Skip to main content

topoloss

Project description

topoloss

topoloss

pip install topoloss

Example

import torchvision.models as models
from topoloss import TopoLoss, LaplacianPyramidLoss

# Load a pre-trained ResNet-18 model
model = models.resnet18(pretrained=False)

# define where to apply the topo loss
topo_loss = TopoLoss(
    losses=[
        LaplacianPyramidLoss.from_layer(
            model=model,
            layer=model.layer3[1].conv2,
            factor_h=3.0,
            factor_w=3.0,
        )
        ## add more layers here if you want :)
    ]
)

# Compute the loss
loss = topo_loss.compute(model=model)
loss.backward()
print(f"Computed topo loss: {loss.item()}")

Project details


Download files

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

Source Distribution

topoloss-0.0.0.tar.gz (3.4 kB view details)

Uploaded Source

Built Distribution

topoloss-0.0.0-py3-none-any.whl (3.1 kB view details)

Uploaded Python 3

File details

Details for the file topoloss-0.0.0.tar.gz.

File metadata

  • Download URL: topoloss-0.0.0.tar.gz
  • Upload date:
  • Size: 3.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for topoloss-0.0.0.tar.gz
Algorithm Hash digest
SHA256 c3bda957e8a9b0f52fdf18433c5dc1dfb7adea9427daa82ff9472ae99da648f3
MD5 4318b7089b21eb32648d2d5650ad70ee
BLAKE2b-256 e382ee3be494114bfa5ed7e7a4cbabdbe819a16fb0264fc49b6e109093fe671f

See more details on using hashes here.

File details

Details for the file topoloss-0.0.0-py3-none-any.whl.

File metadata

  • Download URL: topoloss-0.0.0-py3-none-any.whl
  • Upload date:
  • Size: 3.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.7

File hashes

Hashes for topoloss-0.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 30e56b068db873112fa5ced01389d069c8a40c40aa595645c697588968d9563e
MD5 4546da59a05a200396fc33bc74324c63
BLAKE2b-256 2b5c4ffc4d166902f19b3a37a0c91817d67a0b86d9d4cea4f9d8a85df979f538

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