The efficientnet-b7_auto_aug
model is one of the EfficientNet models designed to perform image classification, trained with the AutoAugmentation preprocessing. This model was pretrained in TensorFlow*. All the EfficientNet models have been pretrained on the ImageNet* image database. For details about this family of models, check out the TensorFlow Cloud TPU repository.
Metric | Value |
---|---|
Type | Classification |
GFLOPs | 77.618 |
MParams | 66.193 |
Source framework | TensorFlow* |
Metric | Original model | Converted model |
---|---|---|
Top 1 | 84.68% | 84.68% |
Top 5 | 97.09% | 97.09% |
Image, name - image
, shape - [1x600x600x3]
, format is [BxHxWxC]
where:
B
- batch sizeH
- heightW
- widthC
- channelChannel order is RGB
.
Image, name - sub/placeholder_port_0
, shape - [1x600x600x3]
, format is [BxHxWxC]
where:
B
- batch sizeH
- heightW
- widthC
- channelChannel order is BGR
.
Object classifier according to ImageNet classes, name - logits
, shape - 1,1000
, output data format is B,C
where:
B
- batch sizeC
- predicted probabilities for each class in the logits formatObject classifier according to ImageNet classes, name - efficientnet-b7/model/head/dense/MatMul
, shape - 1,1000
, output data format is B,C
where:
B
- batch sizeC
- predicted probabilities for each class in the logits formatThe original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in APACHE-2.0-TF-TPU.txt.