Upload folder using huggingface_hub

README.md

@@ -0,0 +1,36 @@
+---
+license: apache-2.0
+pipeline_tag: mask-generation
+library_name: coreml
+---
+
+# SAM 2.1 BasePlus Core ML
+
+SAM 2 (Segment Anything in Images and Videos), is a collection of foundation models from FAIR that aim to solve promptable visual segmentation in images and videos. See the [SAM 2 paper](https://arxiv.org/abs/2408.00714) for more information.
+
+This is the Core ML version of [SAM 2.1 BasePlus](https://huggingface.co/facebook/sam2.1-hiera-base-plus), and is suitable for use with the [SAM2 Studio demo app](https://github.com/huggingface/sam2-studio). It was converted in `float16` precision using [this fork](https://github.com/huggingface/segment-anything-2/tree/coreml-conversion) of the original code repository.
+
+## Download
+
+Install `huggingface-cli`
+
+```bash
+brew install huggingface-cli
+```
+
+```bash
+huggingface-cli download --local-dir models apple/coreml-sam2.1-baseplus
+```
+
+## Citation
+
+To cite the paper, model, or software, please use the below:
+```
+@article{ravi2024sam2,
+  title={SAM 2: Segment Anything in Images and Videos},
+  author={Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan-Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and R{\"a}dle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao-Yuan and Girshick, Ross and Doll{\'a}r, Piotr and Feichtenhofer, Christoph},
+  journal={arXiv preprint arXiv:2408.00714},
+  url={https://arxiv.org/abs/2408.00714},
+  year={2024}
+}
+```

SAM2_1BasePlusImageEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be81ebd5fd3abee3b6db88723f0210791a12f3d4a408647fd0772b09129167d1
+size 298613

SAM2_1BasePlusImageEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809c1b82d3a4400f80c5bf88d2a3f98f2a0b183d1e89ff14c2a64b31f20ffe8d
+size 152949760

SAM2_1BasePlusImageEncoderFLOAT16.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "07FDDAFC-A066-4211-88D1-CBAFF79CC4E4": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "E4008E08-FCC6-49CE-836C-7492F71E0C57": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "07FDDAFC-A066-4211-88D1-CBAFF79CC4E4"
+}

SAM2_1BasePlusMaskDecoderFLOAT16.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b450f1639ec27c8cd01f4c0617c9bf6b0c3f7cc26b556cb1939944d0251168fb
+size 75167

SAM2_1BasePlusMaskDecoderFLOAT16.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809bf07f9e80fca055faf92b536c3f5f8d244f2258d9e16303206c9ba124f1e5
+size 10222400

SAM2_1BasePlusMaskDecoderFLOAT16.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "839D907D-632D-4D54-9104-A0D65AEE372D": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        },
+        "F1949ACC-5666-4411-952D-0D497069EEE4": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        }
+    },
+    "rootModelIdentifier": "839D907D-632D-4D54-9104-A0D65AEE372D"
+}

SAM2_1BasePlusPromptEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/model.mlmodel

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a83c167d8bd63e80f86349a78c2ab0527ce97eca1f848a4ce57fe5351241fa3
+size 20618

SAM2_1BasePlusPromptEncoderFLOAT16.mlpackage/Data/com.apple.CoreML/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca8d97076ef4817ce3804c84398bd7fc1ac8f61008ff07eb4ca39727d394bbb6
+size 2101056

SAM2_1BasePlusPromptEncoderFLOAT16.mlpackage/Manifest.json

@@ -0,0 +1,18 @@
+{
+    "fileFormatVersion": "1.0.0",
+    "itemInfoEntries": {
+        "976BA78F-A552-49FA-A0CA-CDC8A0ABE849": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Weights",
+            "name": "weights",
+            "path": "com.apple.CoreML/weights"
+        },
+        "A8D91659-CDFE-4704-873E-7B01246188F0": {
+            "author": "com.apple.CoreML",
+            "description": "CoreML Model Specification",
+            "name": "model.mlmodel",
+            "path": "com.apple.CoreML/model.mlmodel"
+        }
+    },
+    "rootModelIdentifier": "A8D91659-CDFE-4704-873E-7B01246188F0"
+}