Downloads · 30 days
7
6% of all-time downloads
crossprism/travel_asia_landmarks
travel_asia_landmarks is a image classification model from crossprism. Use it when you need a label for an image. The card lists the license as apache-2.0.
Predicts Asia landmarks from a set of 12039 classes. Output is logits.
Downloads · 30 days
7
6% of all-time downloads
All-time downloads
120
Public
Repo size
46.9 MB
Likes
1
Public
Click a slice to open those files.
.mlmodel15.8 MB · 100%
From the Hugging Face model README
Predicts Asia landmarks from a set of 12039 classes. Output is logits.
Trained on data from: https://github.com/cvdfoundation/google-landmark
Classification head built on top of EfficentnetV2-M-21k feature extractor for CrossPrism on MacOS.
Compressed using 8-bit quantization.