Skip to main content

Dense and fastfood transform wrappers to reproduce "Intrinsic dimensionality of objective landscapes" by Li et al. (2018)

Project description

About

This package includes fastfood and dense transformation wrappers for pytorch modules, primarily to reproduce results from Li, Chunyuan, et al. "Measuring the intrinsic dimension of objective landscapes." arXiv preprint arXiv:1804.08838 (2018) - see below for info.

  • All contributions are welcome! Please raise an issue for a bug, feature or pull request!

  • Give this repo a star! :star:

Install

pip install intrinsic-dimensionality

Quick start on your classification task!

import os
os.environ["CUDA_VISIBLE_DEVICES"] = DEVICE_NUM
import torch
from torch import nn
import torchvision.models as models
from intrinsic import FastFoodWrap

class Classifier(nn.Module):
    def __init__(self, input_dim, n_classes):
        super(Classifier, self).__init__()
        self.fc = nn.Linear(input_dim, n_classes)
        self.maxpool = nn.AdaptiveMaxPool2d(1)

    def forward(self, x):
        x = self.maxpool(x)
        x = x.reshape(x.size(0), -1)
        x = self.fc(x)
        return x

def get_resnet(encoder_name, num_classes, pretrained=False):
    assert encoder_name in ["resnet18", "resnet50"], "{} is a wrong encoder name!".format(encoder_name)
    if encoder_name == "resnet18":
        model = models.resnet18(pretrained=pretrained)
        latent_dim = 512
    else:
        model = models.resnet50(pretrained=pretrained)
        latent_dim = 2048
    children = (list(model.children())[:-2] + [Classifier(latent_dim, num_classes)])
    model = torch.nn.Sequential(*children)
    return model

# Get model and wrap it in fastfood
model = get_resnet("resnet18", num_classes=YOUR_NUMBER_OF_CLASSES).cuda()
model = FastFoodWrap(model, intrinsic_dimension=100, device=DEVICE_NUM)

Reproducing experiments from the paper

Full thread about reproducibility results is available here. Note that some hyper-parameters were not listed in the paper - I raised issues on Uber's Github repo here.

I am able to reproduce their MNIST results with LR=0.0003, batch size 32 for both dense and fastfood transformations using FCN (fcn-dense, fcn-fastfood). However, not for LeNet (cnn-dense, cnn-fastfood).

For CIFAR-10, with far larger resnet (Resnet-18 11mil param) vs 280k 20-layer resnet used in the paper, results appear to be similar. FCN results in appendix (Fig S7) suggest some variation is to be expected.

Cite

@misc{jgamper2020intrinsic,
  title   = "Intrinsic-dimensionality Pytorch",
  author  = "Gamper, Jevgenij",
  year    = "2020",
  url     = "https://github.com/jgamper/intrinsic-dimensionality"
}

@article{li2018measuring,
  title={Measuring the intrinsic dimension of objective landscapes},
  author={Li, Chunyuan and Farkhoor, Heerad and Liu, Rosanne and Yosinski, Jason},
  journal={arXiv preprint arXiv:1804.08838},
  year={2018}
}

Project details


Release history Release notifications | RSS feed

This version

0.1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

intrinsic-dimensionality-0.1.tar.gz (3.2 kB view details)

Uploaded Source

Built Distribution

intrinsic_dimensionality-0.1-py3-none-any.whl (4.0 kB view details)

Uploaded Python 3

File details

Details for the file intrinsic-dimensionality-0.1.tar.gz.

File metadata

  • Download URL: intrinsic-dimensionality-0.1.tar.gz
  • Upload date:
  • Size: 3.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.48.0 CPython/3.6.7

File hashes

Hashes for intrinsic-dimensionality-0.1.tar.gz
Algorithm Hash digest
SHA256 1a505b1ee17aa31426ccff647f8f76b3b36a4c50bd43cea27804fc7176e8ec3f
MD5 0fe7b09cb000f165ac235b085f5c1834
BLAKE2b-256 773409adedea4cb869bbbc8c0281a381680bf93962f31d128d2dc3e473b09886

See more details on using hashes here.

File details

Details for the file intrinsic_dimensionality-0.1-py3-none-any.whl.

File metadata

  • Download URL: intrinsic_dimensionality-0.1-py3-none-any.whl
  • Upload date:
  • Size: 4.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.2.0 requests-toolbelt/0.9.1 tqdm/4.48.0 CPython/3.6.7

File hashes

Hashes for intrinsic_dimensionality-0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 98ab2452ba11506647e1772673c33142058b1944e85fb9c62fcca12d3c81fd3d
MD5 2c061b9abece10154e6a58f9bec66fd4
BLAKE2b-256 80e1ac4f57158703ccfd3b94d90bd6d76ac621fa84ddc25aaf69c0a7f9d1d34b

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page