Upload 15 files

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model_farm_mediapipe_selfie_seg_qcs6490_qnn2.31_int8_aidlite/python/bus.jpg filter=lfs diff=lfs merge=lfs -text
+model_farm_mediapipe_selfie_seg_qcs6490_qnn2.31_w8a16_aidlite/python/bus.jpg filter=lfs diff=lfs merge=lfs -text
+model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_fp16_aidlite/python/bus.jpg filter=lfs diff=lfs merge=lfs -text
+model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_int8_aidlite/python/bus.jpg filter=lfs diff=lfs merge=lfs -text
+model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_w8a16_aidlite/python/bus.jpg filter=lfs diff=lfs merge=lfs -text

model_farm_mediapipe_selfie_seg_qcs6490_qnn2.31_int8_aidlite/README.md

@@ -0,0 +1,40 @@
+## Model Information
+
+### Source model
+- Input shape: [1x3x256x256]
+- Number of parameters: 0.11M
+- Model size: 0.65M
+- Output shape: [1x1x256x256]
+
+Source model repository: [Mediapipe-Selfie-Degmentation](https://github.com/google-ai-edge/mediapipe/tree/master/mediapipe/modules/selfie_segmentation)
+
+### Converted model
+
+- Precision: INT8
+- Backend: QNN2.31
+- Target Device: FV01 QCS6490
+
+## Inference with AidLite SDK
+
+### SDK installation
+Model Farm uses AidLite SDK as the model inference SDK. For details, please refer to the [AidLite Developer Documentation](https://v2.docs.aidlux.com/en/sdk-api/aidlite-sdk/)
+
+- Install AidLite SDK
+
+```bash
+# Install the appropriate version of the aidlite sdk
+sudo aid-pkg update
+sudo aid-pkg install aidlite-sdk
+# Download the qnn version that matches the above backend. Eg Install QNN2.23 Aidlite: sudo aid-pkg install aidlite-qnn223
+sudo aid-pkg install aidlite-{QNN VERSION}
+```
+
+- Verify AidLite SDK
+
+```bash
+# aidlite sdk c++ check
+python3 -c "import aidlite ; print(aidlite.get_library_version())"
+
+# aidlite sdk python check
+python3 -c "import aidlite ; print(aidlite.get_py_library_version())"
+```

model_farm_mediapipe_selfie_seg_qcs6490_qnn2.31_int8_aidlite/models/mediapipe_selfie_seg_w8a8.qnn231.ctx.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d2ef5aee45c54070db7fc5529d644d03b40191be81fedc7bd78275e73ea75b
+size 655672

model_farm_mediapipe_selfie_seg_qcs6490_qnn2.31_w8a16_aidlite/README.md

@@ -0,0 +1,40 @@
+## Model Information
+
+### Source model
+- Input shape: [1x3x256x256]
+- Number of parameters: 0.11M
+- Model size: 0.65M
+- Output shape: [1x1x256x256]
+
+Source model repository: [Mediapipe-Selfie-Degmentation](https://github.com/google-ai-edge/mediapipe/tree/master/mediapipe/modules/selfie_segmentation)
+
+### Converted model
+
+- Precision: W8A16
+- Backend: QNN2.31
+- Target Device: FV01 QCS6490
+
+## Inference with AidLite SDK
+
+### SDK installation
+Model Farm uses AidLite SDK as the model inference SDK. For details, please refer to the [AidLite Developer Documentation](https://v2.docs.aidlux.com/en/sdk-api/aidlite-sdk/)
+
+- Install AidLite SDK
+
+```bash
+# Install the appropriate version of the aidlite sdk
+sudo aid-pkg update
+sudo aid-pkg install aidlite-sdk
+# Download the qnn version that matches the above backend. Eg Install QNN2.23 Aidlite: sudo aid-pkg install aidlite-qnn223
+sudo aid-pkg install aidlite-{QNN VERSION}
+```
+
+- Verify AidLite SDK
+
+```bash
+# aidlite sdk c++ check
+python3 -c "import aidlite ; print(aidlite.get_library_version())"
+
+# aidlite sdk python check
+python3 -c "import aidlite ; print(aidlite.get_py_library_version())"
+```

model_farm_mediapipe_selfie_seg_qcs6490_qnn2.31_w8a16_aidlite/models/mediapipe_selfie_seg_w8a16.qnn231.ctx.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e73b85cc32ee176ad1b850f9174b1e1b154b0d2f789491c96775007e3415729
+size 672120

model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_fp16_aidlite/README.md

@@ -0,0 +1,40 @@
+## Model Information
+
+### Source model
+- Input shape: [1x3x256x256]
+- Number of parameters: 0.11M
+- Model size: 0.65M
+- Output shape: [1x1x256x256]
+
+Source model repository: [Mediapipe-Selfie-Degmentation](https://github.com/google-ai-edge/mediapipe/tree/master/mediapipe/modules/selfie_segmentation)
+
+### Converted model
+
+- Precision: FP16
+- Backend: QNN2.31
+- Target Device: SNM972 QCS8550
+
+## Inference with AidLite SDK
+
+### SDK installation
+Model Farm uses AidLite SDK as the model inference SDK. For details, please refer to the [AidLite Developer Documentation](https://v2.docs.aidlux.com/en/sdk-api/aidlite-sdk/)
+
+- Install AidLite SDK
+
+```bash
+# Install the appropriate version of the aidlite sdk
+sudo aid-pkg update
+sudo aid-pkg install aidlite-sdk
+# Download the qnn version that matches the above backend. Eg Install QNN2.23 Aidlite: sudo aid-pkg install aidlite-qnn223
+sudo aid-pkg install aidlite-{QNN VERSION}
+```
+
+- Verify AidLite SDK
+
+```bash
+# aidlite sdk c++ check
+python3 -c "import aidlite ; print(aidlite.get_library_version())"
+
+# aidlite sdk python check
+python3 -c "import aidlite ; print(aidlite.get_py_library_version())"
+```

model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_fp16_aidlite/models/mediapipe_selfie_seg_fp16.qnn231.ctx.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c655e19fe5f4f79d4bbfa292090016e7e381865479cc34c222f66c2815c5b09
+size 672712

model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_int8_aidlite/README.md

@@ -0,0 +1,40 @@
+## Model Information
+
+### Source model
+- Input shape: [1x3x256x256]
+- Number of parameters: 0.11M
+- Model size: 0.65M
+- Output shape: [1x1x256x256]
+
+Source model repository: [Mediapipe-Selfie-Degmentation](https://github.com/google-ai-edge/mediapipe/tree/master/mediapipe/modules/selfie_segmentation)
+
+### Converted model
+
+- Precision: INT8
+- Backend: QNN2.31
+- Target Device: SNM972 QCS8550
+
+## Inference with AidLite SDK
+
+### SDK installation
+Model Farm uses AidLite SDK as the model inference SDK. For details, please refer to the [AidLite Developer Documentation](https://v2.docs.aidlux.com/en/sdk-api/aidlite-sdk/)
+
+- Install AidLite SDK
+
+```bash
+# Install the appropriate version of the aidlite sdk
+sudo aid-pkg update
+sudo aid-pkg install aidlite-sdk
+# Download the qnn version that matches the above backend. Eg Install QNN2.23 Aidlite: sudo aid-pkg install aidlite-qnn223
+sudo aid-pkg install aidlite-{QNN VERSION}
+```
+
+- Verify AidLite SDK
+
+```bash
+# aidlite sdk c++ check
+python3 -c "import aidlite ; print(aidlite.get_library_version())"
+
+# aidlite sdk python check
+python3 -c "import aidlite ; print(aidlite.get_py_library_version())"
+```

model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_int8_aidlite/models/mediapipe_selfie_seg_w8a8.qnn231.ctx.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23282688cac4760dbd623e6e24ac489d830458feebf173a70751b08151c9fd7f
+size 303416

model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_w8a16_aidlite/README.md

@@ -0,0 +1,40 @@
+## Model Information
+
+### Source model
+- Input shape: [1x3x256x256]
+- Number of parameters: 0.11M
+- Model size: 0.65M
+- Output shape: [1x1x256x256]
+
+Source model repository: [Mediapipe-Selfie-Degmentation](https://github.com/google-ai-edge/mediapipe/tree/master/mediapipe/modules/selfie_segmentation)
+
+### Converted model
+
+- Precision: W8A16
+- Backend: QNN2.31
+- Target Device: SNM972 QCS8550
+
+## Inference with AidLite SDK
+
+### SDK installation
+Model Farm uses AidLite SDK as the model inference SDK. For details, please refer to the [AidLite Developer Documentation](https://v2.docs.aidlux.com/en/sdk-api/aidlite-sdk/)
+
+- Install AidLite SDK
+
+```bash
+# Install the appropriate version of the aidlite sdk
+sudo aid-pkg update
+sudo aid-pkg install aidlite-sdk
+# Download the qnn version that matches the above backend. Eg Install QNN2.23 Aidlite: sudo aid-pkg install aidlite-qnn223
+sudo aid-pkg install aidlite-{QNN VERSION}
+```
+
+- Verify AidLite SDK
+
+```bash
+# aidlite sdk c++ check
+python3 -c "import aidlite ; print(aidlite.get_library_version())"
+
+# aidlite sdk python check
+python3 -c "import aidlite ; print(aidlite.get_py_library_version())"
+```

model_farm_mediapipe_selfie_seg_qcs8550_qnn2.31_w8a16_aidlite/models/mediapipe_selfie_seg_w8a16.qnn231.ctx.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:776d16e54208f2d666d07b05dc4fe5970a0493714c546e8136652883e2cf2035
+size 348472