narenkmanoharan / Imagenet Classifier Tensorflow
Image recognition and classification using Convolutional Neural Networks with TensorFlow
Stars: ✭ 13
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Imagenet Classifier Tensorflow
Arraymancer
A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends
Stars: ✭ 793 (+6000%)
Mutual labels: tensor, cudnn, cuda
Tensorflow Object Detection Tutorial
The purpose of this tutorial is to learn how to install and prepare TensorFlow framework to train your own convolutional neural network object detection classifier for multiple objects, starting from scratch
Stars: ✭ 113 (+769.23%)
Mutual labels: cudnn, cuda
Tensorflow Optimized Wheels
TensorFlow wheels built for latest CUDA/CuDNN and enabled performance flags: SSE, AVX, FMA; XLA
Stars: ✭ 118 (+807.69%)
Mutual labels: cudnn, cuda
Singularity Tutorial
Tutorial for using Singularity containers
Stars: ✭ 46 (+253.85%)
Mutual labels: cudnn, cuda
Aurora
Minimal Deep Learning library is written in Python/Cython/C++ and Numpy/CUDA/cuDNN.
Stars: ✭ 90 (+592.31%)
Mutual labels: cudnn, cuda
Ctranslate2
Fast inference engine for OpenNMT models
Stars: ✭ 140 (+976.92%)
Mutual labels: cudnn, cuda
gpu-monitor
Script to remotely check GPU servers for free GPUs
Stars: ✭ 85 (+553.85%)
Mutual labels: cuda, cudnn
Arch-Data-Science
Archlinux PKGBUILDs for Data Science, Machine Learning, Deep Learning, NLP and Computer Vision
Stars: ✭ 92 (+607.69%)
Mutual labels: cuda, cudnn
Mini Caffe
Minimal runtime core of Caffe, Forward only, GPU support and Memory efficiency.
Stars: ✭ 373 (+2769.23%)
Mutual labels: cudnn, cuda
Nvidia libs test
Tests and benchmarks for cudnn (and in the future, other nvidia libraries)
Stars: ✭ 36 (+176.92%)
Mutual labels: cudnn, cuda
Simple Sh Datascience
A collection of Bash scripts and Dockerfiles to install data science Tool, Lib and application
Stars: ✭ 32 (+146.15%)
Mutual labels: cudnn, cuda
Tutorial Ubuntu 18.04 Install Nvidia Driver And Cuda And Cudnn And Build Tensorflow For Gpu
Ubuntu 18.04 How to install Nvidia driver + CUDA + CUDNN + build tensorflow for gpu step by step command line
Stars: ✭ 91 (+600%)
Mutual labels: cudnn, cuda
Social-Distancing-and-Face-Mask-Detection
Social Distancing and Face Mask Detection using TensorFlow. Install all required Libraries and GPU drivers as well. Refer to README.md or REPORT for know to installation requirement
Stars: ✭ 39 (+200%)
Mutual labels: cuda, cudnn
Chainer
A flexible framework of neural networks for deep learning
Stars: ✭ 5,656 (+43407.69%)
Mutual labels: cudnn, cuda
Neuralsuperresolution
Real-time video quality improvement for applications such as video-chat using Perceptual Losses
Stars: ✭ 18 (+38.46%)
Mutual labels: cuda
ImageNet Classifier with TensorFlow
- Deep CNN with AlexNet for Classifying/Recognizing objects
- Built using Python, TensorFlow, TFlearn and AWS EC2
- Used g2.8x GPU instances to speed up the classification process
- Built a model with an error rate of 6.2%
- Used factional max pooling with sparse CNN to improve accuracy
Technical Specifications
- Python 2.7
- TensorFlow 0.10.0
- TFLearn 0.2.1
- CUDA 8
- CuDnn v5
Convolutional Neural Network
AlexNet Classifier
Dataset Links
Executing the model
Initiate EC2 instance on AWS with the following specification
- g2.8x
- 80GB SSD
- 32 vCPU
Installing initial dependencies
sudo apt-get update
sudo apt-get -y dist-upgrade
sudo apt-get install python
sudo apt install python3-pip
sudo apt-get install -y libglu1-mesa libxi-dev libxmu-dev libglu1-mesa-dev gcc g++ gfortran build-essential git wget linux-image-generic libopenblas-dev python-dev liblapack-dev libblas-dev build-essential cmake git unzip pkg-config linux-image-generic linux-image-extra-virtual linux-source linux-headers-generic
Installing compression libraries
sudo apt-get install zlib1g-dev python-imaging
Exporting TensorFlow 0.10.0 for Python 2.7
export TF_BINARY_URL=https://storage.googleapis.com/tensorflow/linux/cpu/tensorflow-0.10.0rc0-cp27-none-linux_x86_64.whl
Installing TensorFlow
sudo pip install --upgrade $TF_BINARY_URL
Installing and upgrading Python and Pip
sudo apt-get install python
sudo apt install python-pip
sudo pip install --upgrade pip
Downloading and installing
wget -qO- https://github.com/tflearn/tflearn/tarball/0.2.1 | tar xvz
cd tflearn-tflearn-a55c1fd/
sudo python setup.py install
Installing scipy stack dependencies
sudo pip install pillow numpy scipy h5py
Install CUDA
https://developer.nvidia.com/cuda-downloads
Installing CuDNN
https://developer.nvidia.com/cudnn
SCP the code into the remote server and run the code using python 2.7
python alex_net.py
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].