Analyzes regarding Duplicate Reimbursements #286
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…-amor # Conflicts: # conda_requirements.txt # research/Dockerfile # research/requirements.txt
# Including pdf > png # png > sift descriptors # png > keras classifier
PDF to PNG ok PNG to SIFT (error in opencv)
Change the workflow for png references
Download files OK Split Files ok Testing trianing ...
…-amor # Conflicts: # research/Dockerfile
# Building Reference Dataset ok # Building Keras model and evaluation OK # PDF-> PNG OK
# Using dhash to detect near duplications.
silviodc
changed the title
# Inclusion of Fourier transformation to detect rotation, zoom, and filters.
silviodc
changed the title
|
Hi @silviodc, thanks for the contribuition! What I did to test this PR:
$ git clone git@github.com:datasciencebr/serenata-de-amor.git
$ cd serenata-de-amor
$ git checkout -b silviodc-silvio-cardoso master
$ git pull https://github.com/silviodc/serenata-de-amor.git silvio-cardoso
$ conda update conda
$ conda create --name serenata_de_amor python=3
$ source activate serenata_de_amor
$ ./setup
$ jupyter notebook
I really liked your work on it, looks real impressive! There is only one thing that I'll ask you, and then for me we can merge it! |
anaschwendler
requested changes
Oct 11, 2017
research/requirements.txt
Outdated
| tensorflow>=1.2.1 | ||
| h5py>=2.7.0 | ||
| Pillow>=4.2.1 | ||
| opencv-python |
There was a problem hiding this comment.
Can you add the version of the libraries that you are using? It helps in case they change something that make it not working ;)
No. I guess i finished with these analyses. |
anaschwendler
approved these changes
Oct 11, 2017
silviodc
force-pushed
the
silvio-cardoso
branch
from
d02bbbd to
3f76ad6
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Detecting duplicate Reimbursements using dhash.
The last commit has the notebook to detect duplicate Reimbursements. It uses hash and hamming distance.
The other files concerns future implementation as: CFMT block (Compact Fourier Mellin Transform) to be more precise during the detection.
It is related to issue: #32