You're looking at a specific version of this model. Jump to the model overview.

arielreplicate /gscorecam-clip-analyzer:fa04b849

Input schema

The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.

Field Type Default value Description
input_image
string
Path to an image to investigate clip on
input_text
string
An object
What to look for in the image
clip_version
string (enum)
RN50x16

Options:

RN50x16, ViT-B/32

name of the clip model
cam_version
string (enum)
gscorecam

Options:

ablationcam, eigencam, eigengradcam, gradcam, gradcam++, gradientcam, groupcam, gscorecam, gscorecambeta, hilacam, layercam, rawcam, rise, scorecam, sscam1, sscam2, testcam, testhila, vitgradcam, xgradcam

Which base gradient saliency method to use. You should use 'gscorecam'. Other methods serve as reference for the improvement of this method
topk
integer
300

Min: 1

Max: 3072

Number of channels used by gscorecam

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'format': 'uri', 'title': 'Output', 'type': 'string'}