sdhayalk

TensorFlow_Speech_Recognition_Challenge

Implemented 3 neural network architectures: 1) Combination of RNN LSTM nodes and CNN, 2) CNN with residual blocks similar to ResNet, 3) Deep RNN LSTM network; and compared their performance to detect 12 speech commands.

Invasive_Species_Monitoring

Implemented convolutional neural network GoogLeNet with Inception modules and Ensemble of Inception V3, Xception, ResNet50 using transfer learning to detect invasive hydrangea in Brazilian national forest images dataset from Kaggle. Programmed in Keras using TensorFlow backend.

Large_Scale_GeoVisual_Search

Image visual similarity based search in NAIP satellite imagery of some areas of California using Deep Learning. Deep CNN provides output features that are converted into 512-bit binary vector that compactly represents the input image and can be used for similarity based search.

Distracted_Driver_Detection

GoogLeNet architecture with Inception modules that can detect the driver's activity or distraction which can be used to aid autonomous driving agent about driver's state.

Facial_Emotion_Recognition

Convolutional neural network model similar to VGG-D that can detect emotions given facial images. Achieved an accuracy of 65% on the FER-2013 dataset. Code in Keras

Grayscale_to_Color_using_CNN

Convolutional Neural Network architecture to generate Color images from Grayscale input images. Specifically, it generates color images in the YUV channels space when given input grayscale images in the Y channel.

CapsNet-for-Iceberg-or-Submarine-Classification

Nearby_Restaurants_Weather_Offers

AdTracking_Fraud_Detection_TalkingData

advdbSpatialTest

BinaryNet-on-tensorflow

binary weight neural network implementation on tensorflow

caffe_practice

Data_Structures_Implementation

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

Generative_Adversarial_Networks

git_test

Hadoop_MapReduce_Examples

Insurance_Filing_Prediction

Logo_Image_Data_Augmentation

Lung_Cancer_Detection

MNIST_Digit_Recognizer_Kaggle

Test Accuracy: 99.4%. Kaggle Rank: Top 13%. Convolutional neural network using TensorFlow to correctly identify digits from handwritten images

models

Models and examples built with TensorFlow

python-geospatial-analysis-cookbook

Over 60 recipes to work with topology, overlays and indoor routing

rcnn

R-CNN: Regions with Convolutional Neural Network Features

Realtime_Advertisement_Statistics_Using_CNN

resnet-imagenet-caffe

train resnet on imagenet from scratch with caffe

Santander_Value_Prediction_Challenge

Satellite_Imagery_Land_Classification

Spark_Examples

tensorflow

Computation using data flow graphs for scalable machine learning