insikk / delf_enhanced

Wrapper of DELF Tensorflow Model

DELF: DEep Local Features

This project is wrapper of DELF Tensorflow code (introduced in the paper "Large-Scale Image Retrieval with Attentive Deep Local Features") which is more easy to use for below reasons:

• No bell and whistle for setup. All required packages are prepared.

• Modularized code. You can easily import as python package from any of your fantastic project.

  • Get Local Descriptors from any image
  • Get Attention Image, so you can see why the DELFs are selected
  • Get Matching Image, so you can see why the image pair has high score

• You also can load weight on a model build with its code.

  • You now have full access on any tensors in the graph, such as attention
  • You can play with code level instead of just reproducing with exported model.

What is DELF? Why is it good?

According to README in DELF Tensorflow code

DELF is particularly useful for large-scale instance-level image recognition. It detects and describes semantic local features which can be geometrically verified between images showing the same object instance. The pre-trained model released here has been optimized for landmark recognition, so expect it to work well in this area.

Matching, Attention Image Samples

Image in Landmark Dataset	Pisa. See the power of attention	For non-landmark, attention don't work

TODO

Any contributions are welcome 😄

[ ] write batch inference code. (one-by-one inference is too slow for any online application)

[ ] write export script for serving

[ ] write code for fine-tuning, and attention training

If you make use of this code, please consider citing:

Installation

# Python 3

# Tensorflow 1.3
pip install tensorflow==1.3

# OpenCV
pip install opencv-contrib-python

To be able to use this code, please follow these instructions to properly install the DELF library.

Please add path so delf can import these models.

cd ./slim
pip install -e . # install slim as package
cd ..
export PYTHONPATH=$PYTHONPATH:`pwd`
export PATH_TO_PROTOC=`pwd`

If you want to use this one as package, install this to your python env with below command

# In root dir of thie repo
sudo pip install -e .

Acknowledgement

"Large-Scale Image Retrieval with Attentive Deep Local Features",
Hyeonwoo Noh, Andre Araujo, Jack Sim, Tobias Weyand, Bohyung Han,
Proc. ICCV'17

delf_enhanced's Issues

Unsuccessful TensorSliceReader constructor: Failed to get matching files on parameters/delf_v1_20171026/model/variables/variables: Not found: parameters/delf_v1_20171026/model/variables

I ran your code，I reported an error while executing the Feature Matching file：
Unsuccessful TensorSliceReader constructor: Failed to get matching files on parameters/delf_v1_20171026/model/variables/variables: Not found: parameters/delf_v1_20171026/model/variables

I hope I can get your help.
thank you

Link "DEMO Python Notebook" is invalid

Hello,professer insikk. The link of "DEMO Python Notebook" is invalid. I would be grateful if you could update it. Thanks a lot again! Have a good day!

any

Any update ?
can you finetune the model now?