pkmital/tensorflow_tutorials

Stars
5,615
Rank 7,272 (Top 0.2 %)
Language
Jupyter Notebook
License
Other
Created almost 9 years ago
Updated almost 3 years ago

pkmital/tensorflow_tutorials

pkmital

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

From the basics to slightly more interesting applications of Tensorflow

TensorFlow Tutorials

You can find python source code under the python directory, and associated notebooks under notebooks.

	Source code	Description
1	basics.py	Setup with tensorflow and graph computation.
2	linear_regression.py	Performing regression with a single factor and bias.
3	polynomial_regression.py	Performing regression using polynomial factors.
4	logistic_regression.py	Performing logistic regression using a single layer neural network.
5	basic_convnet.py	Building a deep convolutional neural network.
6	modern_convnet.py	Building a deep convolutional neural network with batch normalization and leaky rectifiers.
7	autoencoder.py	Building a deep autoencoder with tied weights.
8	denoising_autoencoder.py	Building a deep denoising autoencoder which corrupts the input.
9	convolutional_autoencoder.py	Building a deep convolutional autoencoder.
10	residual_network.py	Building a deep residual network.
11	variational_autoencoder.py	Building an autoencoder with a variational encoding.

Installation Guides

For Ubuntu users using python3.4+ w/ CUDA 7.5 and cuDNN 7.0, you can find compiled wheels under the wheels directory. Use pip3 install tensorflow-0.8.0rc0-py3-none-any.whl to install, e.g. and be sure to add: export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/cuda/lib64" to your .bashrc. Note, this still requires you to install CUDA 7.5 and cuDNN 7.0 under /usr/local/cuda.

Resources

Author

Parag K. Mital, Jan. 2016.

http://pkmital.com

License

See LICENSE.md

CADL

ARCHIVED: Contains historical course materials/Homework materials for the FREE MOOC course on "Creative Applications of Deep Learning w/ Tensorflow" #CADL

Jupyter Notebook

pycadl

Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"

time-domain-neural-audio-style-transfer

NIPS2017 "Time Domain Neural Audio Style Transfer" code repository

dance2dance

Discrete Figures AI: Seq2Seq of Dance Data (Mikiko + Daito Manabe + Kyle McDonald)

pkmFace

facial shape modeling, appearance modeling, and head pose recognition. Uses Jason Mora Saragih's FaceTracker code to track facial landmarks; GreatYao's aam-library for building/reprojecting the model (which may in fact be an uncited port of Jason's DeMoLib).

Real-Time-Object-Detection

real time object detection using opencv and simple UI to select the object to track

flask-uwsgi-tensorflow

Example of serving a TensorFlow model with Flask and UWSGI

pkmFFT

pkmFFT provide simple interfaces to the Accelerate.framework for performing vectorized FFT. pkmSTFT builds on pkmFFT to perform Short Time Fourier Transform efficiently using vectorized ops. Also handles options for windowing. pkmDCT provides a simple discrete cosine transform using Accelerate and pkmMatrix.

KinectHandAnalysis

Does finger tracking, contour analysis, and different types of shape description for the hand contour using a 3D ROI around the hand-tracked by NITE middleware, using OpenCV 2.2, an OpenGL scene, and OpenNI.

CycleGAN

Describing CycleGAN (excerpt from CADL course on Kadenze, Inc.)

Jupyter Notebook

ofxCaffe

openFrameworks addon for visualizing and interfacing with pre-trained models in Caffe: Convolutional Architectures for Fast Feature Embedding. Requires Caffe, openFrameworks 64-bit, glog, hdf5, OpenCV, CUDA, pkmMatrix, and pkmHeatmap. Pre-trained models not included but can be found linked in Caffe's "Model Zoo" and placed in the bin/data directory of the example project.

MTEC-498-698A-01-Algorithmic-Sound

Generative Sound Practice w/ OpenFrameworks

MTIID-MTEC-616-01-2017

Materials for "Audiovisual Interaction w/ Machine Learning", Bachelors (416) and Graduate (616) course @ CalArts MTIID MTEC

autoEncoderSynthesis

Performs interactive audio synthesis using a previously trained auto encoder. VIsualizes hidden layer and allows for interaction with hidden units. W/ Andy Sarroff. See Andy's github (woodshop) for more interesting projects using Deep Learning and audio synthesis.

pkmOpticalFlow

Interface for OpenCV's TV-L1 Duality Based Approach to Optical Flow. Does some additional tricks to speed up processing, allow for analysis of the spatio-temporal changes in flow, and visualize the results.

StickFigureOSC

Streams PrimeSense NITE's Skeleton Data via OSC (XCode Project)

pkmAudio

Sound synthesis library. Implements a number of feature databses including frame-based, segment-based, and sequence-based audio analysis/storing/retrieval. Also includes libraries for GPS-based synthesis including binarualization retrieval. Complements many other libraries including pkmBinaural and Memory Mosaic. Heavy dependence on vectorized ops using pkmMatrix and OSX's library Accelerate.

CARPE

CARPE is "Computational Algorithmic Representation and Processing of Eye-movements". It supports visualizations of film/eye-movements in columnar format, peak-through visualizations, heatmaps, optical flow analysis, gaze clustering, and many other visualization options. See http://thediemproject.wordpress.com for more details. Compuational and Algorithmic Representation and Processing of Eye-movements - OSX Version

pkmSIFTImage

Creates a dense SIFT image description and displays the image based on a PCA reprojection. Based on SIFT Flow code by Ce Lui, Jenny Yuen, and Antonio Torralba.

pkmBlobTracker

Background modeling for foreground subtraction, tracks multiple blobs (people), their orientations (using leading motion vector), and has a nice visual display for seeing the results... video demonstration here: http://vimeo.com/22054133 - more info here: http://pkmital.com

phdThesis

Ph.D. Thesis from Goldsmiths, University of London entitled, "Audiovisual Scene Synthesis". Hosts all images and latex files.

pkmColorBlobTracker

track overhead using color and map tracked points to a new geometry using a homography transformation and calibration routine - some example test videos are provided in the bin/data directory of an overhead capture. The tracking transformation is useful for when you need a defined metric space of your tracking parameters, or need to account for different user heights in tracking their paths in a space.

NSCARPE

CARPE is "Computational Algorithmic Representation and Processing of Eye-movements". It supports visualizations of film/eye-movements in columnar format, peak-through visualizations, heatmaps, optical flow analysis, gaze clustering, and many other visualization options. CARPE using NSWindow, Multiple Heatmaps, XML file settings, Difference of Heatmaps, GPU optimizations

CEMA

openFrameworks projects from my course at Srishti's School of Art, Design and Technology's Center for Experimental Media: http://pkmital.com/home/teaching/cema-workshop/

pkmPhaseVocoder

Phase vocoder using pkmFFT and pkmMatrix. Does not seem to do as well as commerical applications. Would love it if anyone made use of this and improved upon it.

ofxiTunesLibraryStream

simple way to stream 32-bit float data from itunes in real-time

pkmDetector

3d Object Tracking and Pose Estimation for the iPhone

seq2seq

Exploring audio modeling / synthesis w/ seq2seq

videoSPAM

[in progress] synthesis of audiovisual material from youtube!

pkmKalman

Kalman filter optimized for iOS/OSX

pkmMatrix

pkmMatrix provides a lightweight Matrix class using the Accelerate.framework for vectorized operations

pkmProjectionMapper

openFrameworks based projection mapping for distorting or mapping a collection of drawing commands/videos/images etc... needed a lightweight and robust projection mapping utility though lpmt was too heavy. homography code stolen from lpmt.

eegShapeAnimations

testing some encoding/decoding using EEG. this produces various animations that are co-registered with the recording of eeg.

pkmDPGMM

Interfacing libcluster for doing Variational Dirichlet Process Gaussian Mixture Models. Depends on Eigen3 and pkmMatrix. Libcluster included.

eegLogger

For streaming/logging emotiv eeg headset data

pkmBinaural

For performing GPS based concatenative sound synthesis, ANN retrieval based on GPS locations, HRTF based binauralization (mono->stereo using HRTF FFT-based Overlap-Add Convolution) using the IRCAM HRTF Database

ofxOpenCV2461

ofxOpenCV linking against OpenCV 2.4.6.1, including libraries for OSX

eegGaborAnimations

testing eeg encoding/decoding. this produces some gabor wavelets and co-registers the visualization and recording of eeg.

CADLBook

pkmLSH

Locality Sensitive Hashing

freesoundDownloader

Uses cURL to download from Freesound.org

pkmRecorder

For streaming/recording audio files, circular buffers (see pkmMatrix and pkmEXTAudioFile as well)

pkmEXTAudioFile

pkmEXTAudioFileReader and pkmEXTAudioFileWriter provides simple interfaces to reading and writing audio files.

pkmPoseCalibrator

Calibrate head pose with respect to a screen (television/monitor) for an attention-based measure. Uses Jason Mora Saragih's FaceTracker, please contact him for the code.

pkmHeatmap

GPU Shader implementation of common heatmap/colormaps for mapping grayscale->colormap such as JET, COOL, HOT, difference heatmaps which map to similar ranges, and support for sending point list for creating a Gaussian Mixture Model which can be visualized as a heatmap or readback for your own purposes..

CARPE-unstable

CARPE is "Computational Algorithmic Representation and Processing of Eye-movements". It supports visualizations of film/eye-movements in columnar format, peak-through visualizations, heatmaps, optical flow analysis, gaze clustering, and many other visualization options. See http://thediemproject.wordpress.com for more details. Initial release of CARPE hosted for historical purposes. Includes many experimental addons for CARPE including dROIs, GMM, GPU-Flow, and others. See also CARPE and NSCARPE for more recent, stable versions not including the experimental addons.