Module google/‌imagenet/‌resnet_v2_101/‌feature_vector/1

Feature vectors of images with ResNet V2 101 trained on ImageNet (ILSVRC-2012-CLS).

Module URL: https://tfhub.dev/google/imagenet/resnet_v2_101/feature_vector/1

Overview

ResNet V2 is a family of network architectures for image classification with a variable number of layers. It builds on the ResNet architecture originally published by

The full preactivation 'V2' variant of ResNet used in this module was introduced by

The key difference compared to ResNet V1 is the use of batch normalization before every weight layer.

This TF-Hub module uses the TF-Slim implementation of resnet_v2_101 with 101 layers. The module contains a trained instance of the network, packaged to get feature vectors from images. If you want the full model including the classification it was originally trained for, use module google/imagenet/resnet_v2_101/classification/1 instead.

Training

The checkpoint exported into this module was resnet_v2_101_2017_04_14/resnet_v2_101.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 computing image feature vectors. It can be used like

module = hub.Module("https://tfhub.dev/google/imagenet/resnet_v2_101/feature_vector/1")
height, width = hub.get_expected_image_size(module)
images = ...  # A batch of images with shape [batch_size, height, width, 3].
features = module(images)  # Features with shape [batch_size, num_features].

...or using the signature name image_feature_vector. The output for each image in the batch is a feature vector of size num_features = 2048.

For this module, the size of the input image is fixed to height x width = 224 x 224 pixels. The input images are expected to have color values in the range [0,1], following the common image input conventions.

Fine-tuning

Consumers of this module can fine-tune it. This requires importing the graph version with tag set {"train"} in order to operate batch normalization in training mode.