KittiSeg | A Kitti Road Segmentation model implemented in tensorflow | Machine Learning library

by MarvinTeichmann Python Version: Current License: MIT

X-Ray Key Features Code Snippets Community Discussions(2)Vulnerabilities Install Support

kandi X-RAY | KittiSeg Summary

KittiSeg is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning, Pytorch, Tensorflow applications. KittiSeg has no bugs, it has no vulnerabilities, it has build file available, it has a Permissive License and it has medium support. You can download it from GitHub.

KittiSeg performs segmentation of roads by utilizing an FCN based model. The model achieved first place on the Kitti Road Detection Benchmark at submission time. Check out our paper for a detailed model description. The model is designed to perform well on small datasets. The training is done using just 250 densely labelled images. Despite this a state-of-the art MaxF1 score of over 96% is achieved. The model is usable for real-time application. Inference can be performed at the impressive speed of 95ms per image. The repository contains code for training, evaluating and visualizing semantic segmentation in TensorFlow. It is build to be compatible with the TensorVision back end which allows to organize experiments in a very clean way. Also check out KittiBox a similar projects to perform state-of-the art detection. And finally the MultiNet repository contains code to jointly train segmentation, classification and detection. KittiSeg and KittiBox are utilized as submodules in MultiNet.

Support

Quality

Security

License

Reuse

Support

KittiSeg has a medium active ecosystem.

It has 892 star(s) with 408 fork(s). There are 44 watchers for this library.

It had no major release in the last 6 months.

There are 95 open issues and 93 have been closed. On average issues are closed in 21 days. There are 3 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of KittiSeg is current.

Quality

KittiSeg has 0 bugs and 0 code smells.

Security

KittiSeg has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

KittiSeg code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

KittiSeg 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

KittiSeg releases are not available. You will need to build from source code and install.

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

Installation instructions, examples and code snippets are available.

KittiSeg saves you 1353 person hours of effort in developing the same functionality from scratch.

It has 3032 lines of code, 142 functions and 27 files.

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

Top functions reviewed by kandi - BETA

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

Evaluate the model
Evaluate an image
Resize label image
Maximize FMeasure
Calculate EvalMeasures
Transformer decoder
Create an upsample layer
Summarize activations
Calculate softmax
Embed inference
Binary function
Get a single variable
Plot precision recall curves
Download and extract the data
Create data generator
Compute the loss function
Define inputs
Splits data into train and test examples
Saves an image to a given axis
Start the enqueueing thread
Create tensorflow queue
Perform shuffle operation
Return the path to the data directory
Download a file
Recursively merge two dicts
Convolution layer

Get all kandi verified functions for this library.

KittiSeg Key Features

No Key Features are available at this moment for KittiSeg.

KittiSeg Examples and Code Snippets

No Code Snippets are available at this moment for KittiSeg.

Community Discussions

Trending Discussions on KittiSeg

Single Image Inference in Tensorflow [Python]

regarding print out os.environ variables

QUESTION

Single Image Inference in Tensorflow [Python]

Asked 2017-Aug-23 at 09:00

I have already converted a pre-trained .ckpt file to .pb file freezing the model and saving the weighs as well. What I am trying to do now is to make a simple inference using that .pb file and extract and save output image. The model is a (Fully Convolutional Network for Semantic Segmentation) downloaded from here : https://github.com/MarvinTeichmann/KittiSeg . So far I have managed to, load the image, set the default tf graph and import the graph defined by the model on that, read the input and the output tensors and run the session (error here).

...

ANSWER

Answered 2017-Aug-15 at 19:26

Have you already looked at the demo.py. There is shown at line 141 how they modify the input of the graph:

Source https://stackoverflow.com/questions/45697823

QUESTION

regarding print out os.environ variables

Asked 2017-Mar-31 at 16:19

There is a code segment in one Python program. It runs fine.

...

ANSWER

Answered 2017-Mar-31 at 16:19

I think you'll find that 'TV_DIR_RUNS' is not in os.environ. Change your line to print(os.environ.get('TV_DIR_RUNS'))

The line os.environ['TV_DIR_RUNS'] = ... is inside the block of the if statement, checking if 'TV_DIR_RUNS' is in os.environ.

Source https://stackoverflow.com/questions/43145319

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

Vulnerabilities

No vulnerabilities reported

Install KittiSeg

Running the model using demo.py does not require you to download kitti data (step 3). Step 3 is only required if you want to train your own model using train.py or bench a model agains the official evaluation score evaluate.py. Also note, that I recommend using download_data.py instead of downloading the data yourself. The script will also extract and prepare the data. See Section Manage data storage if you like to control where the data is stored. If you forget the second step you might end up with an inconstant repository state. You will already have the new code for KittiSeg but run it old submodule versions code. This can work, but I do not run any tests to verify this.
Clone this repository: git clone https://github.com/MarvinTeichmann/KittiSeg.git
Initialize all submodules: git submodule update --init --recursive
[Optional] Download Kitti Road Data: Retrieve kitti data url here: http://www.cvlibs.net/download.php?file=data_road.zip Call python download_data.py --kitti_url URL_YOU_RETRIEVED
Pull all patches: git pull
Update all submodules: git submodule update --init --recursive
Run: python demo.py --input_image data/demo/demo.png to obtain a prediction using demo.png as input. Run: python evaluate.py to evaluate a trained model. Run: python train.py --hypes hypes/KittiSeg.json to train a model using Kitti Data. If you like to understand the code, I would recommend looking at demo.py first. I have documented each step as thoroughly as possible in this file.