Methods and systems for visual representation of model performance
Disclosed herein at methods and systems for visualizing machine learning model performance. One method comprises receiving a request to provide a visual representation of a machine learning technique executed on a set of images to generate a first attribute and a second attribute for each image; executing the machine learning model to receive the first and the second attribute for each image; mapping the first attribute to a visual distinctiveness protocol; identifying a distance for each image, the distance representing a difference between the second attribute predicted by the model for each pair of respective images within the set of images; and providing for display at least a subset of the set of images arranged in accordance with their respective distance and having a visual attribute corresponding to the mapped first attribute for each image.
1. A method, comprising:
receiving, by a data processing system comprising one or more processors and memory, a request to provide a visual representation of a machine learning technique executed on a set of images to generate a first attribute and a second attribute for each image;
executing, by the data processing system, the machine learning model to receive the first and the second attribute for each image;
mapping, by the data processing system, the first attribute to a visual distinctiveness protocol;
identifying, by the data processing system, a distance for each image, the distance representing a difference between the second attribute predicted by the model for each pair of respective images within the set of images; and
providing for display, by the data processing system, at least a subset of the set of images arranged in accordance with their respective distance and having a visual attribute corresponding to the mapped first attribute for each image.
2. The method of claim 1 , wherein visual distinctiveness protocol corresponds to a color spectrum.
3. The method of claim 2 , wherein the visual attribute corresponds to a colored border for at least one image where the color is selected based on the color spectrum.
4. The method of claim 1 , wherein visual distinctiveness protocol corresponds to different shapes selected based on the first attribute.
5. The method of claim 1 , wherein the subset of the set of images are selected based on a prediction threshold.
6. The method of claim 1 , wherein the subset of the set of images are selected based on a known attribute associated with the set of images.
7. The method of claim 1 , wherein the machine learning technique corresponds to at least one of a binary technique, a classification technique, a regression technique, a clustering technique, a multi-class technique, or a multi-labeling technique.
8. The method of claim 1 , further comprising:
providing for display, by the data processing system, an input element configured to receive a feedback value.
9. The method of claim 1 , further comprising:
providing for display, by the data processing system, an activation map associated with the subset of the set of images.
10. A computer system comprising:
a server having one or more processors configured to:
receive a request to provide a visual representation of a machine learning technique executed on a set of images to generate a first attribute and a second attribute for each image;
execute the machine learning model to receive the first and the second attribute for each image;
map the first attribute to a visual distinctiveness protocol;
identify a distance for each image, the distance representing a difference between the second attribute predicted by the model for each pair of respective images within the set of images; and
provide for display at least a subset of the set of images arranged in accordance with their respective distance and having a visual attribute corresponding to the mapped first attribute for each image.
11. The system of claim 10 , wherein visual distinctiveness protocol corresponds to a color spectrum.
12. The system of claim 11 , wherein the visual attribute corresponds to a colored border for at least one image where the color is selected based on the color spectrum.
13. The system of claim 10 , wherein visual distinctiveness protocol corresponds to different shapes selected based on the first attribute.
14. The system of claim 10 , wherein the subset of the set of images are selected based on a prediction threshold.
15. The system of claim 10 , wherein the subset of the set of images are selected based on a known attribute associated with the set of images.
16. The system of claim 10 , wherein the machine learning technique corresponds to at least one of a binary technique, a classification technique, a regression technique, a clustering technique, a multi-class technique, or a multi-labeling technique.
17. The system of claim 10 , wherein the server is further configured to:
provide for display an input element configured to receive a feedback value.
18. The system of claim 10 , wherein the server is further configured to:
provide for display an activation map associated with the subset of the set of images.
19. A computer system comprising:
a server comprising a processor and a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform operations comprising:
receiving a request to provide a visual representation of a machine learning technique executed on a set of images to generate a first attribute and a second attribute for each image;
executing the machine learning model to receive the first and the second attribute for each image;
mapping, by the data processing system, the first attribute to a visual distinctiveness protocol;
identifying a distance for each image, the distance representing a difference between the second attribute predicted by the model for each pair of respective images within the set of images; and
providing for display at least a subset of the set of images arranged in accordance with their respective distance and having a visual attribute corresponding to the mapped first attribute for each image.
20. The system of claim 19 , wherein the machine learning technique corresponds to at least one of a binary technique, a classification technique, a regression technique, a clustering technique, a multi-class technique, or a multi-labeling technique.