netvlad-tf

Use Case and High-Level Description

NetVLAD is a CNN architecture which tackles the problem of large scale visual place recognition. The architecture uses VGG 16 as base network and NetVLAD - a new trainable generalized VLAD (Vector of Locally Aggregated Descriptors) layer. It is a place recognition model pre-trained on the Pittsburgh 250k dataset.

For details see repository and paper.

Specification

Metric

Value

Type

Place recognition

GFLOPs

36.6374

MParams

149.0021

Source framework

TensorFlow*

Accuracy

Accuracy metrics are obtained on a smaller validation subset of Pittsburgh 250k dataset (Pitts30k) containing 10k database images in each set (train/test/validation). Images were resized to input size.

Metric

Value

localization_recall

82.0321%

Input

Original model

Image, name - Placeholder, shape - 1, 200, 300, 3, format is B, H, W, C, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Channel order is RGB.

Converted model

Image, name - Placeholder, shape - 1, 3, 200, 300, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Channel order is BGR.

Output

Original model

Floating point embeddings, name - vgg16_netvlad_pca/l2_normalize_1, shape - 1, 4096, output data format - B, C, where:

  • B - batch size

  • C - vector of 4096 floating points values, local image descriptors

Converted model

Floating point embeddings, name - vgg16_netvlad_pca/l2_normalize_1, shape - 1, 4096, output data format - B, C, where:

  • B - batch size

  • C - vector of 4096 floating points values, local image descriptors

Download a Model and Convert it into Inference Engine Format

You can download models and if necessary convert them into Inference Engine format using the Model Downloader and other automation tools as shown in the examples below.

An example of using the Model Downloader:

python3 <omz_dir>/tools/downloader/downloader.py --name <model_name>

An example of using the Model Converter:

python3 <omz_dir>/tools/downloader/converter.py --name <model_name>