NIMA: Neural IMage Assessment

Overview

PyTorch NIMA: Neural IMage Assessment

PyTorch implementation of Neural IMage Assessment by Hossein Talebi and Peyman Milanfar. You can learn more from this post at Google Research Blog.

Installing

Docker

docker run -it truskovskiyk/nima:latest /bin/bash

PYPI package (In Progress)

pip install nima

VirtualEnv

git clone https://github.com/truskovskiyk/nima.pytorch.git
cd nima.pytorch
virtualenv -p python3.7 env
source ./env/bin/activate

Dataset

The model was trained on the AVA (Aesthetic Visual Analysis) dataset You can get it from here Here are some examples of images with theire scores result1

Pre-train model (In Progress)


Deployment (In progress)


Usage

nima-cli

Usage: cli.py [OPTIONS] COMMAND [ARGS]...

Options:
  --help  Show this message and exit.

Commands:
  get_image_score  Get image scores
  prepare_dataset  Parse, clean and split dataset
  run_web_api      Start server for model serving
  train_model      Train model
  validate_model   Validate model

Previous version of this project is still valid and works

you can find here

Contributing

Contributing are welcome

License

This project is licensed under the MIT License - see the LICENSE file for details

Acknowledgments

Comments
  • Missing tensorboardX dependency

    Missing tensorboardX dependency

    Thanks for releasing this.

    The separate dependencies for GPU vs CPU vs Mac is very nice.

    You need to add tensorboardX. I guess it should go in base.txt but not entirely sure.

    opened by nlothian 1
  • Bump numpy from 1.16.4 to 1.22.0

    Bump numpy from 1.16.4 to 1.22.0

    Bumps numpy from 1.16.4 to 1.22.0.

    Release notes

    Sourced from numpy's releases.

    v1.22.0

    NumPy 1.22.0 Release Notes

    NumPy 1.22.0 is a big release featuring the work of 153 contributors spread over 609 pull requests. There have been many improvements, highlights are:

    • Annotations of the main namespace are essentially complete. Upstream is a moving target, so there will likely be further improvements, but the major work is done. This is probably the most user visible enhancement in this release.
    • A preliminary version of the proposed Array-API is provided. This is a step in creating a standard collection of functions that can be used across application such as CuPy and JAX.
    • NumPy now has a DLPack backend. DLPack provides a common interchange format for array (tensor) data.
    • New methods for quantile, percentile, and related functions. The new methods provide a complete set of the methods commonly found in the literature.
    • A new configurable allocator for use by downstream projects.

    These are in addition to the ongoing work to provide SIMD support for commonly used functions, improvements to F2PY, and better documentation.

    The Python versions supported in this release are 3.8-3.10, Python 3.7 has been dropped. Note that 32 bit wheels are only provided for Python 3.8 and 3.9 on Windows, all other wheels are 64 bits on account of Ubuntu, Fedora, and other Linux distributions dropping 32 bit support. All 64 bit wheels are also linked with 64 bit integer OpenBLAS, which should fix the occasional problems encountered by folks using truly huge arrays.

    Expired deprecations

    Deprecated numeric style dtype strings have been removed

    Using the strings "Bytes0", "Datetime64", "Str0", "Uint32", and "Uint64" as a dtype will now raise a TypeError.

    (gh-19539)

    Expired deprecations for loads, ndfromtxt, and mafromtxt in npyio

    numpy.loads was deprecated in v1.15, with the recommendation that users use pickle.loads instead. ndfromtxt and mafromtxt were both deprecated in v1.17 - users should use numpy.genfromtxt instead with the appropriate value for the usemask parameter.

    (gh-19615)

    ... (truncated)

    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    • @dependabot use these labels will set the current labels as the default for future PRs for this repo and language
    • @dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language
    • @dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language
    • @dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

    You can disable automated security fix PRs for this repo from the Security Alerts page.

    dependencies 
    opened by dependabot[bot] 0
  • Bump ipython from 7.5.0 to 7.16.3

    Bump ipython from 7.5.0 to 7.16.3

    Bumps ipython from 7.5.0 to 7.16.3.

    Commits

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    • @dependabot use these labels will set the current labels as the default for future PRs for this repo and language
    • @dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language
    • @dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language
    • @dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

    You can disable automated security fix PRs for this repo from the Security Alerts page.

    dependencies 
    opened by dependabot[bot] 0
  • Update to modern pytorch and fix model ckpt link

    Update to modern pytorch and fix model ckpt link

    I fixed up the code to make inference possible out of the box

    Inference example:

    from nima.inference.inference_model import InferenceModel
    
    model = InferenceModel(path_to_model=Path('./pretrain-model.pth'))
    
    result = model.predict_from_pil_image(img)
    
    
    opened by Dawars 1
  • Bump aiohttp from 3.5.4 to 3.7.4

    Bump aiohttp from 3.5.4 to 3.7.4

    Bumps aiohttp from 3.5.4 to 3.7.4.

    Release notes

    Sourced from aiohttp's releases.

    aiohttp 3.7.3 release

    Features

    • Use Brotli instead of brotlipy [#3803](https://github.com/aio-libs/aiohttp/issues/3803) <https://github.com/aio-libs/aiohttp/issues/3803>_
    • Made exceptions pickleable. Also changed the repr of some exceptions. [#4077](https://github.com/aio-libs/aiohttp/issues/4077) <https://github.com/aio-libs/aiohttp/issues/4077>_

    Bugfixes

    • Raise a ClientResponseError instead of an AssertionError for a blank HTTP Reason Phrase. [#3532](https://github.com/aio-libs/aiohttp/issues/3532) <https://github.com/aio-libs/aiohttp/issues/3532>_
    • Fix web_middlewares.normalize_path_middleware behavior for patch without slash. [#3669](https://github.com/aio-libs/aiohttp/issues/3669) <https://github.com/aio-libs/aiohttp/issues/3669>_
    • Fix overshadowing of overlapped sub-applications prefixes. [#3701](https://github.com/aio-libs/aiohttp/issues/3701) <https://github.com/aio-libs/aiohttp/issues/3701>_
    • Make BaseConnector.close() a coroutine and wait until the client closes all connections. Drop deprecated "with Connector():" syntax. [#3736](https://github.com/aio-libs/aiohttp/issues/3736) <https://github.com/aio-libs/aiohttp/issues/3736>_
    • Reset the sock_read timeout each time data is received for a aiohttp.client response. [#3808](https://github.com/aio-libs/aiohttp/issues/3808) <https://github.com/aio-libs/aiohttp/issues/3808>_
    • Fixed type annotation for add_view method of UrlDispatcher to accept any subclass of View [#3880](https://github.com/aio-libs/aiohttp/issues/3880) <https://github.com/aio-libs/aiohttp/issues/3880>_
    • Fixed querying the address families from DNS that the current host supports. [#5156](https://github.com/aio-libs/aiohttp/issues/5156) <https://github.com/aio-libs/aiohttp/issues/5156>_
    • Change return type of MultipartReader.aiter() and BodyPartReader.aiter() to AsyncIterator. [#5163](https://github.com/aio-libs/aiohttp/issues/5163) <https://github.com/aio-libs/aiohttp/issues/5163>_
    • Provide x86 Windows wheels. [#5230](https://github.com/aio-libs/aiohttp/issues/5230) <https://github.com/aio-libs/aiohttp/issues/5230>_

    Improved Documentation

    • Add documentation for aiohttp.web.FileResponse. [#3958](https://github.com/aio-libs/aiohttp/issues/3958) <https://github.com/aio-libs/aiohttp/issues/3958>_
    • Removed deprecation warning in tracing example docs [#3964](https://github.com/aio-libs/aiohttp/issues/3964) <https://github.com/aio-libs/aiohttp/issues/3964>_
    • Fixed wrong "Usage" docstring of aiohttp.client.request. [#4603](https://github.com/aio-libs/aiohttp/issues/4603) <https://github.com/aio-libs/aiohttp/issues/4603>_
    • Add aiohttp-pydantic to third party libraries [#5228](https://github.com/aio-libs/aiohttp/issues/5228) <https://github.com/aio-libs/aiohttp/issues/5228>_

    Misc

    ... (truncated)

    Changelog

    Sourced from aiohttp's changelog.

    3.7.4 (2021-02-25)

    Bugfixes

    • (SECURITY BUG) Started preventing open redirects in the aiohttp.web.normalize_path_middleware middleware. For more details, see https://github.com/aio-libs/aiohttp/security/advisories/GHSA-v6wp-4m6f-gcjg.

      Thanks to Beast Glatisant <https://github.com/g147>__ for finding the first instance of this issue and Jelmer Vernooij <https://jelmer.uk/>__ for reporting and tracking it down in aiohttp. [#5497](https://github.com/aio-libs/aiohttp/issues/5497) <https://github.com/aio-libs/aiohttp/issues/5497>_

    • Fix interpretation difference of the pure-Python and the Cython-based HTTP parsers construct a yarl.URL object for HTTP request-target.

      Before this fix, the Python parser would turn the URI's absolute-path for //some-path into / while the Cython code preserved it as //some-path. Now, both do the latter. [#5498](https://github.com/aio-libs/aiohttp/issues/5498) <https://github.com/aio-libs/aiohttp/issues/5498>_


    3.7.3 (2020-11-18)

    Features

    • Use Brotli instead of brotlipy [#3803](https://github.com/aio-libs/aiohttp/issues/3803) <https://github.com/aio-libs/aiohttp/issues/3803>_
    • Made exceptions pickleable. Also changed the repr of some exceptions. [#4077](https://github.com/aio-libs/aiohttp/issues/4077) <https://github.com/aio-libs/aiohttp/issues/4077>_

    Bugfixes

    • Raise a ClientResponseError instead of an AssertionError for a blank HTTP Reason Phrase. [#3532](https://github.com/aio-libs/aiohttp/issues/3532) <https://github.com/aio-libs/aiohttp/issues/3532>_
    • Fix web_middlewares.normalize_path_middleware behavior for patch without slash. [#3669](https://github.com/aio-libs/aiohttp/issues/3669) <https://github.com/aio-libs/aiohttp/issues/3669>_
    • Fix overshadowing of overlapped sub-applications prefixes. [#3701](https://github.com/aio-libs/aiohttp/issues/3701) <https://github.com/aio-libs/aiohttp/issues/3701>_

    ... (truncated)

    Commits
    • 0a26acc Bump aiohttp to v3.7.4 for a security release
    • 021c416 Merge branch 'ghsa-v6wp-4m6f-gcjg' into master
    • 4ed7c25 Bump chardet from 3.0.4 to 4.0.0 (#5333)
    • b61f0fd Fix how pure-Python HTTP parser interprets //
    • 5c1efbc Bump pre-commit from 2.9.2 to 2.9.3 (#5322)
    • 0075075 Bump pygments from 2.7.2 to 2.7.3 (#5318)
    • 5085173 Bump multidict from 5.0.2 to 5.1.0 (#5308)
    • 5d1a75e Bump pre-commit from 2.9.0 to 2.9.2 (#5290)
    • 6724d0e Bump pre-commit from 2.8.2 to 2.9.0 (#5273)
    • c688451 Removed duplicate timeout parameter in ClientSession reference docs. (#5262) ...
    • Additional commits viewable in compare view

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    • @dependabot use these labels will set the current labels as the default for future PRs for this repo and language
    • @dependabot use these reviewers will set the current reviewers as the default for future PRs for this repo and language
    • @dependabot use these assignees will set the current assignees as the default for future PRs for this repo and language
    • @dependabot use this milestone will set the current milestone as the default for future PRs for this repo and language

    You can disable automated security fix PRs for this repo from the Security Alerts page.

    dependencies 
    opened by dependabot[bot] 0
  • Difference between deploy and released models

    Difference between deploy and released models

    Based on the same image, 5.9 is received through your get-image-score command. But 6.58 out of your deploy url 'https://neural-image-assessment.herokuapp.com/api/get_scores'. Furthermore, on your github page, the result is 6.38. So, are there different models you used in these different ways. Looking forward to your reply.

    opened by ChuanchuanZheng 0
  • CLI command can only be invoked by

    CLI command can only be invoked by " - " rather than " _ " in the original setting.

    I was just tried to run the get one image's score as
    python nima/cli.py get_image_score --path_to_model_weight ./pretrain-model.pth --path_to_image test_image.jpg while find below error, then I check the help info, and the program run correctly if I use "get-image-score" as in help info. I wander why this would occur when the defination and call function in cli.py are all using " _ ".

    image

    opened by JustinAsdz 1
Owner
Kyryl Truskovskyi
Machine Learning Engineer 🇺🇦🇨🇦
Kyryl Truskovskyi
[CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment

RADN [CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment [Paper on arXiv] Overview Update [2021/5/7] add codes for W

IIGROUP 53 Dec 28, 2022
Official PyTorch implementation of the paper "Recycling Discriminator: Towards Opinion-Unaware Image Quality Assessment Using Wasserstein GAN", accepted to ACM MM 2021 BNI Track.

RecycleD Official PyTorch implementation of the paper "Recycling Discriminator: Towards Opinion-Unaware Image Quality Assessment Using Wasserstein GAN

Yunan Zhu 23 Nov 5, 2022
Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment"

DSN-IQA Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment" Requirements Python >=3.8.0 Pytorch >=1.7.1 Usage wit

null 7 Oct 13, 2022
Lightweight Face Image Quality Assessment

LightQNet This is a demo code of training and testing [LightQNet] using Tensorflow. Uncertainty Losses: IDQ loss PCNet loss Uncertainty Networks: Mobi

Kaen 5 Nov 18, 2022
No-reference Image Quality Assessment(NIQA) Algorithms (BRISQUE, NIQE, PIQE, RankIQA, MetaIQA)

No-Reference Image Quality Assessment Algorithms No-reference Image Quality Assessment(NIQA) is a task of evaluating an image without a reference imag

Dae-Young Song 26 Jan 4, 2023
[CVPRW 2022] Attentions Help CNNs See Better: Attention-based Hybrid Image Quality Assessment Network

Attention Helps CNN See Better: Hybrid Image Quality Assessment Network [CVPRW 2022] Code for Hybrid Image Quality Assessment Network [paper] [code] T

IIGROUP 49 Dec 11, 2022
Easy and comprehensive assessment of predictive power, with support for neuroimaging features

Documentation: https://raamana.github.io/neuropredict/ News As of v0.6, neuropredict now supports regression applications i.e. predicting continuous t

Pradeep Reddy Raamana 93 Nov 29, 2022
MagFace: A Universal Representation for Face Recognition and Quality Assessment

MagFace MagFace: A Universal Representation for Face Recognition and Quality Assessment in IEEE Conference on Computer Vision and Pattern Recognition

Qiang Meng 523 Jan 5, 2023
Code for paper "A Critical Assessment of State-of-the-Art in Entity Alignment" (https://arxiv.org/abs/2010.16314)

A Critical Assessment of State-of-the-Art in Entity Alignment This repository contains the source code for the paper A Critical Assessment of State-of

Max Berrendorf 16 Oct 14, 2022
Repo for 2021 SDD assessment task 2, by Felix, Anna, and James.

SoftwareTask2 Repo for 2021 SDD assessment task 2, by Felix, Anna, and James. File/folder structure: helloworld.py - demonstrates various map backgrou

null 3 Dec 13, 2022
[ICCV 2021] Group-aware Contrastive Regression for Action Quality Assessment

CoRe Created by Xumin Yu*, Yongming Rao*, Wenliang Zhao, Jiwen Lu, Jie Zhou This is the PyTorch implementation for ICCV paper Group-aware Contrastive

Xumin Yu 31 Dec 24, 2022
Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis"

StrengthNet Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis" https://arxiv.org/abs/2110

RuiLiu 65 Dec 20, 2022
Implementation of temporal pooling methods studied in [ICIP'20] A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment

Implementation of temporal pooling methods studied in [ICIP'20] A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment

Zhengzhong Tu 5 Sep 16, 2022
A user-friendly research and development tool built to standardize RL competency assessment for custom agents and environments.

Built with ❤️ by Sam Showalter Contents Overview Installation Dependencies Usage Scripts Standard Execution Environment Development Environment Benchm

SRI-AIC 1 Nov 18, 2021
MRQy is a quality assurance and checking tool for quantitative assessment of magnetic resonance imaging (MRI) data.

Front-end View Backend View Table of Contents Description Prerequisites Running Basic Information Measurements User Interface Feedback and usage Descr

Center for Computational Imaging and Personalized Diagnostics 58 Dec 2, 2022
ZEBRA: Zero Evidence Biometric Recognition Assessment

ZEBRA: Zero Evidence Biometric Recognition Assessment license: LGPLv3 - please reference our paper version: 2020-06-11 author: Andreas Nautsch (EURECO

Voice Privacy Challenge 2 Dec 12, 2021
Pytorch implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"

MOSNet pytorch implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion" https://arxiv.org/abs/1904.08352 Dependency L

null 9 Nov 18, 2022
To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

Kunal Wadhwa 2 Jan 5, 2022
Internship Assessment Task for BaggageAI.

BaggageAI Internship Task Problem Statement: You are given two sets of images:- background and threat objects. Background images are the background x-

Arya Shah 10 Nov 14, 2022