Pinned Repositories
CapsNet-for-Iceberg-or-Submarine-Classification
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.
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.
Nearby_Restaurants_Weather_Offers
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.
sdhayalk's Repositories
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.
sdhayalk/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.
sdhayalk/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.
sdhayalk/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.
sdhayalk/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.
sdhayalk/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
sdhayalk/CapsNet-for-Iceberg-or-Submarine-Classification
sdhayalk/Nearby_Restaurants_Weather_Offers
sdhayalk/AdTracking_Fraud_Detection_TalkingData
sdhayalk/advdbSpatialTest
sdhayalk/BinaryNet-on-tensorflow
binary weight neural network implementation on tensorflow
sdhayalk/caffe_practice
sdhayalk/Data_Structures_Implementation
sdhayalk/generative-models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
sdhayalk/Generative_Adversarial_Networks
sdhayalk/git_test
sdhayalk/Hadoop_MapReduce_Examples
sdhayalk/Insurance_Filing_Prediction
sdhayalk/Logo_Image_Data_Augmentation
sdhayalk/Lung_Cancer_Detection
sdhayalk/MNIST_Digit_Recognizer_Kaggle
Test Accuracy: 99.4%. Kaggle Rank: Top 13%. Convolutional neural network using TensorFlow to correctly identify digits from handwritten images
sdhayalk/models
Models and examples built with TensorFlow
sdhayalk/python-geospatial-analysis-cookbook
Over 60 recipes to work with topology, overlays and indoor routing
sdhayalk/rcnn
R-CNN: Regions with Convolutional Neural Network Features
sdhayalk/Realtime_Advertisement_Statistics_Using_CNN
sdhayalk/resnet-imagenet-caffe
train resnet on imagenet from scratch with caffe
sdhayalk/Santander_Value_Prediction_Challenge
sdhayalk/Satellite_Imagery_Land_Classification
sdhayalk/Spark_Examples
sdhayalk/tensorflow
Computation using data flow graphs for scalable machine learning