action at this time.