big-lama for Core ML, verified against the official weights

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 [2021] Samsung Research
+
+   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.

LaMa.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289f2c611bd3e52805ee3e686e290981d96d3b9674db93fe6bf30962f7e60d87
+size 1166404

LaMa.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b80614ec29e2362acc33cd4f37bb87574c07229fa378655fe2ada8c5be5a17bd
+size 204086656

LaMa.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "4C193088-7908-4A38-96B2-51F9DD98CAB9": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "874474C4-B3A3-472A-8AB1-A26370F1FFE5": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "4C193088-7908-4A38-96B2-51F9DD98CAB9"
+}

NOTICE

@@ -0,0 +1,9 @@
+LaMa: Resolution-robust Large Mask Inpainting with Fourier Convolutions
+Copyright Samsung AI Center / advimman. Licensed under the Apache License, Version 2.0 (LICENSE).
+Original code and weights: https://github.com/advimman/lama — weights "big-lama" from
+https://huggingface.co/smartywu/big-lama (the download the official README points to).
+
+This repository redistributes a Core ML conversion of big-lama (LaMa.mlpackage). The package
+was published without a licence statement at huggingface.co/jerhoads/lama-coreml (commit
+da9859ec149712a4bba6dfb2946f097b026bc8ec); its weights were verified here to be big-lama
+(see README.md and verify_against_official.py). The files are unmodified.

README.md

@@ -0,0 +1,32 @@
+---
+license: apache-2.0
+library_name: coreml
+pipeline_tag: image-to-image
+tags: [inpainting, lama, coreml, apple-silicon, object-removal]
+base_model: smartywu/big-lama
+---
+
+# LaMa (big-lama) for Core ML — object removal
+
+What `img erase` in the arraypress tools downloads: give it a picture and a mask of what to
+remove, and LaMa fills the hole plausibly. 800×800 image and mask in, image out; outside the
+mask the input passes through untouched.
+
+## Provenance and verification
+
+- **Weights:** big-lama from [advimman/lama](https://github.com/advimman/lama) (Apache-2.0),
+  via [smartywu/big-lama](https://huggingface.co/smartywu/big-lama) — the download the official
+  README gives (`curl -LJO https://huggingface.co/smartywu/big-lama/resolve/main/big-lama.zip`).
+- **This package:** the Core ML conversion published at `jerhoads/lama-coreml`
+  (commit `da9859ec149712a4bba6dfb2946f097b026bc8ec`), which states no licence of its own.
+  Re-hosted unmodified (file hashes identical) so the fleet does not depend on a third-party repo.
+- **Verified against the official weights** (`verify_against_official.py`): the original PyTorch
+  generator (`FFCResNetGenerator`, `models/best.ckpt`) and this package run on CPU on three
+  scenes (gradient + shapes, noise texture, a stock photo) × two masks:
+  - inside the mask: **58.9 dB PSNR** in every case — 8-bit rounding, i.e. the same model;
+  - outside the mask: identical to the input (max difference 0).
+- Conversion metadata: coremltools 7.2 from a TorchScript trace (torch 2.2.0), ML Program.
+
+## Licence
+
+Apache-2.0 — see `LICENSE` and `NOTICE`.

verify_against_official.py

@@ -0,0 +1,82 @@
+import sys, types, os, math
+import numpy as np, torch
+from PIL import Image, ImageDraw
+L = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, f'{L}/lama')
+# Stub the training-only imports so the generator module loads without kornia/lightning.
+st = types.ModuleType('saicinpainting.training.modules.spatial_transform')
+class LearnableSpatialTransformWrapper(torch.nn.Module): pass
+st.LearnableSpatialTransformWrapper = LearnableSpatialTransformWrapper
+sys.modules['saicinpainting.training.modules.spatial_transform'] = st
+ut = types.ModuleType('saicinpainting.utils')
+ut.get_shape = lambda t: tuple(t.shape)
+sys.modules['saicinpainting.utils'] = ut
+from saicinpainting.training.modules.ffc import FFCResNetGenerator
+
+gen = FFCResNetGenerator(4, 3, ngf=64, n_downsampling=3, n_blocks=18, add_out_act='sigmoid',
+                         init_conv_kwargs=dict(ratio_gin=0, ratio_gout=0, enable_lfu=False),
+                         downsample_conv_kwargs=dict(ratio_gin=0, ratio_gout=0, enable_lfu=False),
+                         resnet_conv_kwargs=dict(ratio_gin=0.75, ratio_gout=0.75, enable_lfu=False))
+import pickle
+class _Any(dict):
+    def __init__(self, *a, **k): pass
+    def __setstate__(self, state): pass
+class _Unpickler(pickle.Unpickler):
+    def find_class(self, module, name):
+        if module.startswith('pytorch_lightning') or module.startswith('lightning'):
+            return _Any
+        return super().find_class(module, name)
+_pm = types.ModuleType('lightning_free_pickle'); _pm.Unpickler = _Unpickler; _pm.load = pickle.load
+ck = torch.load(f'{L}/big-lama/models/best.ckpt', map_location='cpu', weights_only=False, pickle_module=_pm)
+sd = {k[len('generator.'):]: v for k, v in ck['state_dict'].items() if k.startswith('generator.')}
+missing, unexpected = gen.load_state_dict(sd, strict=True), None
+gen.eval()
+
+import coremltools as ct
+cm = ct.models.MLModel(f'{L}/tp/LaMa.mlpackage', compute_units=ct.ComputeUnit.CPU_ONLY)
+
+N = 800
+def scenes():
+    rng = np.random.default_rng(7)
+    # 1: smooth gradient with shapes
+    a = np.zeros((N, N, 3), np.float32)
+    yy, xx = np.mgrid[0:N, 0:N] / N
+    a[..., 0] = xx; a[..., 1] = yy; a[..., 2] = 0.5 + 0.5 * np.sin(6 * xx)
+    im = Image.fromarray((a * 255).astype(np.uint8)); d = ImageDraw.Draw(im)
+    d.ellipse([200, 200, 420, 420], fill=(240, 40, 40)); d.rectangle([500, 450, 700, 700], fill=(30, 30, 200))
+    yield 'gradient', im
+    # 2: noisy texture
+    yield 'texture', Image.fromarray((rng.random((N, N, 3)) * 80 + np.array([90, 140, 60])).astype(np.uint8))
+    # 3: a stock photo (Apple's User Pictures)
+    src = '/System/Library/Templates/Data/Library/User Pictures/Animals/Eagle.heic'
+    os.system(f"sips -s format png -z {N} {N} '{src}' --out {L}/eagle.png >/dev/null 2>&1")
+    yield 'eagle', Image.open(f'{L}/eagle.png').convert('RGB').resize((N, N))
+def masks():
+    m1 = Image.new('L', (N, N), 0); ImageDraw.Draw(m1).rectangle([250, 250, 480, 520], fill=255)
+    m2 = Image.new('L', (N, N), 0); ImageDraw.Draw(m2).ellipse([380, 120, 640, 340], fill=255)
+    return [('rect', m1), ('ellipse', m2)]
+
+def psnr(a, b, sel=None):
+    a = a.astype(np.float64); b = b.astype(np.float64)
+    if sel is not None: a, b = a[sel], b[sel]
+    mse = ((a - b) ** 2).mean()
+    return 99.0 if mse == 0 else 10 * math.log10(255 ** 2 / mse)
+
+for sname, img in scenes():
+    for mname, m in masks():
+        x = torch.from_numpy(np.asarray(img, np.float32) / 255).permute(2, 0, 1)[None]
+        mk = (torch.from_numpy(np.asarray(m, np.float32) / 255) > 0.5).float()[None, None]
+        with torch.no_grad():
+            out = gen(torch.cat([x * (1 - mk), mk], 1))
+        pt = (out[0].permute(1, 2, 0).numpy() * 255).clip(0, 255)
+        cmo = np.asarray(cm.predict({'image': img, 'mask': m})['output'].convert('RGB'), np.float32)
+        sel = np.asarray(m) > 127
+        # Inside the mask is what the model invents; outside, either may pass the input through.
+        print(f'{sname:9} {mname:8} PSNR inside mask {psnr(pt, cmo, sel):6.2f} dB | whole frame {psnr(pt, cmo):6.2f} dB')
+
+# Outside the mask, the package should pass the input through unchanged.
+for sname, img in scenes():
+    m = masks()[0][1]
+    cmo = np.asarray(cm.predict({'image': img, 'mask': m})['output'].convert('RGB'), np.float32)
+    sel = np.asarray(m) <= 127
+    print(f'{sname:9} outside mask vs input: PSNR {psnr(np.asarray(img, np.float32), cmo, sel):6.2f} dB, max diff {np.abs(np.asarray(img, np.float32)[sel] - cmo[sel]).max():.0f}')