slide2vec 2.0.1__tar.gz → 3.0.0__tar.gz

slide2vec-3.0.0/PKG-INFO

@@ -0,0 +1,166 @@
+Metadata-Version: 2.4
+Name: slide2vec
+Version: 3.0.0
+Summary: Embedding of whole slide images with Foundation Models
+Home-page: https://github.com/clemsgrs/slide2vec
+Author: Clément Grisi
+Author-email: clement.grisi@radboudumc.nl
+Project-URL: Bug Tracker, https://github.com/clemsgrs/slide2vec/issues
+Platform: unix
+Platform: linux
+Platform: osx
+Platform: cygwin
+Platform: win32
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: hs2p<3,>=2.0
+Requires-Dist: omegaconf
+Requires-Dist: h5py
+Requires-Dist: huggingface-hub
+Requires-Dist: numpy<2
+Requires-Dist: pandas
+Requires-Dist: pillow
+Requires-Dist: rich
+Requires-Dist: tqdm
+Requires-Dist: torchvision
+Requires-Dist: wholeslidedata<0.0.16
+Requires-Dist: matplotlib
+Requires-Dist: timm
+Requires-Dist: torch
+Requires-Dist: transformers
+Requires-Dist: environs
+Requires-Dist: sacremoses
+Requires-Dist: einops
+Requires-Dist: einops-exts
+Requires-Dist: xformers
+Requires-Dist: wandb
+Provides-Extra: testing
+Requires-Dist: pytest>=6.0; extra == "testing"
+Requires-Dist: pytest-cov>=2.0; extra == "testing"
+Requires-Dist: mypy>=0.910; extra == "testing"
+Requires-Dist: flake8>=3.9; extra == "testing"
+Requires-Dist: tox>=3.24; extra == "testing"
+Dynamic: author-email
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: project-url
+
+# slide2vec
+
+[![PyPI version](https://img.shields.io/pypi/v/slide2vec?label=pypi&logo=pypi&color=3776AB)](https://pypi.org/project/slide2vec/)
+
+`slide2vec` is a Python package for efficient encoding of whole-slide images using publicly available foundation models. It builds on [`hs2p`](https://pypi.org/project/hs2p/) for fast preprocessing and exposes a focused surface around `Model`, `Pipeline`, and `ExecutionOptions`.
+
+## Installation
+
+```shell
+pip install slide2vec
+```
+
+## Python API
+
+```python
+from slide2vec import Model, PreprocessingConfig
+
+model = Model.from_pretrained("virchow2", level="region")
+preprocessing = PreprocessingConfig(
+    target_spacing_um=0.5,
+    target_tile_size_px=224,
+    tissue_threshold=0.1,
+)
+embedded = model.embed_slide(
+    "/path/to/slide.svs",
+    preprocessing=preprocessing,
+)
+
+tile_embeddings = embedded.tile_embeddings
+coordinates = embedded.coordinates
+```
+
+By default, `ExecutionOptions()` uses all available GPUs. Set `ExecutionOptions(num_gpus=4)` when you want to cap the sharding explicitly.
+
+Use `Pipeline(...)` for manifest-driven batch processing when you want artifacts written to disk instead of only in-memory outputs:
+
+```python
+from slide2vec import ExecutionOptions, Pipeline
+
+pipeline = Pipeline(
+    model=model,
+    preprocessing=preprocessing,
+    execution=ExecutionOptions(output_dir="outputs/demo"),
+)
+result = pipeline.run(manifest_path="/path/to/slides.csv")
+```
+
+### Input Manifest
+
+Manifest-driven runs use the schema below. `mask_path` and `spacing_at_level_0` are optional.
+
+```csv
+sample_id,image_path,mask_path,spacing_at_level_0
+slide-1,/path/to/slide-1.svs,/path/to/mask-1.png,0.25
+slide-2,/path/to/slide-2.svs,,
+...
+```
+
+Use `spacing_at_level_0` when the slide file reports a missing or incorrect level-0 spacing and you want to override it.
+
+
+### Outputs
+
+The package writes explicit artifact directories:
+
+- `tile_embeddings/<sample_id>.pt` or `.npz`
+- `tile_embeddings/<sample_id>.meta.json`
+- `slide_embeddings/<sample_id>.pt` or `.npz`
+- `slide_embeddings/<sample_id>.meta.json`
+- optional `slide_latents/<sample_id>.pt` or `.npz`
+
+`.pt` remains the default format. `.npz` is available through `ExecutionOptions(output_format="npz")`.
+
+### Supported Models
+
+`slide2vec` currently ships preset configs for 10 tile-level models and 3 slide-level models.  
+For the full catalog and preset names, see [`docs/models.md`](docs/models.md).
+
+## CLI
+
+The CLI is a thin wrapper over the package API.  
+Bundled configs live under `slide2vec/configs/preprocessing/` and `slide2vec/configs/models/`.
+
+```shell
+python -m slide2vec --config-file /path/to/config.yaml
+```
+
+By default, manifest-driven CLI runs use all available GPUs. Set `speed.num_gpus=4` when you want to cap the sharding explicitly.
+
+New to the CLI or doing batch runs to disk? Start with [`docs/cli.md`](docs/cli.md) for the config-driven workflow, overrides, and common run patterns.
+
+## Docker
+
+[![Docker Version](https://img.shields.io/docker/v/waticlems/slide2vec?sort=semver&label=docker&logo=docker&color=2496ED)](https://hub.docker.com/r/waticlems/slide2vec)
+
+Docker remains available when you prefer a containerized runtime:
+
+```shell
+docker pull waticlems/slide2vec:latest
+docker run --rm -it \
+    -v /path/to/your/data:/data \
+    -e HF_TOKEN=<your-huggingface-api-token> \
+    waticlems/slide2vec:latest
+```
+
+## Documentation
+
+- [`docs/cli.md`](docs/cli.md) for the config-driven CLI guide
+- [`docs/python-api.md`](docs/python-api.md) for the detailed API reference
+- [`docs/models.md`](docs/models.md) for the full supported-model catalog

slide2vec-3.0.0/README.md

@@ -0,0 +1,110 @@
+# slide2vec
+
+[![PyPI version](https://img.shields.io/pypi/v/slide2vec?label=pypi&logo=pypi&color=3776AB)](https://pypi.org/project/slide2vec/)
+
+`slide2vec` is a Python package for efficient encoding of whole-slide images using publicly available foundation models. It builds on [`hs2p`](https://pypi.org/project/hs2p/) for fast preprocessing and exposes a focused surface around `Model`, `Pipeline`, and `ExecutionOptions`.
+
+## Installation
+
+```shell
+pip install slide2vec
+```
+
+## Python API
+
+```python
+from slide2vec import Model, PreprocessingConfig
+
+model = Model.from_pretrained("virchow2", level="region")
+preprocessing = PreprocessingConfig(
+    target_spacing_um=0.5,
+    target_tile_size_px=224,
+    tissue_threshold=0.1,
+)
+embedded = model.embed_slide(
+    "/path/to/slide.svs",
+    preprocessing=preprocessing,
+)
+
+tile_embeddings = embedded.tile_embeddings
+coordinates = embedded.coordinates
+```
+
+By default, `ExecutionOptions()` uses all available GPUs. Set `ExecutionOptions(num_gpus=4)` when you want to cap the sharding explicitly.
+
+Use `Pipeline(...)` for manifest-driven batch processing when you want artifacts written to disk instead of only in-memory outputs:
+
+```python
+from slide2vec import ExecutionOptions, Pipeline
+
+pipeline = Pipeline(
+    model=model,
+    preprocessing=preprocessing,
+    execution=ExecutionOptions(output_dir="outputs/demo"),
+)
+result = pipeline.run(manifest_path="/path/to/slides.csv")
+```
+
+### Input Manifest
+
+Manifest-driven runs use the schema below. `mask_path` and `spacing_at_level_0` are optional.
+
+```csv
+sample_id,image_path,mask_path,spacing_at_level_0
+slide-1,/path/to/slide-1.svs,/path/to/mask-1.png,0.25
+slide-2,/path/to/slide-2.svs,,
+...
+```
+
+Use `spacing_at_level_0` when the slide file reports a missing or incorrect level-0 spacing and you want to override it.
+
+
+### Outputs
+
+The package writes explicit artifact directories:
+
+- `tile_embeddings/<sample_id>.pt` or `.npz`
+- `tile_embeddings/<sample_id>.meta.json`
+- `slide_embeddings/<sample_id>.pt` or `.npz`
+- `slide_embeddings/<sample_id>.meta.json`
+- optional `slide_latents/<sample_id>.pt` or `.npz`
+
+`.pt` remains the default format. `.npz` is available through `ExecutionOptions(output_format="npz")`.
+
+### Supported Models
+
+`slide2vec` currently ships preset configs for 10 tile-level models and 3 slide-level models.  
+For the full catalog and preset names, see [`docs/models.md`](docs/models.md).
+
+## CLI
+
+The CLI is a thin wrapper over the package API.  
+Bundled configs live under `slide2vec/configs/preprocessing/` and `slide2vec/configs/models/`.
+
+```shell
+python -m slide2vec --config-file /path/to/config.yaml
+```
+
+By default, manifest-driven CLI runs use all available GPUs. Set `speed.num_gpus=4` when you want to cap the sharding explicitly.
+
+New to the CLI or doing batch runs to disk? Start with [`docs/cli.md`](docs/cli.md) for the config-driven workflow, overrides, and common run patterns.
+
+## Docker
+
+[![Docker Version](https://img.shields.io/docker/v/waticlems/slide2vec?sort=semver&label=docker&logo=docker&color=2496ED)](https://hub.docker.com/r/waticlems/slide2vec)
+
+Docker remains available when you prefer a containerized runtime:
+
+```shell
+docker pull waticlems/slide2vec:latest
+docker run --rm -it \
+    -v /path/to/your/data:/data \
+    -e HF_TOKEN=<your-huggingface-api-token> \
+    waticlems/slide2vec:latest
+```
+
+## Documentation
+
+- [`docs/cli.md`](docs/cli.md) for the config-driven CLI guide
+- [`docs/python-api.md`](docs/python-api.md) for the detailed API reference
+- [`docs/models.md`](docs/models.md) for the full supported-model catalog

{slide2vec-2.0.1 → slide2vec-3.0.0}/pyproject.toml

@@ -23,7 +23,7 @@ warn_unused_configs = true
 no_implicit_reexport = true
 
 [tool.bumpver]
-current_version = "2.0.1"
+current_version = "3.0.0"
 version_pattern = "MAJOR.MINOR.PATCH"
 commit = false       # We do version bumping in CI, not as a commit
 tag = false          # Git tag already exists — we don't auto-tag

{slide2vec-2.0.1 → slide2vec-3.0.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = slide2vec
-version = 2.0.1
+version = 3.0.0
 description = Embedding of whole slide images with Foundation Models
 author = Clément Grisi
 platforms = unix, linux, osx, cygwin, win32
@@ -16,17 +16,18 @@ classifiers =
 packages = 
 	slide2vec
 install_requires = 
+	hs2p>=2.0,<3
 	omegaconf
+	h5py
 	huggingface-hub
 	numpy<2
 	pandas
 	pillow
+	rich
 	tqdm
-	numba
 	torchvision
-	opencv-python
-	matplotlib
 	wholeslidedata<0.0.16
+	matplotlib
 	timm
 	torch
 	transformers
@@ -35,6 +36,7 @@ install_requires =
 	einops
 	einops-exts
 	xformers
+	wandb
 python_requires = >=3.10
 zip_safe = no
 include_package_data = True
@@ -49,6 +51,11 @@ testing =
 
 [options.package_data]
 slide2vec = py.typed
+slide2vec.configs = *.yaml, models/*.yaml, preprocessing/*.yaml
+
+[options.entry_points]
+console_scripts = 
+	slide2vec = slide2vec.cli:main
 
 [flake8]
 max-line-length = 160

slide2vec-3.0.0/slide2vec/__init__.py

@@ -0,0 +1,17 @@
+from slide2vec.api import EmbeddedSlide, ExecutionOptions, Model, Pipeline, PreprocessingConfig, RunResult
+from slide2vec.artifacts import SlideEmbeddingArtifact, TileEmbeddingArtifact
+
+
+__version__ = "3.0.0"
+
+__all__ = [
+    "Model",
+    "Pipeline",
+    "PreprocessingConfig",
+    "ExecutionOptions",
+    "RunResult",
+    "EmbeddedSlide",
+    "SlideEmbeddingArtifact",
+    "TileEmbeddingArtifact",
+    "__version__",
+]

slide2vec-3.0.0/slide2vec/__main__.py

@@ -0,0 +1,5 @@
+from slide2vec.cli import main
+
+
+if __name__ == "__main__":
+    main()