tf-image | TensorFlow2 graph image augmentation | Machine Learning library

by Ximilar-com Python Version: 0.2.0 License: MIT

X-Ray Key Features Code Snippets Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | tf-image Summary

tf-image is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Tensorflow applications. tf-image has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has low support. You can install using 'pip install tf-image' or download it from GitHub, PyPI.

TensorFlow2+ graph image augmentation library optimized for tf.data.Dataset.

Support

Quality

Security

License

Reuse

Support

tf-image has a low active ecosystem.

It has 20 star(s) with 2 fork(s). There are 3 watchers for this library.

It had no major release in the last 12 months.

There are 0 open issues and 3 have been closed. On average issues are closed in 13 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of tf-image is 0.2.0

Quality

tf-image has 0 bugs and 0 code smells.

Security

tf-image has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

tf-image code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

tf-image is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

tf-image releases are not available. You will need to build from source code and install.

Deployable package is available in PyPI.

Build file is available. You can build the component from source.

Installation instructions, examples and code snippets are available.

It has 830 lines of code, 59 functions and 21 files.

It has medium code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed tf-image and discovered the below as its top functions. This is intended to give you an instant insight into tf-image implemented functionality, and help decide if they suit your requirements.

Performs random augmentations
Clips a random image
Generate random augmentations
Clip a random image
Rotate image
Rotate points
Clips bounding boxes
Rotate given image
Decorate a function to convert bboxes
Convert bounding boxes to absolute coordinates
Convert bboxes to relative coordinates
Drop a channel
Randomly select a random number

Get all kandi verified functions for this library.

tf-image Key Features

No Key Features are available at this moment for tf-image.

tf-image Examples and Code Snippets

No Code Snippets are available at this moment for tf-image.

Community Discussions

Trending Discussions on tf-image

AttributeError: 'numpy.ndarray' object has no attribute 'get_shape'?

QUESTION

AttributeError: 'numpy.ndarray' object has no attribute 'get_shape'?

Asked 2020-May-06 at 21:20

As I'm running beginner.ipynb from google's intro to tensorflow locally, the execution breaks at

...

ANSWER

Answered 2020-May-06 at 21:20

The answer, as mentioned by the OP is to to use tensorflow2. Though it wasn't possible to get to the root cause of this problem it seems like it may be stemming from unsupported functionality in tensorflow1.x.

See here for the changes of 1.x vs 2.x

Source https://stackoverflow.com/questions/61315515

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install tf-image

For installation from source code, clone the repository and install it from code (pip install -e .). There are no dependencies specified. You have to install TensorFlow 2+ and appropriate TensorFlow Addons. Specific version is on you, we wanted to keep this library as general as possible.
For your convenience, we included a simple and configurable application, which combines all the provided augmentations. They are performed in a random order to make the augmentation even more powerful. There is also one script which uses this augmentation function and which outputs three augmented image without bounding boxes and three with bonding boxes. See example/example.py for more information.