timm

library1.0.28pypypi✓ verified 26d ago

PyTorch Image Models — collection of SOTA vision models, pretrained weights, layers, optimizers, and training utilities by Ross Wightman. Current version is 1.0.15 (Mar 2026). Primary weight source is now Hugging Face Hub. Import path for layers changed: timm.models.layers → timm.layers.

ai-ml

pip install timm

github ↗package ↗docs ↗

INSTALL

IMPORT

SIG · TIMM

timm

ai-mlpythonv1.0.28

Install

66.1s avg

Import

14933ms

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 v1.0.28 · 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

✓ 72.9s

py 3.11

✕ build_error

✓ 70.4s

py 3.12

✕ build_error

✓ 59.6s

py 3.13

✕ build_error

✓ 61.4s

py 3.9

✕ build_error

✕ timeout

4890MB installed

● package 4890MB

Code

Verified usage

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

timm.layers

✓ from timm.layers import PatchEmbed, Mlp, DropPath # or import timm.layers

✗ from timm.models.layers import PatchEmbed, Mlp, DropPath # moved in 0.9 — deprecated mapping exists but will be removed

timm.models.layers was moved to timm.layers in 0.9.x. Direct module imports like import timm.models.layers.module no longer work — only the top-level from timm.models.layers import name still works via a deprecation shim.

create_model

✓ import timm # Load with pretrained weights model = timm.create_model('resnet50', pretrained=True) # Load specific weight variant using architecture.tag format model = timm.create_model('resnet50.a1_in1k', pretrained=True) # Custom num_classes for fine-tuning model = timm.create_model('efficientnet_b0', pretrained=True, num_classes=10) # Feature extraction (removes classifier) model = timm.create_model('resnet50', features_only=True, pretrained=True)

✗ # Old-style weight loading from GitHub releases (no longer primary source) model = timm.create_model('resnet50', pretrained=True) # Weights now come from HF Hub: https://huggingface.co/timm

Pretrained weights now load from Hugging Face Hub (huggingface.co/timm) not GitHub releases. Model names with architecture.pretrained_tag (e.g. resnet50.a1_in1k) select specific weight variants.

Load pretrained model, apply model-specific preprocessing, run inference.

import timm import torch from PIL import Image from timm.data import resolve_data_config, create_transform # List available models print(timm.list_models('resnet*')[:5]) # Load pretrained model model = timm.create_model('efficientnet_b0.ra_in1k', pretrained=True) model.eval() # Get model-specific preprocessing config = resolve_data_config({}, model=model) transform = create_transform(**config) # Inference img = Image.open('image.jpg').convert('RGB') tensor = transform(img).unsqueeze(0) with torch.no_grad(): output = model(tensor) # [1, 1000] logits probs = torch.softmax(output, dim=1) top5 = torch.topk(probs, 5) # Fine-tune with custom head model = timm.create_model('resnet50', pretrained=True, num_classes=10)

Debug

Known issues

breakingtimm.models.layers module moved to timm.layers in 0.9.x. Direct module imports (import timm.models.layers.module) fail. Only top-level from timm.models.layers import name still works via deprecation shim — which will be removed.

fix

Replace from timm.models.layers import X with from timm.layers import X throughout your codebase.

affects: >= 0.9

breakingModel naming changed to architecture.pretrained_tag format in 0.9+. Old names like resnet50_21k still work via deprecation remapping but new weight variants are only accessible via the new format (e.g. resnet50.a1_in1k).

fix

Use timm.list_models() to discover available model names. For specific weight variants use the architecture.tag format.

affects: >= 0.9

breakingPretrained weights now loaded from Hugging Face Hub (https://huggingface.co/timm) not GitHub releases. Old GitHub release URLs hardcoded in custom code will 404.

fix

Use timm.create_model(name, pretrained=True) — weight URLs are managed automatically. Do not hardcode weight URLs.

affects: >= 0.9

gotchatimm.create_model with num_classes=0 removes the classifier entirely and returns features. num_classes=None is NOT the same — it keeps the default head. Setting wrong num_classes silently produces wrong output shapes.

fix

For feature extraction: num_classes=0 (removes head). For fine-tuning with N classes: num_classes=N (replaces head with random init). Use model.reset_classifier(num_classes=N) to change after creation.

affects: all

gotchaEach model has its own expected preprocessing (mean, std, input size). Using generic ImageNet normalization values directly instead of model-specific config produces degraded accuracy.

fix

Always use timm's preprocessing utilities: config = timm.data.resolve_data_config({}, model=model); transform = timm.data.create_transform(**config).

affects: all

gotchaNot all model variants have pretrained weights — timm lists models without weights too. timm.create_model('some_model', pretrained=True) raises RuntimeError if no weights exist for that variant.

fix

Use timm.list_models(pretrained=True) to list only models with available weights. Or check: timm.list_pretrained().

affects: all

breakingInstalling `timm` can lead to dependency conflicts with other packages in the environment (e.g., `torch`, `torchvision`, `Pillow`, `packaging`) or specific Python versions, resulting in `ERROR: ResolutionImpossible` during `pip install`.

fix

Ensure your Python environment is clean or use a virtual environment. Try to install `timm` in isolation or verify dependency compatibility with other packages. Consider explicitly installing compatible versions of `timm`'s main dependencies (like `torch`, `torchvision`) before installing `timm`.

affects: all

Errors

Common errors & fixes

ModuleNotFoundError: No module named 'timm.models.layers'

The import path for utility layers in `timm` changed from `timm.models.layers` to `timm.layers` starting from version 0.10.0 (and is present in 1.0.15).

fix

Replace `from timm.models.layers import ...` with `from timm.layers import ...`.

OSError: Specified pretrained weights did not exist for model 'model_name'. Check your entry and try again.

The model name provided to `timm.create_model` might be incorrect, there could be network issues preventing download from Hugging Face Hub, or the specified model does not have pretrained weights available.

fix

Verify the model name against `timm.list_models(pretrained=True)`, ensure an active internet connection, and check if the model actually supports pretrained weights.

RuntimeError: Expected 4D input for conv2d, got 3D input instead

The input tensor provided to the model's `forward` method is missing the expected batch dimension. `timm` models typically expect input in `[batch_size, channels, height, width]` format.

fix

Add a batch dimension to your input tensor, typically by using `input_tensor.unsqueeze(0)` for a single image.

AttributeError: 'ResNet' object has no attribute 'fc' (or 'EfficientNet' object has no attribute 'classifier')

The name of the final classification layer (or head) varies across different `timm` models and architectures. Common names include `head`, `fc`, or `classifier`.

fix

Inspect the model's structure (e.g., `print(model)`) to identify the correct attribute name for the classification head, which is often `model.head` for many `timm` models.

Upgrade

Version history

1.0.28latest on PyPI · released Jul 11, 2026

Audit

Dependencies

torch>=1.7requiredRequired. Install PyTorch separately first — timm does not pin a specific version.

torchvisionrequiredRequired. Installed automatically.

huggingface-hubrequiredRequired for loading weights from HF Hub (default since 0.9). Installed automatically.

safetensorsrequiredRequired for safetensors weight format. Installed automatically.

Agent activity

26 hits · last 30 days

node

Amazon

OpenAI (training)

Resources

githubhttps://github.com/huggingface/pytorch-image-models ↗

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

docshttps://huggingface.co/docs/timm/en/index ↗