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
- Downloads last month
- 0
Inference API (serverless) does not yet support tf-keras models for this pipeline type.