imgraft 0.1.0__tar.gz

imgraft-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

imgraft-0.1.0/PKG-INFO

@@ -0,0 +1,253 @@
+Metadata-Version: 2.4
+Name: imgraft
+Version: 0.1.0
+Summary: Semantic image dataset curation using CLIP + HDBSCAN
+License: MIT
+Project-URL: Homepage, https://github.com/dasarinikhil/imgraft
+Project-URL: Issues, https://github.com/dasarinikhil/imgraft/issues
+Keywords: clip,hdbscan,dataset-curation,computer-vision,image-deduplication,semantic-clustering,umap
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: open-clip-torch>=2.20.0
+Requires-Dist: hdbscan>=0.8.33
+Requires-Dist: umap-learn>=0.5.3
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: Pillow>=10.0.0
+Requires-Dist: tqdm>=4.66.0
+Requires-Dist: rich>=13.7.0
+Requires-Dist: typer>=0.12.0
+Requires-Dist: plotly>=5.18.0
+Requires-Dist: scikit-learn>=1.3.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0.0; extra == "dev"
+Provides-Extra: vis
+Requires-Dist: matplotlib>=3.8.0; extra == "vis"
+Requires-Dist: kaleido>=0.2.1; extra == "vis"
+Dynamic: license-file
+
+# imgraft
+
+**Semantic image dataset curation via CLIP + HDBSCAN.**
+
+[![PyPI version](https://badge.fury.io/py/imgraft.svg)](https://pypi.org/project/imgraft/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/)
+
+imgraft helps you clean, balance, and curate any messy image dataset — no labels, no manual annotation needed. Give it a folder of images and it returns a semantically balanced, deduplicated subset with full visualizations.
+
+---
+
+## How it works
+
+![imgraft pipeline](docs/pipeline.png)
+
+Five stages — all automatic:
+
+1. **Embed** — every image gets a CLIP vector (ViT-B/32 or ViT-L/14)
+2. **Cluster** — HDBSCAN finds semantic groups, UMAP pre-reduces for speed
+3. **Curate** — pick a strategy: centroid, diversity, or text-query filter
+4. **Inspect** — contact sheet PNGs per cluster for visual verification
+5. **Export** — structured `core/` + `diverse/` + `noise/` folders, ready for training
+
+---
+
+## Why imgraft?
+
+Raw image datasets are messy. Web scrapes contain near-duplicates. Crawled sets are class-imbalanced. Annotators mislabel. Training on noisy data silently destroys model performance.
+
+imgraft solves this using **semantic similarity** — it embeds every image with CLIP, discovers visual groups with HDBSCAN, and selects the best representatives per cluster. No domain assumptions. Works on any image type.
+
+> **Real-world impact**: On a production OCR project, an automated CLIP + HDBSCAN curation pipeline recovered model accuracy from 2% (after discovering 100K+ mislabeled images) to 90% on first retrain, reaching 95% through iteration.
+
+---
+
+## Install
+
+```bash
+pip install imgraft
+```
+
+For PNG visualization support:
+```bash
+pip install imgraft[vis]
+```
+
+---
+
+## Quick start
+
+### Python API
+
+```python
+from imgraft import Curator
+
+curator = Curator(model="ViT-B/32")   # or "ViT-L/14" for higher accuracy
+
+result = curator.run(
+    image_dir="./raw_images/",
+    keep_ratio=0.25,           # keep 25% of dataset
+    strategy="diversity",      # centroid | diversity | text-query | drop-noise
+    drop_noise=True,           # remove OOD/noise images
+)
+
+# ── verify clusters visually ───────────────────────────────────────────────────
+result.inspect(
+    output_dir="./cluster_grids/",   # one PNG contact sheet per cluster
+    n_per_side=5,                    # 5 centroid + 5 random thumbnails side by side
+)
+# open cluster_000.png, cluster_001.png etc. — visually verify before committing
+
+# ── export structured dataset ──────────────────────────────────────────────────
+result.export_clusters(
+    output_dir="./dataset/",
+    n_core=50,      # N most representative images per cluster
+    n_diverse=50,   # N most diverse images per cluster
+)
+
+# ── interactive UMAP explorer ──────────────────────────────────────────────────
+result.plot("clusters.html")   # hover any point to see the image
+
+print(result.stats())
+# {'total': 8211, 'kept': 1642, 'clusters': 47, 'noise': 312, ...}
+```
+
+### CLI
+
+```bash
+# basic — keep 25% using diversity sampling
+imgraft run ./images/ --keep 0.25 --out ./curated/
+
+# with interactive visualization
+imgraft run ./images/ --keep 0.25 --visualize --out ./curated/
+
+# filter by text query (zero-shot, no labels needed)
+imgraft run ./images/ \
+  --strategy text-query \
+  --query "a clear front-facing product photo on white background" \
+  --out ./curated/
+
+# drop noise/OOD images only, keep everything else
+imgraft run ./images/ --strategy drop-noise --out ./cleaned/
+
+# inspect dataset structure before curating
+imgraft info ./images/
+```
+
+---
+
+## Cluster inspection
+
+Before exporting your dataset, visually verify what each cluster contains:
+
+```python
+result.inspect(output_dir="./cluster_grids/", n_per_side=5)
+```
+
+Each PNG contact sheet shows **two sides**:
+
+| Left | Right |
+|---|---|
+| Core — closest to cluster centroid | Random sample from the cluster |
+
+Lets you spot bad clusters at a glance — if `cluster_003` is all blurry images or mislabeled examples, you know to drop it before training.
+
+---
+
+## Structured export
+
+```python
+result.export_clusters(
+    output_dir="./dataset/",
+    n_core=50,
+    n_diverse=50,
+)
+```
+
+Output layout:
+
+```
+dataset/
+  cluster_000/
+    core/           ← centroid-closest (most representative)
+    diverse/        ← furthest-point sampled (max variety)
+  cluster_001/
+    core/
+    diverse/
+  ...
+  noise/            ← all HDBSCAN outliers, isolated
+  export_summary.json
+```
+
+`core/` is best for training classifiers. `diverse/` maximises variety and removes near-duplicates. `noise/` gives a clean view of OOD images to review or discard.
+
+---
+
+## Curation strategies
+
+| Strategy | Best for | How it works |
+|---|---|---|
+| `diversity` | Removing near-duplicates, max variety | Greedy furthest-point sampling per cluster |
+| `centroid` | Balanced, representative subsets | Keeps images closest to each cluster center |
+| `text-query` | Domain-specific filtering, no labels | CLIP zero-shot similarity to a text prompt |
+| `drop-noise` | Quick clean without size reduction | Removes HDBSCAN outliers only |
+
+---
+
+## Works on any domain
+
+- **Web-scraped datasets** — deduplicate crawled images, remove OOD noise
+- **Medical imaging** — balance X-ray / pathology / dermoscopy class distributions
+- **Satellite / aerial** — curate geospatial image sets by region and content type
+- **E-commerce / products** — deduplicate product catalogs by visual similarity
+- **Industrial / manufacturing** — balance defect vs. normal in inspection datasets
+- **Document / form images** — group by layout type, sample representative subset
+- **General ML training prep** — quality control before sending to annotation
+
+---
+
+## Backbone options
+
+| Model | Embedding dim | Speed | Quality |
+|---|---|---|---|
+| `ViT-B/32` | 512 | ⚡ Fast | Good |
+| `ViT-B/16` | 512 | Medium | Better |
+| `ViT-L/14` | 768 | Slower | High |
+| `ViT-H/14` | 1024 | Slow | Highest |
+
+Switch with `--model ViT-L/14` or `Curator(model="ViT-L/14")`.
+
+---
+
+## Embedding cache
+
+Re-embedding large folders is slow. Cache embeddings to disk so reruns skip it:
+
+```bash
+imgraft run ./images/ --cache ./.imgraft_cache/ --keep 0.25
+```
+
+---
+
+## Visualizations
+
+**Interactive HTML** (`result.plot("clusters.html")`):
+- UMAP scatter colored by cluster
+- Hover any point → see the image thumbnail
+- Kept images at full opacity, dropped faded
+
+**Cluster grids** (`result.inspect("./grids/")`):
+- One PNG per cluster — centroid sample vs random sample side by side
+- Visual verification before committing to training
+
+---
+
+## License
+
+MIT

imgraft-0.1.0/README.md

@@ -0,0 +1,219 @@
+# imgraft
+
+**Semantic image dataset curation via CLIP + HDBSCAN.**
+
+[![PyPI version](https://badge.fury.io/py/imgraft.svg)](https://pypi.org/project/imgraft/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/)
+
+imgraft helps you clean, balance, and curate any messy image dataset — no labels, no manual annotation needed. Give it a folder of images and it returns a semantically balanced, deduplicated subset with full visualizations.
+
+---
+
+## How it works
+
+![imgraft pipeline](docs/pipeline.png)
+
+Five stages — all automatic:
+
+1. **Embed** — every image gets a CLIP vector (ViT-B/32 or ViT-L/14)
+2. **Cluster** — HDBSCAN finds semantic groups, UMAP pre-reduces for speed
+3. **Curate** — pick a strategy: centroid, diversity, or text-query filter
+4. **Inspect** — contact sheet PNGs per cluster for visual verification
+5. **Export** — structured `core/` + `diverse/` + `noise/` folders, ready for training
+
+---
+
+## Why imgraft?
+
+Raw image datasets are messy. Web scrapes contain near-duplicates. Crawled sets are class-imbalanced. Annotators mislabel. Training on noisy data silently destroys model performance.
+
+imgraft solves this using **semantic similarity** — it embeds every image with CLIP, discovers visual groups with HDBSCAN, and selects the best representatives per cluster. No domain assumptions. Works on any image type.
+
+> **Real-world impact**: On a production OCR project, an automated CLIP + HDBSCAN curation pipeline recovered model accuracy from 2% (after discovering 100K+ mislabeled images) to 90% on first retrain, reaching 95% through iteration.
+
+---
+
+## Install
+
+```bash
+pip install imgraft
+```
+
+For PNG visualization support:
+```bash
+pip install imgraft[vis]
+```
+
+---
+
+## Quick start
+
+### Python API
+
+```python
+from imgraft import Curator
+
+curator = Curator(model="ViT-B/32")   # or "ViT-L/14" for higher accuracy
+
+result = curator.run(
+    image_dir="./raw_images/",
+    keep_ratio=0.25,           # keep 25% of dataset
+    strategy="diversity",      # centroid | diversity | text-query | drop-noise
+    drop_noise=True,           # remove OOD/noise images
+)
+
+# ── verify clusters visually ───────────────────────────────────────────────────
+result.inspect(
+    output_dir="./cluster_grids/",   # one PNG contact sheet per cluster
+    n_per_side=5,                    # 5 centroid + 5 random thumbnails side by side
+)
+# open cluster_000.png, cluster_001.png etc. — visually verify before committing
+
+# ── export structured dataset ──────────────────────────────────────────────────
+result.export_clusters(
+    output_dir="./dataset/",
+    n_core=50,      # N most representative images per cluster
+    n_diverse=50,   # N most diverse images per cluster
+)
+
+# ── interactive UMAP explorer ──────────────────────────────────────────────────
+result.plot("clusters.html")   # hover any point to see the image
+
+print(result.stats())
+# {'total': 8211, 'kept': 1642, 'clusters': 47, 'noise': 312, ...}
+```
+
+### CLI
+
+```bash
+# basic — keep 25% using diversity sampling
+imgraft run ./images/ --keep 0.25 --out ./curated/
+
+# with interactive visualization
+imgraft run ./images/ --keep 0.25 --visualize --out ./curated/
+
+# filter by text query (zero-shot, no labels needed)
+imgraft run ./images/ \
+  --strategy text-query \
+  --query "a clear front-facing product photo on white background" \
+  --out ./curated/
+
+# drop noise/OOD images only, keep everything else
+imgraft run ./images/ --strategy drop-noise --out ./cleaned/
+
+# inspect dataset structure before curating
+imgraft info ./images/
+```
+
+---
+
+## Cluster inspection
+
+Before exporting your dataset, visually verify what each cluster contains:
+
+```python
+result.inspect(output_dir="./cluster_grids/", n_per_side=5)
+```
+
+Each PNG contact sheet shows **two sides**:
+
+| Left | Right |
+|---|---|
+| Core — closest to cluster centroid | Random sample from the cluster |
+
+Lets you spot bad clusters at a glance — if `cluster_003` is all blurry images or mislabeled examples, you know to drop it before training.
+
+---
+
+## Structured export
+
+```python
+result.export_clusters(
+    output_dir="./dataset/",
+    n_core=50,
+    n_diverse=50,
+)
+```
+
+Output layout:
+
+```
+dataset/
+  cluster_000/
+    core/           ← centroid-closest (most representative)
+    diverse/        ← furthest-point sampled (max variety)
+  cluster_001/
+    core/
+    diverse/
+  ...
+  noise/            ← all HDBSCAN outliers, isolated
+  export_summary.json
+```
+
+`core/` is best for training classifiers. `diverse/` maximises variety and removes near-duplicates. `noise/` gives a clean view of OOD images to review or discard.
+
+---
+
+## Curation strategies
+
+| Strategy | Best for | How it works |
+|---|---|---|
+| `diversity` | Removing near-duplicates, max variety | Greedy furthest-point sampling per cluster |
+| `centroid` | Balanced, representative subsets | Keeps images closest to each cluster center |
+| `text-query` | Domain-specific filtering, no labels | CLIP zero-shot similarity to a text prompt |
+| `drop-noise` | Quick clean without size reduction | Removes HDBSCAN outliers only |
+
+---
+
+## Works on any domain
+
+- **Web-scraped datasets** — deduplicate crawled images, remove OOD noise
+- **Medical imaging** — balance X-ray / pathology / dermoscopy class distributions
+- **Satellite / aerial** — curate geospatial image sets by region and content type
+- **E-commerce / products** — deduplicate product catalogs by visual similarity
+- **Industrial / manufacturing** — balance defect vs. normal in inspection datasets
+- **Document / form images** — group by layout type, sample representative subset
+- **General ML training prep** — quality control before sending to annotation
+
+---
+
+## Backbone options
+
+| Model | Embedding dim | Speed | Quality |
+|---|---|---|---|
+| `ViT-B/32` | 512 | ⚡ Fast | Good |
+| `ViT-B/16` | 512 | Medium | Better |
+| `ViT-L/14` | 768 | Slower | High |
+| `ViT-H/14` | 1024 | Slow | Highest |
+
+Switch with `--model ViT-L/14` or `Curator(model="ViT-L/14")`.
+
+---
+
+## Embedding cache
+
+Re-embedding large folders is slow. Cache embeddings to disk so reruns skip it:
+
+```bash
+imgraft run ./images/ --cache ./.imgraft_cache/ --keep 0.25
+```
+
+---
+
+## Visualizations
+
+**Interactive HTML** (`result.plot("clusters.html")`):
+- UMAP scatter colored by cluster
+- Hover any point → see the image thumbnail
+- Kept images at full opacity, dropped faded
+
+**Cluster grids** (`result.inspect("./grids/")`):
+- One PNG per cluster — centroid sample vs random sample side by side
+- Visual verification before committing to training
+
+---
+
+## License
+
+MIT

imgraft-0.1.0/imgraft.egg-info/PKG-INFO

@@ -0,0 +1,253 @@
+Metadata-Version: 2.4
+Name: imgraft
+Version: 0.1.0
+Summary: Semantic image dataset curation using CLIP + HDBSCAN
+License: MIT
+Project-URL: Homepage, https://github.com/dasarinikhil/imgraft
+Project-URL: Issues, https://github.com/dasarinikhil/imgraft/issues
+Keywords: clip,hdbscan,dataset-curation,computer-vision,image-deduplication,semantic-clustering,umap
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: torch>=2.0.0
+Requires-Dist: open-clip-torch>=2.20.0
+Requires-Dist: hdbscan>=0.8.33
+Requires-Dist: umap-learn>=0.5.3
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: Pillow>=10.0.0
+Requires-Dist: tqdm>=4.66.0
+Requires-Dist: rich>=13.7.0
+Requires-Dist: typer>=0.12.0
+Requires-Dist: plotly>=5.18.0
+Requires-Dist: scikit-learn>=1.3.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=5.0.0; extra == "dev"
+Provides-Extra: vis
+Requires-Dist: matplotlib>=3.8.0; extra == "vis"
+Requires-Dist: kaleido>=0.2.1; extra == "vis"
+Dynamic: license-file
+
+# imgraft
+
+**Semantic image dataset curation via CLIP + HDBSCAN.**
+
+[![PyPI version](https://badge.fury.io/py/imgraft.svg)](https://pypi.org/project/imgraft/)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/)
+
+imgraft helps you clean, balance, and curate any messy image dataset — no labels, no manual annotation needed. Give it a folder of images and it returns a semantically balanced, deduplicated subset with full visualizations.
+
+---
+
+## How it works
+
+![imgraft pipeline](docs/pipeline.png)
+
+Five stages — all automatic:
+
+1. **Embed** — every image gets a CLIP vector (ViT-B/32 or ViT-L/14)
+2. **Cluster** — HDBSCAN finds semantic groups, UMAP pre-reduces for speed
+3. **Curate** — pick a strategy: centroid, diversity, or text-query filter
+4. **Inspect** — contact sheet PNGs per cluster for visual verification
+5. **Export** — structured `core/` + `diverse/` + `noise/` folders, ready for training
+
+---
+
+## Why imgraft?
+
+Raw image datasets are messy. Web scrapes contain near-duplicates. Crawled sets are class-imbalanced. Annotators mislabel. Training on noisy data silently destroys model performance.
+
+imgraft solves this using **semantic similarity** — it embeds every image with CLIP, discovers visual groups with HDBSCAN, and selects the best representatives per cluster. No domain assumptions. Works on any image type.
+
+> **Real-world impact**: On a production OCR project, an automated CLIP + HDBSCAN curation pipeline recovered model accuracy from 2% (after discovering 100K+ mislabeled images) to 90% on first retrain, reaching 95% through iteration.
+
+---
+
+## Install
+
+```bash
+pip install imgraft
+```
+
+For PNG visualization support:
+```bash
+pip install imgraft[vis]
+```
+
+---
+
+## Quick start
+
+### Python API
+
+```python
+from imgraft import Curator
+
+curator = Curator(model="ViT-B/32")   # or "ViT-L/14" for higher accuracy
+
+result = curator.run(
+    image_dir="./raw_images/",
+    keep_ratio=0.25,           # keep 25% of dataset
+    strategy="diversity",      # centroid | diversity | text-query | drop-noise
+    drop_noise=True,           # remove OOD/noise images
+)
+
+# ── verify clusters visually ───────────────────────────────────────────────────
+result.inspect(
+    output_dir="./cluster_grids/",   # one PNG contact sheet per cluster
+    n_per_side=5,                    # 5 centroid + 5 random thumbnails side by side
+)
+# open cluster_000.png, cluster_001.png etc. — visually verify before committing
+
+# ── export structured dataset ──────────────────────────────────────────────────
+result.export_clusters(
+    output_dir="./dataset/",
+    n_core=50,      # N most representative images per cluster
+    n_diverse=50,   # N most diverse images per cluster
+)
+
+# ── interactive UMAP explorer ──────────────────────────────────────────────────
+result.plot("clusters.html")   # hover any point to see the image
+
+print(result.stats())
+# {'total': 8211, 'kept': 1642, 'clusters': 47, 'noise': 312, ...}
+```
+
+### CLI
+
+```bash
+# basic — keep 25% using diversity sampling
+imgraft run ./images/ --keep 0.25 --out ./curated/
+
+# with interactive visualization
+imgraft run ./images/ --keep 0.25 --visualize --out ./curated/
+
+# filter by text query (zero-shot, no labels needed)
+imgraft run ./images/ \
+  --strategy text-query \
+  --query "a clear front-facing product photo on white background" \
+  --out ./curated/
+
+# drop noise/OOD images only, keep everything else
+imgraft run ./images/ --strategy drop-noise --out ./cleaned/
+
+# inspect dataset structure before curating
+imgraft info ./images/
+```
+
+---
+
+## Cluster inspection
+
+Before exporting your dataset, visually verify what each cluster contains:
+
+```python
+result.inspect(output_dir="./cluster_grids/", n_per_side=5)
+```
+
+Each PNG contact sheet shows **two sides**:
+
+| Left | Right |
+|---|---|
+| Core — closest to cluster centroid | Random sample from the cluster |
+
+Lets you spot bad clusters at a glance — if `cluster_003` is all blurry images or mislabeled examples, you know to drop it before training.
+
+---
+
+## Structured export
+
+```python
+result.export_clusters(
+    output_dir="./dataset/",
+    n_core=50,
+    n_diverse=50,
+)
+```
+
+Output layout:
+
+```
+dataset/
+  cluster_000/
+    core/           ← centroid-closest (most representative)
+    diverse/        ← furthest-point sampled (max variety)
+  cluster_001/
+    core/
+    diverse/
+  ...
+  noise/            ← all HDBSCAN outliers, isolated
+  export_summary.json
+```
+
+`core/` is best for training classifiers. `diverse/` maximises variety and removes near-duplicates. `noise/` gives a clean view of OOD images to review or discard.
+
+---
+
+## Curation strategies
+
+| Strategy | Best for | How it works |
+|---|---|---|
+| `diversity` | Removing near-duplicates, max variety | Greedy furthest-point sampling per cluster |
+| `centroid` | Balanced, representative subsets | Keeps images closest to each cluster center |
+| `text-query` | Domain-specific filtering, no labels | CLIP zero-shot similarity to a text prompt |
+| `drop-noise` | Quick clean without size reduction | Removes HDBSCAN outliers only |
+
+---
+
+## Works on any domain
+
+- **Web-scraped datasets** — deduplicate crawled images, remove OOD noise
+- **Medical imaging** — balance X-ray / pathology / dermoscopy class distributions
+- **Satellite / aerial** — curate geospatial image sets by region and content type
+- **E-commerce / products** — deduplicate product catalogs by visual similarity
+- **Industrial / manufacturing** — balance defect vs. normal in inspection datasets
+- **Document / form images** — group by layout type, sample representative subset
+- **General ML training prep** — quality control before sending to annotation
+
+---
+
+## Backbone options
+
+| Model | Embedding dim | Speed | Quality |
+|---|---|---|---|
+| `ViT-B/32` | 512 | ⚡ Fast | Good |
+| `ViT-B/16` | 512 | Medium | Better |
+| `ViT-L/14` | 768 | Slower | High |
+| `ViT-H/14` | 1024 | Slow | Highest |
+
+Switch with `--model ViT-L/14` or `Curator(model="ViT-L/14")`.
+
+---
+
+## Embedding cache
+
+Re-embedding large folders is slow. Cache embeddings to disk so reruns skip it:
+
+```bash
+imgraft run ./images/ --cache ./.imgraft_cache/ --keep 0.25
+```
+
+---
+
+## Visualizations
+
+**Interactive HTML** (`result.plot("clusters.html")`):
+- UMAP scatter colored by cluster
+- Hover any point → see the image thumbnail
+- Kept images at full opacity, dropped faded
+
+**Cluster grids** (`result.inspect("./grids/")`):
+- One PNG per cluster — centroid sample vs random sample side by side
+- Visual verification before committing to training
+
+---
+
+## License
+
+MIT

imgraft-0.1.0/imgraft.egg-info/SOURCES.txt

@@ -0,0 +1,9 @@
+LICENSE
+README.md
+pyproject.toml
+imgraft.egg-info/PKG-INFO
+imgraft.egg-info/SOURCES.txt
+imgraft.egg-info/dependency_links.txt
+imgraft.egg-info/entry_points.txt
+imgraft.egg-info/requires.txt
+imgraft.egg-info/top_level.txt

imgraft-0.1.0/imgraft.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

imgraft-0.1.0/imgraft.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+imgraft = imgraft.cli:app

imgraft-0.1.0/imgraft.egg-info/requires.txt

@@ -0,0 +1,19 @@
+torch>=2.0.0
+open-clip-torch>=2.20.0
+hdbscan>=0.8.33
+umap-learn>=0.5.3
+numpy>=1.24.0
+Pillow>=10.0.0
+tqdm>=4.66.0
+rich>=13.7.0
+typer>=0.12.0
+plotly>=5.18.0
+scikit-learn>=1.3.0
+
+[dev]
+pytest>=8.0.0
+pytest-cov>=5.0.0
+
+[vis]
+matplotlib>=3.8.0
+kaleido>=0.2.1

imgraft-0.1.0/imgraft.egg-info/top_level.txt

@@ -0,0 +1 @@
+

imgraft-0.1.0/pyproject.toml

@@ -0,0 +1,50 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "imgraft"
+version = "0.1.0"
+description = "Semantic image dataset curation using CLIP + HDBSCAN"
+readme = "README.md"
+license = { text = "MIT" }
+requires-python = ">=3.9"
+keywords = [
+    "clip", "hdbscan", "dataset-curation", "computer-vision",
+    "image-deduplication", "semantic-clustering", "umap"
+]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Image Processing",
+]
+
+dependencies = [
+    "torch>=2.0.0",
+    "open-clip-torch>=2.20.0",
+    "hdbscan>=0.8.33",
+    "umap-learn>=0.5.3",
+    "numpy>=1.24.0",
+    "Pillow>=10.0.0",
+    "tqdm>=4.66.0",
+    "rich>=13.7.0",
+    "typer>=0.12.0",
+    "plotly>=5.18.0",
+    "scikit-learn>=1.3.0",
+]
+
+[project.optional-dependencies]
+dev = ["pytest>=8.0.0", "pytest-cov>=5.0.0"]
+vis = ["matplotlib>=3.8.0", "kaleido>=0.2.1"]   # static PNG export
+
+[project.urls]
+Homepage   = "https://github.com/dasarinikhil/imgraft"
+Issues     = "https://github.com/dasarinikhil/imgraft/issues"
+
+[project.scripts]
+imgraft = "imgraft.cli:app"
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["imgraft*"]

imgraft-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+