featlens 0.2.5

Model-agnostic feature-map visualization: PCA, cosine-similarity, k-means and foreground maps from any vision model and any layer.

📖 Documentation: https://turhancan97.github.io/FeatLens/  ·  🤗 Live demo: https://huggingface.co/spaces/turhancan97/FeatLens-demo

See what any vision model encodes. FeatLens renders feature maps for any vision model — DINO, DINOv2/v3, CLIP, SigLIP, MAE, DeiT, V-JEPA, CNNs, … — loaded from any source (timm, HuggingFace transformers, torch.hub, an external repo, or a model you built yourself), and from any layer, as a clean model × layer grid. Color the features by robust PCA, cosine-similarity to a seed patch, k-means segmentation, or a foreground mask — and match patches across two images.

Most "DINO PCA" scripts are welded to one model. FeatLens separates representation access (a small adapter layer over the model zoo) from visualization (PCA / cosine / k-means / foreground), so you can point it at a new model in seconds and compare models/layers side by side.

Gallery

All produced by examples/quickstart.py. The per-image rows below use DINO ViT-S/8 at 768px — a small patch-8 backbone at high resolution gives a fine 96×96 feature grid, so thin structures (whiskers, feather barbs, individual fruit) stay crisp. The model × layer, compare and method figures further down use DINO ViT-B/16 at the default 224px.

visualize(...) — DINO ViT-S/8 @ 768px, feature maps across layers 2 / 5 / 8 / 11:

Image (original size)	Source	Feature maps
peacock.jpg · 1600×1280
cat_hires.jpg · 1600×1200
market.jpg · 1600×1063

grid(...) — model × layer, overlaid on the image (DINO vs DINOv2 across layers 2/5/8/11):

compare(...) — models at the final layer  |  custom_adapter — a ResNet-50 (CNN escape hatch)

  

Same scene, six ViT-B/16 backbones — market.jpg at 1024px, last-layer features (a 64×64 grid), PCA→RGB per model. Architecture and patch size are held fixed, so the differences are purely the training objective: DINOv3 and DINO carve the scene into smooth semantic regions, MAE stays low-frequency, while SigLIP, supervised, and Perception Encoder encode much higher-frequency detail.

Beyond PCA — the same DINOv2 row, recolored by cosine-similarity to a seed patch, k-means segmentation, and a foreground mask (across layers 2 / 5 / 8 / 11):

Method	Across layers
cosine (seed on the cat)
kmeans (k=6)
foreground

correspond(...) — seed a patch in image A, find the matches in image B. Here the seed is on a real cat's eye; DINOv2 features match the same semantic part on a watercolor cat, across the photo→illustration domain gap:

Install

pip install -e ".[timm]"          # timm backend (DINO, CLIP, SigLIP, DeiT, ...)
# extras: [hf] transformers · [clip] open_clip · [all]

Install PyTorch for your platform first (https://pytorch.org).

Quick start (Python)

import featlens as ll

# One model, scrub layers (shared PCA basis -> colors comparable across the row)
ll.visualize("dinov2_vitb14", "img.jpg", layers=[2, 5, 8, 11], out="row.png")

# Compare models at the final layer (per-tile basis)
ll.compare(["dino_vitb16", "mae_vitb16", "clip_large_openai"], "img.jpg", layer=-1, out="cmp.png")

# Full model x layer grid, overlaid on the image
ll.grid(["dino_vitb16", "dinov2_vitb14"], "img.jpg", layers=[2, 5, 8, 11], overlay=True, out="grid.png")

# Batch a whole folder -> one figure per image (model loads once, reused across images)
ll.batch("dino_vitb16", "photos/", "out/", layers=[2, 5, 8, 11])

Quick start (CLI)

featlens --models dino_vitb16 clip_large_openai --layers 2 5 8 11 \
    --images examples/images/cat.jpg --mode grid --out out/grid.png
featlens --config configs/example.yaml --images examples/images/cat.jpg --out out/grid.png

# Batch: point --images at a folder (or glob) and --out-dir at an output folder
featlens --models dino_vitb16 --layers 2 5 8 11 --images photos/ --out-dir out/

Image size & resizing

Images are resized to a square img_size × img_size before the model (default 224). img_size must be divisible by the model's patch size (multiples of 16 for patch-16 models, 14 for patch-14). Larger sizes give a finer feature grid at more compute:

ll.visualize("dinov2_vitb14", "img.jpg", layers=[2, 5, 8, 11], img_size=448)   # 32x32 grid

For non-square images, choose how aspect ratio is handled with resize_mode:

resize_mode	behavior
squash (default)	resize straight to img_size² — may distort
crop	resize shortest side to img_size, center-crop — aspect preserved
pad	resize longest side to img_size, pad to square — keeps the whole image

ll.grid([...], "wide.jpg", resize_mode="crop")          # Python

featlens --models dino_vitb16 --images wide.jpg --resize-mode pad --img-size 448 --out g.png

(FeatureGrid(interpolation_size=…) is separate — it only upscales the rendered tiles, not the model input.)

Model sources

Source	How to pass it	Needs
timm	friendly name (dinov2_vitb14) or raw id (vit_base_patch16_224)	[timm]
HuggingFace	hf:facebook/dinov2-base	[hf]
torch.hub (V-JEPA)	vjepa2_vitl16	network for weights
External repo (VGGT/SPA/…)	external_adapter.load(repo_dir, builder, hook_target=…)	the cloned repo
Your own model	custom_adapter.load(model, feature_fn=…)	—

Friendly names (see featlens/registry.py) cover DINO, DINOv2/v3, CLIP, SigLIP, MAE, DeiT, Perception Encoder and V-JEPA; any other timm id works directly.

Layers

layers=[2, 5, 8, 11] selects transformer block indices (0-based, negatives allowed, -1 = last). The same convention holds across backends — for HuggingFace models FeatLens maps block i to hidden_states[i+1] (skipping the embedding output) for you.

Visualization methods

Every method consumes the same dense feature stack, so it works on grid / visualize / compare and across any layer:

cosine mode: the heatmap (right) tracks the seed patch (white dot) — click anywhere on the 🤗 live demo.

method	shows	extra args
pca (default)	robust PCA → RGB	basis, remove_first_component
cosine	cosine similarity to a seed patch (with a [-1, 1] colorbar)	seed=(x, y), colormap
kmeans	unsupervised k-means segmentation (with a cluster legend)	k
foreground	fg/bg mask (first PCA component)	—

fl.visualize("dino_vitb16", "img.jpg", layers=[2, 5, 8, 11], method="cosine", seed=(0.5, 0.5))
fl.compare(["dino_vitb16", "dinov2_vitb14"], "img.jpg", layer=-1, method="kmeans", k=8)
fl.correspond("dino_vitb16", "a.jpg", "b.jpg", seed=(0.4, 0.5), topk=3, out="corr.png")  # cross-image

seed is normalized image coords (x, y) ∈ [0, 1] (resolution/model independent). Pass cache=True to memoize extraction on disk ($FEATLENS_CACHE_DIR, else ~/.cache/featlens) so re-renders are instant. Try it in the browser on the 🤗 live demo (or run demo/ locally) — in cosine mode, click the image to move the seed. See the docs.

Bring your own model

Anything that isn't built in works through the escape hatch — give a feature function or a hook target. CNNs work for free (their conv map is already spatial):

import torch.nn as nn, torchvision
from featlens import FeatureExtractor, FeatureGrid
from featlens.adapters import custom_adapter

resnet = torchvision.models.resnet50(weights="DEFAULT")
trunk = nn.Sequential(*list(resnet.children())[:-2])           # -> [B, 2048, h, w]
lm = custom_adapter.load(trunk, patch_size=32, feature_fn=lambda m, x: m(x), name="resnet50")
FeatureGrid([FeatureExtractor(lm)]).render("img.jpg", out_path="resnet50.png")

For a model in its own repo, external_adapter.load(repo_dir, builder, hook_target="blocks") puts the repo on sys.path, builds the model, and hooks its blocks.

How it works

1. Adapters resolve a spec → a LoadedModel and drive extraction in one of three modes: forward hooks on per-block modules (ViTs/CNNs/V-JEPA), HF output_hidden_states, or a user callable.
2. tokens_to_grid normalizes whatever a layer emits ([B,N,D] tokens with optional CLS/register prefixes, or [B,D,h,w] maps) into a dense [B,D,h,w] grid.
3. Robust PCA (median-absolute-deviation outlier filtering) projects features to RGB; FeatureGrid lays out the model × layer tiles with a per-tile or shared-per-model basis.

The extraction core adapts the FrozenBackbone pattern; the PCA is adapted from the SpaRRTa feature-map script.

Releasing

Releases publish to PyPI automatically via .github/workflows/publish.yml (PyPI Trusted Publishing — no API token stored in the repo).

One-time setup on PyPI: add a trusted publisher for the project (Account → Publishing) with owner turhancan97, repository FeatLens, workflow publish.yml, environment pypi. PyPI supports a pending publisher so the very first release can also go through Actions.

Then cut a release by pushing a tag:

# bump the version in pyproject.toml first, then:
git tag v0.1.0 && git push origin v0.1.0

The workflow builds the sdist + wheel, runs twine check, and uploads to PyPI.

License

MIT.