Feature vectors of images with Inception V2 trained on ImageNet (ILSVRC-2012-CLS).
Inception V2 is a neural network architecture for image classification. It builds on the Inception architecture originally published by
- Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke and Andrew Rabinovich: "Going deeper with convolutions", 2014.
Inception V2 uses are more powerful architecture made possible by the use of batch normalization. Both were introduced by
- Sergey Ioffe and Christian Szegedy: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, 2015.
This TF-Hub module uses the TF-Slim implementation of
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
The checkpoint exported into this module was
TF-Slim's pre-trained models.
Its weights were originally obtained by training on the ILSVRC-2012-CLS
dataset for image classification ("Imagenet").
This module implements the common signature for computing image feature vectors. It can be used like
module = hub.Module("https://tfhub.dev/google/imagenet/inception_v2/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 = 1024.
For this module, the size of the input image is fixed to
width = 224 x 224 pixels.
images are expected to have color values in the range [0,1],
common image input
Consumers of this module can fine-tune it.
This requires importing the graph version with tag set
in order to operate batch normalization in training mode.