Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

correct headers levels in tutorials #225

Merged
merged 1 commit into from
Feb 11, 2022
Merged

correct headers levels in tutorials #225

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions tutorials/kernelshap_geometric_shapes.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
"source": [
"<img width=\"150\" alt=\"Logo_ER10\" src=\"https://user-images.githubusercontent.com/3244249/151994514-b584b984-a148-4ade-80ee-0f88b0aefa45.png\">\n",
"\n",
"## Model Interpretation for Pretrained Model to Recognize Geometric Shapes using KernelSHAP\n",
"### Model Interpretation for Pretrained Model to Recognize Geometric Shapes using KernelSHAP\n",
"\n",
"This notebook demonstrates how to apply the KernelSHAP explainability method on a pretrained model used to classify geometric shapes. The relevance attributions for each pixel/super-pixel are visualized by displaying them on the image. <br>\n",
"\n",
Expand Down Expand Up @@ -36,7 +36,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1 - Loading the model and the dataset\n",
"#### 1 - Loading the model and the dataset\n",
"Loads pretrained model and the image to be explained."
]
},
Expand Down Expand Up @@ -282,7 +282,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3 - Conclusions\n",
"#### 3 - Conclusions\n",
"The Shapley scores are estimated using KernelSHAP. The example here shows that the KernelSHAP method evaluates the importance of each segmentations/super pixels to the classification of geometric shapes and the results are a bit difficult to interpret based on human visual preception of the chosen testing circle image."
]
}
Expand Down
4 changes: 2 additions & 2 deletions tutorials/kernelshap_mnist.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
"source": [
"<img width=\"150\" alt=\"Logo_ER10\" src=\"https://user-images.githubusercontent.com/3244249/151994514-b584b984-a148-4ade-80ee-0f88b0aefa45.png\">\n",
"\n",
"## Model Interpretation for Pretrained Binary MNIST Model using KernelSHAP\n",
"### Model Interpretation for Pretrained Binary MNIST Model using KernelSHAP\n",
"\n",
"This notebook demonstrates how to apply KernelSHAP method on pretrained binary MNIST model using a hand-written digit image. It visualizes the relevance attributions for each pixel/super-pixel by displaying them on the image. <br>\n",
"\n",
Expand Down Expand Up @@ -36,7 +36,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1 - Loading the model and the dataset\n",
"#### 1 - Loading the model and the dataset\n",
"Loads pretrained binary MNIST model and the image to be explained."
]
},
Expand Down
4 changes: 2 additions & 2 deletions tutorials/rise_imagenet.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
"source": [
"<img width=\"150\" alt=\"Logo_ER10\" src=\"https://user-images.githubusercontent.com/3244249/151994514-b584b984-a148-4ade-80ee-0f88b0aefa45.png\">\n",
"\n",
"## Model Interpretation for Pretrained ImageNet Model using RISE\n",
"### Model Interpretation for Pretrained ImageNet Model using RISE\n",
"\n",
"This notebook demonstrates how to apply the RISE explainability method on pretrained ImageNet model using a bee image. It visualizes the relevance scores for all pixels/super-pixels by displaying them on the image.<br>\n",
"\n",
Expand Down Expand Up @@ -43,7 +43,7 @@
"id": "1e3de949",
"metadata": {},
"source": [
"## 1 - Loading the model and the dataset\n",
"#### 1 - Loading the model and the dataset\n",
"Loads pretrained ImageNet model and the image to be explained."
]
},
Expand Down
4 changes: 2 additions & 2 deletions tutorials/rise_mnist.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
"source": [
"<img width=\"150\" alt=\"Logo_ER10\" src=\"https://user-images.githubusercontent.com/3244249/151994514-b584b984-a148-4ade-80ee-0f88b0aefa45.png\">\n",
"\n",
"## Model Interpretation for Binary MNIST Model using RISE\n",
"### Model Interpretation for Binary MNIST Model using RISE\n",
"\n",
"This notebook demonstrates how to apply the RISE explainability method on a pretrained binary MNIST model using a hand-written digit image. It visualizes the relevance attributions for each pixel/super-pixel by displaying them on top of the input image.<br>\n",
"\n",
Expand Down Expand Up @@ -39,7 +39,7 @@
"id": "4230e223",
"metadata": {},
"source": [
"## 1 - Loading the model and the dataset\n",
"#### 1 - Loading the model and the dataset\n",
"Loads pretrained binary MNIST model and the image to be explained."
]
},
Expand Down