Registry / ai-ml / pretrainedmodels

pretrainedmodels

library0.7.4pypypiunverified

A library providing pretrained models for PyTorch, including architectures like ResNet, DenseNet, Inception, and more. Version 0.7.4 is the latest release, though the project is in maintenance mode with infrequent updates. It is commonly used for transfer learning and feature extraction, but users should prefer torchvision's model zoo for active support.

ai-ml

pip install pretrainedmodels

github ↗package ↗

INSTALL

IMPORT

SIG · PRETRAINEDMODELS

pretrainedmodels

ai-mlpythonv0.7.4

Install

70.7s avg

Import

—

Disk

4890MB

Pass rate

4/ 10

Env Coverage4 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.7.4 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✕ build_error

✓ 82.9s

py 3.11

✕ build_error

✓ 76.7s

py 3.12

✕ build_error

✓ 63.4s

py 3.13

✕ build_error

✓ 59.9s

py 3.9

✕ build_error

✕ timeout

4890MB installed

● package 4890MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

pretrainedmodels

✓ import pretrainedmodels

✗ from pretrainedmodels import ...

Direct import is fine, but common mistake is to import submodules incorrectly; use pretrainedmodels.__dict__ to list models.

models

✓ from pretrainedmodels import models

To access model constructors like models.resnet101()

Load a pretrained ResNet-101 model and run inference.

import torch import pretrainedmodels model = pretrainedmodels.__dict__['resnet101'](pretrained='imagenet') model.eval() print(model) # Example inference from pretrainedmodels import utils import torchvision.transforms as transforms tf = utils.TransformImage(model) input_tensor = torch.randn(1, 3, 224, 224) out = model(input_tensor) print(out.shape)

Debug

Known issues

deprecatedpretrainedmodels is in maintenance mode; many models are outdated and may not work with newer PyTorch versions. Prefer torchvision's model zoo or timm.

fix

Switch to torchvision.models or the timm library.

affects: >=0.7.0

gotchaThe pretrained='imagenet' argument may fail silently if checkpoint not found. Always verify the model downloads correctly.

fix

Check network connectivity or manually download pretrained weights from the official repository.

affects: all

gotchaModel input sizes vary; not all models accept 224x224 images. Use utils.TransformImage to get the correct preprocessing.

fix

Always use pretrainedmodels.utils.TransformImage(model) to get the right transforms.

affects: all

breakingPyTorch 1.9+ may cause compatibility issues with older model definitions. You may see AttributeError: module 'torch' has no attribute 'irfft'.

fix

Use torchvision or timm instead. Or pin PyTorch to 1.8.x.

affects: 0.7.4 with PyTorch >=1.9

Upgrade

Version history

0.7.4latest on PyPI · released Oct 29, 2018

Audit

Dependencies

torchrequiredCore dependency for all models and operations

torchvisionoptionalRequired for some model definitions and transforms (e.g., pretrainedmodels.utils)

Agent activity

4 hits · last 30 days

node

Resources

githubhttps://github.com/cadene/pretrained-models.pytorch ↗

packagehttps://pypi.org/project/pretrainedmodels/ ↗