I have a master's degree in informatics and with a decade of experience as a Software Developer, I'm all about crafting top-notch software that stands the test of time. I'm super passionate about Software Engineering, Software Architecture, and ensuring software is not just functional, but fabulous! ๐ป My journey includes diving deep into data science ๐ and geeking out over data-centric AI ๐ค. I'm also a Linux enthusiast ๐ง who loves customizing Linux-based OSs and dabbling in DevOps by self-hosting various services. As a productivity geek ๐, I'm all about automating those mundane tasks to free up time for the good stuff! โ๏ธ When I'm not knee-deep in code, you'll catch me gaming ๐ฎ, snapping photos ๐ธ, getting lost in Sci-Fi books ๐, analyzing scientific papers ๐, or making a splash in the pool! ๐โโ๏ธ Let's chat about creating some seriously cool software together! ๐
mastersthesis's Introduction
mastersthesis's People
mastersthesis's Issues
Creating A Report For NN Structure 1
- execute around 10 examples from FlyingThings3D
- execute a couple of examples from KITTIE 2015
- create a PDF report
- think about the future path and structure
Export Images at the end of each epoch
- A callback to render a batch of test images when each epoch ends.
Optimizing the network's Hyper Parameters
After DisparityNet (FlowNet2.0, #34) is completed. Networks "Hyper-Parameters" should be optimized.
A More Coherence Code
Make multi-stage learning Coherent and Object Oriented
Saving a model structure without training
It is more logical to save a network in a file (like model_init
) then load and train for certain epochs.
This allows for having only one train code.
Test a dataset: SlidingThings3D.
Some generic 3D meshes will slide and rotate in front of the camera and rendering the result into a dataset. This will be a test for SlidingOrgans3D
.
Some things to look for:
- Disparities should be between
0
and50
. - They should increment gradually.
- No sudden breaks in disparities.
- Lights should be static but rendered in the scene.
Flownet Specialized Functions
Bring Flownet Specialized functions to this repository.
- Correlation Function.
- Warping function.
- Correction on DisparityNet SD
Adding Tensorboard support
Adding tensorboard
support to keras
model.
Check if it is possible to access the tensorboard
itself from the server without downloading log
fiels.
Create new Data Generator for SlidingOrgans
- Divide the data into Test and Validation.
- Re pack the data.
Upload to Ehsan's Server. - Upload to Ayber's Server.
- Create Data Generator.
This can be tested in Aybar's server.
Train Networks For Presentation Day
- DisparityNet S
- DisparityNet C
- DisparityNet CS
- DisparityNet SD
- DisparityNet CS2 (Parallel)
Write a report for each here in the post
Devise a initial/simple auto encoder structure
An initial and simple auto encoder structure for FlyingThings3D should be devised.
PFM to PNG
Create a simple piece of code to convert PFM files to PNG.
- The output should be color-coded, like a rainbow.
- the least and most should be detected automatically.
Image Warping
Warp left
image to right
image using TensorFlow
and save it.
The outcome of this task is applicable in #34.
Learning Rate Scheduler
Implement a Keras
Callback
to adapt Learning Rate.
Create a Real World Test Dataset
A good starting point will be TMI Dataset
- Crop rectified images into a 512x512 shape.
- Create a code to convert the disparity into a mesh.
Better Feed Forward Code
Current Feed Forward Code Outputs the result as a PFM file. There should be
- a PFM output,
- a color-coded PNG output.
- a Print out of metrics such as Bad1.0, Bad2.0, and Bad4.0
List Available Data in FlyingThings3D
FlyingThings3D has been downloaded to Thesis-Server.
Create an automated file listing:
- It should be object-oriented.
- It should mention "Specifically for Flying Things"
- It should be out of the main network folder.
Data Generator Implementation
Implement an implementation of Keras Data Generator
Example Here
Implementation should be detailed.
A Better Architecture
Implement DisparityNet modeled after FlowNet2.0
Better Accuracy Calculation
Normal measures of accuracy (metrics) in Keras core are not designed to depict the accuracy of matching disparity maps.
A Disparity Error measure should be found and implemented to work with Keras.
Search for Datasets
- Search for datasets.
- Email the researchers.
Needed Textures List
Gather a list of necessary organs.
Compare the organs shape and texture in Human, Cow and Lamb.
Create a report.
A plugin for disparity rendering
- Check this plugin and try to render into disparities.
- Create simple objects and check to see if the disparity is rendered correctly.
Transfer Learning
Try Initial Learning with FlyingThings3D and Transfer to SlidingTissues3D
Human Anatomy Model into Blender and Render Test
- Import Human Anatomy Model that is purchased - hopefully in #52 - and import it correctly into Blender.
- Create render tests - with disparity - from the model to evaluate realism.
- Test to see if it is possible to use the Textures, Normal Maps etc on other models.
Optimizing the initial network structures.
The initial network structure developed in issue #3, is (probably) not sufficient/good enough architecture to solve the issue at hand.
A new design should be derived and implemented.
A better loss function to train with
What is the preferred loss?
Minimum and Maximum Disparities
Images from OpenCAS dataset TMI are rectified so they are the prime candidate for real test data.
Calculate the minimum and maximum disparities in examples.
Converting Disparity Map to Mesh
Check and try to create and save mesh with and without disparity maps.
CSV Logger
Create a CSV Logger to keep track of loss and metrics values.
Must be tested in case of None Termination
or Raised Errors
that is known to occur.
Combine Output Directories
Right now, there are 3 directories for 3 types of outputs, csvs
, logs
, and models
.
They should be combined.
Note: Back up the current progress especially models first.
Multi-Stage Training
There is a need to create a more flexible code, one that can resume training for some certain epochs.
For now, a separate code to resume the initial training stage suffices.
Look for texture and simulate some data.
Look for meet texture. Perferably with Normals etc.
Feedforward Code
Create a feedforward code to input stereo images and outputs the disparities.
Multiple GPUs
Adapt the code to use multiple GPUs.
Although the initial structure of the neural network implemented in issue #3 is proven to be too shallow, this adaption is merely a test so the old structure would be used.
Note: Current GPU numbers are 2 so the network should be designed for two GPUs.
Laptop Vs. Server
Investigate why some Server trained network does not work in the laptop?
EndoAbS Dataset
- Check the validity of Ground Truth (GT). GT is given in an unusual format.
Purchasing a Human Anatomy Model
- Check buying procedure. Maybe Ehsan's help is required.
- A realistic Human Anatomy model should be purchased. There are some examples in #45. Also ask for Mina's advise. Maybe it is better to wait for Erkan Hoca's response.
Test more images
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. ๐๐๐
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.