tomrunia / Tf_featureextraction
Convenient wrapper for TensorFlow feature extraction from pre-trained models using tf.contrib.slim
Stars: ✭ 169
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Tf featureextraction
Seg Mentor
TFslim based semantic segmentation models, modular&extensible boutique design
Stars: ✭ 43 (-74.56%)
Mutual labels: feature-extraction, slim
Dgm
Direct Graphical Models (DGM) C++ library, a cross-platform Conditional Random Fields library, which is optimized for parallel computing and includes modules for feature extraction, classification and visualization.
Stars: ✭ 157 (-7.1%)
Mutual labels: feature-extraction
Audioowl
Fast and simple music and audio analysis using RNN in Python 🕵️♀️ 🥁
Stars: ✭ 151 (-10.65%)
Mutual labels: feature-extraction
Slim Oauth2
Routes and Middleware for Using OAuth2 Server within a Slim Framework API
Stars: ✭ 121 (-28.4%)
Mutual labels: slim
Color recognition
🎨 Color recognition & classification & detection on webcam stream / on video / on single image using K-Nearest Neighbors (KNN) is trained with color histogram features by OpenCV.
Stars: ✭ 154 (-8.88%)
Mutual labels: feature-extraction
Imagefeaturedetector
A C++ Qt GUI desktop program to calculate Harris, FAST, SIFT and SURF image features with OpenCV
Stars: ✭ 112 (-33.73%)
Mutual labels: feature-extraction
Rest Api Slim Php
Example of REST API with Slim PHP Framework.
Stars: ✭ 165 (-2.37%)
Mutual labels: slim
Machine Learning Workflow With Python
This is a comprehensive ML techniques with python: Define the Problem- Specify Inputs & Outputs- Data Collection- Exploratory data analysis -Data Preprocessing- Model Design- Training- Evaluation
Stars: ✭ 157 (-7.1%)
Mutual labels: feature-extraction
Textfeatures
👷♂️ A simple package for extracting useful features from character objects 👷♀️
Stars: ✭ 148 (-12.43%)
Mutual labels: feature-extraction
Dry View
Complete, standalone view rendering system that gives you everything you need to write well-factored view code.
Stars: ✭ 124 (-26.63%)
Mutual labels: slim
Isee
R/shiny interface for interactive visualization of data in SummarizedExperiment objects
Stars: ✭ 155 (-8.28%)
Mutual labels: feature-extraction
Msmbuilder
🏗 Statistical models for biomolecular dynamics 🏗
Stars: ✭ 118 (-30.18%)
Mutual labels: feature-extraction
Emotion Recognition Using Speech
Building and training Speech Emotion Recognizer that predicts human emotions using Python, Sci-kit learn and Keras
Stars: ✭ 159 (-5.92%)
Mutual labels: feature-extraction
The Building Data Genome Project
A collection of non-residential buildings for performance analysis and algorithm benchmarking
Stars: ✭ 117 (-30.77%)
Mutual labels: feature-extraction
Sourceafis Java
Fingerprint recognition engine for Java that takes a pair of human fingerprint images and returns their similarity score. Supports efficient 1:N search.
Stars: ✭ 136 (-19.53%)
Mutual labels: feature-extraction
Nwaves
.NET library for 1D signal processing focused specifically on audio processing
Stars: ✭ 151 (-10.65%)
Mutual labels: feature-extraction
Augmented reality
💎 "Marker-less Augmented Reality" with OpenCV and OpenGL.
Stars: ✭ 165 (-2.37%)
Mutual labels: feature-extraction
TensorFlow Feature Extractor
This is a convenient wrapper for feature extraction or classification in TensorFlow. Given well known pre-trained models on ImageNet, the extractor runs over a list or directory of images. Optionally, features can be saved as HDF5 file. It supports all the pre-trained models listed on the official page.
TensorFlow models tested:
- Inception v1-v4
- ResNet v1 and v2
- VGG 16-19
Requirements
- TensorFlow (tested with version 1.8)
- TensorFlow Models
- The usual suspects:
numpy
,scipy
. - Optionally
h5py
for saving features to HDF5 file
Setup
- Checkout the TensorFlow
models
repository somewhere on your machine. The path where you checkout the repository will be denoted<checkout_dir>/models
git clone https://github.com/tensorflow/models/
- Add the directory
<checkout_dir>/research/slim
to the$PYTHONPATH
variable. Or add a line to your.bashrc
file.
export PYTHONPATH="<checkout_dir>/research/slim:$PYTHONPATH"
- Download the model checkpoints from the official page.
Usage
There are two example files, one for classification and one for feature extraction.
Feature Extraction
ResNet-v1-101
example_feat_extract.py
--network resnet_v1_101
--checkpoint ./checkpoints/resnet_v1_101.ckpt
--image_path ./images_dir/
--out_file ./features.h5
--num_classes 1000
--layer_names resnet_v1_101/logits
ResNet-v2-101
example_feat_extract.py
--network resnet_v2_101
--checkpoint ./checkpoints/resnet_v2_101.ckpt
--image_path ./images_dir/
--out_file ./features.h5
--layer_names resnet_v2_101/logits
--preproc_func inception
Inception-v4
example_feat_extract.py
--network inception_v4
--checkpoint ./checkpoints/inception_v4.ckpt
--image_path ./images_dir/
--out_file ./features.h5
--layer_names Logits
Image Classification
example_classification.py
--network resnet_v1_101
--checkpoint ./checkpoints/resnet_v1_101.ckpt
--image_path ./images_dir/
--num_classes 1000
--logits_name resnet_v1_101/logits
Work in Progress
Save image file names to HDF5 fileSupport for multi-threaded preprocessing
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].