image path fixes
This commit is contained in:
@@ -13,7 +13,7 @@ XAI:
|
||||
|
||||
I do research with phD student Katelyn Morrison, and learned about [her work with saliency mapping](https://cmu-vis-2021.github.io/Insightful-Saliency-Maps/), which is a visual way to show what areas of an image are most significant for ML classification.
|
||||
|
||||

|
||||

|
||||
|
||||
When I saw these maps, I immediately wondered if I could make art using ML classifications.
|
||||
|
||||
@@ -39,7 +39,7 @@ The core question my tool seeks to answer: *when a model classifies an image, wh
|
||||
|
||||
## How It Works
|
||||
|
||||

|
||||

|
||||
|
||||
|
||||
All seven supported models are **convolutional neural networks (CNNs)** trained on ImageNet, which is a dataset of 1.2 million images across 1,000 categories. The training process adjusts millions of numerical weights until the network can reliably distinguish between categories like "labrador retriever," "coffee," and "duck."
|
||||
@@ -498,15 +498,15 @@ The algorithms seem to struggle with classifying this image.
|
||||
|
||||
*croquet ball, goldfish, mailbox*
|
||||
|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||

|
||||
|
||||
Reference in New Issue
Block a user