[RedSuns Review] Change tpc API in pytorch tutorials.

tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_activation_threshold_search.ipynb

@@ -219,7 +219,7 @@
    },
    "source": [
     "## Target Platform Capabilities\n",
-    "MCT optimizes the model for dedicated hardware. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the default Tensorflow TPC:"
+    "MCT optimizes the model for dedicated hardware. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the TPC object for imx500 hardware with version 1.0:"
    ]
   },
   {
@@ -233,8 +233,8 @@
    "source": [
     "import model_compression_toolkit as mct\n",
     "\n",
-    "# Get a TargetPlatformCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the default platform that is attached to a Pytorch layers representation.\n",
-    "target_platform_cap = mct.get_target_platform_capabilities('pytorch', 'default')"
+    "# Get a TargetPlatformCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the TPC object for imx500 hardware with version 1.0.\n",
+    "target_platform_cap = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -749,7 +749,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "torch1 (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },

tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_activation_z_score_threshold.ipynb

@@ -232,7 +232,7 @@
    },
    "source": [
     "## Target Platform Capabilities\n",
-    "MCT optimizes the model for dedicated hardware. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the default Torch TPC:"
+    "MCT optimizes the model for dedicated hardware. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the TPC object for imx500 hardware with version 1.0:"
    ]
   },
   {
@@ -246,8 +246,8 @@
    "source": [
     "import model_compression_toolkit as mct\n",
     "\n",
-    "# Get a TargetPlatformCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the default platform that is attached to a Pytorch layers representation.\n",
-    "target_platform_cap = mct.get_target_platform_capabilities('pytorch', 'default')"
+    "# Get a TargetPlatformCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the TPC object for imx500 hardware with version 1.0.\n",
+    "target_platform_cap = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -753,7 +753,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "torch2 (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },

tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_data_generation.ipynb

@@ -220,7 +220,7 @@
     "In order to evaulate our generated images, we will use them to quantize the model using MCT's PTQ.This is referred to as **\"Zero-Shot Quantization (ZSQ)\"** or **\"Data-Free Quantization\"** because no real data is used in the quantization process. Next we will define configurations for MCT's PTQ.\n",
     "\n",
     "### Target Platform Capabilities (TPC)\n",
-    "MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the default Pytorch TPC:"
+    "MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the TPC object for imx500 hardware with version 1.0:"
    ]
   },
   {
@@ -232,7 +232,7 @@
    },
    "outputs": [],
    "source": [
-    "target_platform_cap = mct.get_target_platform_capabilities(\"pytorch\", \"default\")"
+    "target_platform_cap = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {

tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_mixed_precision_ptq.ipynb

@@ -183,7 +183,8 @@
    "source": [
     "## Target Platform Capabilities (TPC)\n",
     "In addition, MCT optimizes models for dedicated hardware platforms using Target Platform Capabilities (TPC). \n",
-    "**Note:**  To apply mixed-precision quantization to specific layers, the TPC must define different bit-width options for those layers. For more details, please refer to our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html). In this example, we use the default PyTorch TPC, which supports 2, 4, and 8-bit options for convolution and linear layers."
+    "\n",
+    "**Note:**  To apply mixed-precision quantization to specific layers, the TPC must define different bit-width options for those layers. For more details, please refer to our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html). In this example, we use the TPC object for imx500 hardware with version 1.0, which supports 2, 4, and 8-bit options for convolution and linear layers."
    ]
   },
   {
@@ -197,8 +198,8 @@
    "source": [
     "import model_compression_toolkit as mct\n",
     "\n",
-    "# Get a FrameworkQuantizationCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the default platform that is attached to a Pytorch layers representation.\n",
-    "target_platform_cap = mct.get_target_platform_capabilities('pytorch', 'default')"
+    "# Get a TargetPlatformCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the TPC object for imx500 hardware with version 1.0.\n",
+    "target_platform_cap = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -451,7 +452,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "torch6 (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },

tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_mobilenet_gptq.ipynb

@@ -223,7 +223,7 @@
     "gptq_config = mct.gptq.get_pytorch_gptq_config(n_epochs=50)\n",
     "\n",
     "# Specify the target platform capability (TPC)\n",
-    "tpc = mct.get_target_platform_capabilities(\"pytorch\", 'imx500', target_platform_version='v1')"
+    "tpc = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -432,7 +432,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "torch7 (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },

tutorials/notebooks/mct_features_notebooks/pytorch/example_pytorch_post_training_quantization.ipynb

@@ -182,7 +182,7 @@
    },
    "source": [
     "## Target Platform Capabilities (TPC)\n",
-    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the default Pytorch TPC:"
+    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the TPC object for imx500 hardware with version 1.0:"
    ]
   },
   {
@@ -196,8 +196,8 @@
    "source": [
     "import model_compression_toolkit as mct\n",
     "\n",
-    "# Get a FrameworkQuantizationCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the default platform that is attached to a Pytorch layers representation.\n",
-    "target_platform_cap = mct.get_target_platform_capabilities('pytorch', 'default')"
+    "# Get a TargetPlatformCapabilities object that models the hardware platform for the quantized model inference. Here, for example, we use the TPC object for imx500 hardware with version 1.0.\n",
+    "target_platform_cap = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -403,7 +403,7 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "torch8 (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },

tutorials/notebooks/task_notebooks/pytorch/example_deeplabv3p_pytorch_mixed_precision_ptq.ipynb

@@ -344,7 +344,7 @@
    "metadata": {},
    "source": [
     "## Target Platform Capabilities (TPC)\n",
-    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the default Pytorch TPC:"
+    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the TPC object for imx500 hardware with version 1.0:"
    ]
   },
   {
@@ -356,7 +356,7 @@
    "source": [
     "import model_compression_toolkit as mct\n",
     "\n",
-    "tpc = mct.get_target_platform_capabilities('pytorch', 'default')"
+    "tpc = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -533,7 +533,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "py310-deeplabv3ptest (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },

tutorials/notebooks/task_notebooks/pytorch/example_posenet_pytorch_mixed_precision_ptq.ipynb

@@ -562,7 +562,7 @@
    "metadata": {},
    "source": [
     "## Target Platform Capabilities (TPC)\n",
-    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the default Pytorch TPC:"
+    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the TPC object for imx500 hardware with version 1.0:"
    ]
   },
   {
@@ -574,7 +574,7 @@
    "source": [
     "import model_compression_toolkit as mct\n",
     "\n",
-    "tpc = mct.get_target_platform_capabilities('pytorch', 'default')"
+    "tpc = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -806,7 +806,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "torch12 (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },

tutorials/notebooks/task_notebooks/pytorch/example_yolox_pytorch_mixed_precision_ptq.ipynb

@@ -530,7 +530,7 @@
    "metadata": {},
    "source": [
     "## Target Platform Capabilities (TPC)\n",
-    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the default Pytorch TPC:"
+    "In addition, MCT optimizes the model for dedicated hardware platforms. This is done using TPC (for more details, please visit our [documentation](https://sonysemiconductorsolutions.github.io/mct-model-optimization/api/api_docs/modules/target_platform_capabilities.html)). Here, we use the TPC object for imx500 hardware with version 1.0:"
    ]
   },
   {
@@ -540,7 +540,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "tpc = mct.get_target_platform_capabilities('pytorch', 'default')"
+    "tpc = mct.get_target_platform_capabilities(tpc_version='1.0', device_type='imx500')"
    ]
   },
   {
@@ -738,7 +738,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "torch13 (3.10.12)",
+   "display_name": "py310-mct251_tpc (3.10.12)",
    "language": "python",
    "name": "python3"
   },