960-endoscopy-inbody-classification-tutorial

README.md

@@ -204,6 +204,8 @@ This tutorial shows a straightforward ensemble application to instruct users on
 **computer_assisted_intervention**
 #### [video segmentation](./computer_assisted_intervention/video_seg.ipynb)
 This tutorial shows how to train a surgical tool segmentation model to locate tools in a given image. In addition, it also builds an example pipeline of an end-to-end video tool segmentation, with video input and video output.
+#### [endoscopic inbody classification](./computer_assisted_intervention/endoscopic_inbody_classification.ipynb)
+Tutorial to show the pipeline of fine tuning an endoscopic inbody classification model based on a corresponding pretrained bundle in monai model zoo.
 
 **modules**
 #### [bundle](./bundle)

computer_assisted_intervention/video_seg.ipynb

@@ -233,7 +233,9 @@
     "\n",
     "For the dataset, we use two instances of `VideoFileDataset`, one for the input video and the other for the ground truth segmentations. We create a `CombinedVidDataset` that enables us to iterate across these two at the same time.\n",
     "\n",
-    "The data loader is the standard."
+    "The data loader is a thread dataloader, which is able to accelerate inference and training.\n",
+    "\n",
+    "When videos cannot be opened by `VideoFileDataset`, check if python-opencv library is installed with ffmpeg. If not, please uninstall and reinstall python-opencv in your environment."
    ]
   },
   {
@@ -373,7 +375,7 @@
     "There is a pretrained bundle for surgical tool segmentation task in the MONAI model-zoo, the model can be automatically downloaded and loaded to the network by adding codes to the block below:\n",
     "```\n",
     "pretrained_weights = monai.bundle.load(\n",
-    "    name=\"surgical_tool_segmentation\", bundle_dir=\"./\", version=\"0.2.0\"\n",
+    "    name=\"endoscopic_tool_segmentation\", bundle_dir=\"./\", version=\"0.2.0\"\n",
     ")\n",
     "model.load_state_dict(pretrained_weights)\n",
     "```"
@@ -505,7 +507,7 @@
    "source": [
     "## Generating video\n",
     "\n",
-    "A video with masks will be generated by using the trained model to predict tool segmentation results."
+    "A video with masks will be generated by using the trained model to predict tool segmentation results. If cannot open video in notebook, please check saved video in local specified directory."
    ]
   },
   {