NIMA: Neural IMage Assessment

truskovskiyk, updated πŸ•₯ 2022-06-21 22:14:08

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

bash 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)

```bash

```

Deployment (In progress)

```bash

```

Usage

```bash 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

Issues

Bump numpy from 1.16.4 to 1.22.0

opened on 2022-06-21 22:14:08 by dependabot[bot]

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](https://github.com/truskovskiyk/nima.pytorch/network/alerts).

Bump ipython from 7.5.0 to 7.16.3

opened on 2022-01-21 18:56:55 by dependabot[bot]

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](https://github.com/truskovskiyk/nima.pytorch/network/alerts).

Update to modern pytorch and fix model ckpt link

opened on 2021-06-14 16:33:09 by Dawars

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

Inference example:

```python from nima.inference.inference_model import InferenceModel

model = InferenceModel(path_to_model=Path('./pretrain-model.pth'))

result = model.predict_from_pil_image(img)

```

Bump aiohttp from 3.5.4 to 3.7.4

opened on 2021-02-26 02:32:28 by dependabot[bot]

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 VernooΔ³ <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](https://github.com/truskovskiyk/nima.pytorch/network/alerts).

Difference between deploy and released models

opened on 2020-11-12 11:25:45 by ChuanchuanZheng

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.

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

opened on 2020-09-27 07:56:51 by JustinAsdz

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

Kyryl Truskovskyi

Machine Learning Engineer πŸ‡ΊπŸ‡¦πŸ‡¨πŸ‡¦

GitHub Repository

nima pytorch deep-learning python machine-learning computer-vision neural-network arxiv