Downloads · 30 days
0
crossprism/efficientnetv2-21k-fv-m-tf
efficientnetv2-21k-fv-m-tf is a image feature extraction model from crossprism. Use it for the image feature extraction task on the model card, and read the license before you ship it in a product. It is set up for tf-keras. The card lists the license as apache-2.0.
EfficientnetV2 M model trained on ImageNet21k, input is a 480x480 image normalized to 0-1.0. Outputs a feature vector of size 1280.
Downloads · 30 days
0
Access
Public
Updated May 2, 2024
Repo size
223 MB
Likes
0
Public
Click a slice to open those files.
.data-00000-of-00001213 MB · 96%
From the Hugging Face model README
EfficientnetV2 M model trained on ImageNet21k, input is a 480x480 image normalized to 0-1.0. Outputs a feature vector of size 1280.
Copied from https://www.kaggle.com/models/google/efficientnet-v2/tensorFlow2/imagenet21k-m-feature-vector