Module google/‌imagenet/‌inception_resnet_v2/‌classification/1

Imagenet (ILSVRC-2012-CLS) classification with Inception ResNet V2.

Module URL: https://tfhub.dev/google/imagenet/inception_resnet_v2/classification/1

Overview

Inception ResNet V2 is a neural network architecture for image classification, originally published by

This TF-Hub module uses the TF-Slim implementation of inception_resnet_v2. The module contains a trained instance of the network, packaged to do the image classification that the network was trained on. If you merely want to transform images into feature vectors, use module google/imagenet/inception_resnet_v2/feature_vector/1 instead, and save the space occupied by the classification layer.

Training

The checkpoint exported into this module was inception_resnet_v2_2016_08_30/inception_resnet_v2_2016_08_30.ckpt downloaded from TF-Slim's pre-trained models. Its weights were originally obtained by training on the ILSVRC-2012-CLS dataset for image classification ("Imagenet").

Usage

This module implements the common signature for image classification. It can be used like

module = hub.Module("https://tfhub.dev/google/imagenet/inception_resnet_v2/classification/1")
height, width = hub.get_expected_image_size(module)
images = ...  # A batch of images with shape [batch_size, height, width, 3].
logits = module(images)  # Logits with shape [batch_size, num_classes].

...or using the signature name image_classification. The indices into logits are the num_classes = 1001 classes of the classification from the original training (see above).

This module can also be used to compute image feature vectors, using the signature name image_feature_vector.

For this module, the size of the input image is fixed to height x width = 299 x 299 pixels. The input images are expected to have color values in the range [0,1], following the common image input conventions.

Fine-tuning

In principle, consumers of this module can fine-tune it. However, fine-tuning through a large classification might be prone to overfit.

Fine-tuning requires importing the graph version with tag set {"train"} in order to operate batch normalization in training mode.