removing quickstart project from mct (#1054)

* Remove quickstart project from mct
sony · May 8, 2024 · 98f771f · 98f771f
1 parent 9bf3ea7
commit 98f771f
Show file tree

Hide file tree

Showing 40 changed files with 63 additions and 3,782 deletions.
diff --git a/README.md b/README.md
@@ -45,9 +45,6 @@ for hands-on learning. For example:
 * [Post training quantization with PyTorch](tutorials/notebooks/pytorch/ptq/example_pytorch_quantization_mnist.ipynb)
 * [Data Generation for ResNet18 with PyTorch](tutorials/notebooks/pytorch/data_generation/example_pytorch_data_generation.ipynb).
 
-Additionally, for quick quantization of a variety of models from well-known collections,
-visit the [quick-start page](tutorials/quick_start/README.md) and the
-[results CSV](tutorials/quick_start/results/model_quantization_results.csv).
 
 ### Supported Versions
 

diff --git a/model_compression_toolkit/gptq/README.md b/model_compression_toolkit/gptq/README.md
@@ -17,7 +17,7 @@ The Hessian information is approximated in a label-free manner, thus, does not r
 
 ## GPTQ Usage
 
-For detailed examples and tutorials on using GPTQ in MCT with TensorFlow or PyTorch across various models and tasks, please refer to the [tutorials package](../../tutorials). You will find comprehensive explanations, notebook examples, and a [quick-start guide](../../tutorials/quick_start/README.md) for straightforward execution.
+For detailed examples and tutorials on using GPTQ in MCT with TensorFlow or PyTorch across various models and tasks, please refer to the [tutorials package](../../tutorials). You will find comprehensive explanations and notebook examples for straightforward execution.
 
 ## References
 

diff --git a/tutorials/notebooks/IMX500_notebooks.md b/tutorials/notebooks/IMX500_notebooks.md
@@ -3,10 +3,66 @@
 Here we provide examples on quantizing pre-trained models for deployment on Sony-IMX500 processing platform.
 We will cover various tasks and demonstrate the necessary steps to achieve efficient quantization for optimal
 deployment performance.
-
-  | Task                                                            | Model          | Source Repository                                                   | Notebook                                                                                                |
-  |-----------------------------------------------------------------|----------------|---------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------|
-  | Classification                                                  | MobileNetV2    | [Keras Applications](https://keras.io/api/applications/)            | [Keras notebook](keras/ptq/example_keras_imagenet.ipynb)         |
-  | Object Detection                                                | YOLOv8n        | [Ultralytics](https://github.com/ultralytics/ultralytics)           | [Keras notebook](keras/ptq/keras_yolov8n_for_imx500.ipynb)       | 
-  | Semantic Segmentation                                           | DeepLabV3-Plus | [bonlime's repo](https://github.com/bonlime/keras-deeplab-v3-plus)  | [Keras notebook](keras/ptq/keras_deeplabv3plus_for_imx500.ipynb) |
+
+<table>
+    <tr>
+        <th rowspan="1">Task</th>
+        <th rowspan="1">Model Name</th>
+        <th rowspan="1">Framework</th>
+        <th rowspan="1">Dataset Name</th>
+    </tr>
+    <!-- Classification Models (ImageNet) -->
+    <tr>
+        <td rowspan="2">Classification</td>
+        <td> <a href="keras/ptq/example_keras_imagenet.ipynb">MobilenetV2</a></td>
+        <td>Keras</td>
+        <td>ImageNet</td>
+    </tr>
+    <tr>
+        <td> <a href="pytorch/ptq/pytorch_mobilevit_xs_for_imx500.ipynb">MobileVit</a></td>
+        <td>PyTorch</td>
+        <td>ImageNet</td>
+    </tr>
+    <!-- Object Detection Models (COCO) -->
+    <tr>
+        <td rowspan="4">Object Detection</td>
+        <td> <a href="keras/ptq/keras_yolov8n_for_imx500.ipynb">YOLOv8n</a></td>
+        <td>Keras</td>
+        <td>COCO</td>
+    </tr>
+    <tr>
+        <td> <a href="pytorch/ptq/keras_yolov8n_for_imx500.ipynb">YOLOv8n</a></td>
+        <td>PyTorch</td>
+        <td>COCO</td>
+    </tr>
+    <tr>
+        <td> <a href="keras/ptq/example_keras_nanodet_plus.ipynb">NanoDet-Plus-m-416</a></td>
+        <td>Keras</td>
+        <td>COCO</td>
+    </tr>
+    <tr>
+        <td> <a href="keras/ptq/example_keras_effdet_lite0.ipynb">EfficientDet-lite0</a></td>
+        <td>Keras</td>
+        <td>COCO</td>
+    </tr>
+    <tr>
+        <td>Semantic Segmentation</td>
+        <td> <a href="keras/ptq/keras_deeplabv3plus_for_imx500.ipynb">Deeplabv3plus</a></td>
+        <td>Keras</td>
+        <td>PASCAL VOC</td>
+    </tr>
+    <tr>
+        <td >Instance Segmentation</td>
+        <td>YOLOv8n-seg</td>
+        <td>PyTorch</td>
+        <td>COCO</td>
+    </tr>
+    <tr>
+        <td>Pose Estimation</td>
+        <td>YOLOv8n-pose</td>
+        <td>PyTorch</td>
+        <td>COCO</td>
+    </tr>
+
+</table>
 
diff --git a/tutorials/notebooks/MCT_notebooks.md b/tutorials/notebooks/MCT_notebooks.md
@@ -69,16 +69,6 @@ These techniques are essential for further optimizing models and achieving super
 ### Pytorch Tutorials
 
 
-<details id="pytorch-quickstart-torchvision">
-  <summary>Quick-Start with Torchvision</summary>
-
-  | Tutorial                                                                                                        |
-  |-----------------------------------------------------------------------------------------------------------------|
-  | [Quick Start - Torchvision Pretrained Model](pytorch/example_quick_start_torchvision.ipynb) |
-
-</details>
-
-
 <details id="pytorch-ptq">
   <summary>Post-Training Quantization (PTQ)</summary>
 

diff --git a/tutorials/notebooks/pytorch/example_quick_start_torchvision.ipynb b/tutorials/notebooks/pytorch/example_quick_start_torchvision.ipynb