glom-pytorch

GLOM - Pytorch

An implementation of Glom, Geoffrey Hinton's new idea that integrates concepts from neural fields, top-down-bottom-up processing, and attention (consensus between columns) for learning emergent part-whole heirarchies from data.

Yannic Kilcher's video was instrumental in helping me to understand this paper

Install

$ pip install glom-pytorch

Usage

import torch
from glom_pytorch import Glom

model = Glom(
    dim = 512,         # dimension
    levels = 6,        # number of levels
    image_size = 224,  # image size
    patch_size = 14    # patch size
)

img = torch.randn(1, 3, 224, 224)
levels = model(img, iters = 12) # (1, 256, 6, 512) - (batch - patches - levels - dimension)

Pass the return_all = True keyword argument on forward, and you will be returned all the column and level states per iteration, (including the initial state, number of iterations + 1). You can then use this to attach any losses to any level outputs at any time step.

It also gives you access to all the level data across iterations for clustering, from which one can inspect for the theorized islands in the paper.

import torch
from glom_pytorch import Glom

model = Glom(
    dim = 512,         # dimension
    levels = 6,        # number of levels
    image_size = 224,  # image size
    patch_size = 14    # patch size
)

img = torch.randn(1, 3, 224, 224)
all_levels = model(img, iters = 12, return_all = True) # (13, 1, 256, 6, 512) - (time, batch, patches, levels, dimension)

# get the top level outputs after iteration 6
top_level_output = all_levels[7, :, :, -1] # (1, 256, 512) - (batch, patches, dimension)

Denoising self-supervised learning for encouraging emergence, as described by Hinton

…

You can pass in the state of the column and levels back into the model to continue where you left off (perhaps if you are processing consecutive frames of a slow video, as mentioned in the paper)

import torch
from glom_pytorch import Glom

model = Glom(
    dim = 512,
    levels = 6,
    image_size = 224,
    patch_size = 14
)

img1 = torch.randn(1, 3, 224, 224)
img2 = torch.randn(1, 3, 224, 224)
img3 = torch.randn(1, 3, 224, 224)

levels1 = model(img1, iters = 12)                   # image 1 for 12 iterations
levels2 = model(img2, levels = levels1, iters = 10) # image 2 for 10 iteratoins
levels3 = model(img3, levels = levels2, iters = 6)  # image 3 for 6 iterations

Appreciation

Thanks goes out to Cfoster0 for reviewing the code

Todo

• contrastive / consistency regularization of top-ish levels

Citations

@misc{hinton2021represent,
    title   = {How to represent part-whole hierarchies in a neural network}, 
    author  = {Geoffrey Hinton},
    year    = {2021},
    eprint  = {2102.12627},
    archivePrefix = {arXiv},
    primaryClass = {cs.CV}
}