Pinned Repositories
caffe
modified version of caffe which support DeconvNet and DecoupledNet
DeconvNet
DeconvNet : Learning Deconvolution Network for Semantic Segmentation
DecoupledNet
DecoupledNet: Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation
DPPnet
DPPnet: Image Question Answering using Convolutional Neural Network with Dynamic Parameter Prediction
my_ubuntu_settings
RAU_VQA
Training Recurrent Answering Units with Joint Loss Minimization for VQA
voc_classification
VQA-Transfer-ExternalData
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
vqa_task_discovery
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
VQABrowser
Qualitative / quantitative evaluation tool for Visual Question Answering dataset.
HyeonwooNoh's Repositories
HyeonwooNoh/vqa_task_discovery
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
HyeonwooNoh/voc_classification
HyeonwooNoh/VQA-Transfer-ExternalData
Transfer Learning via Unsupervised Task Discovery for Visual Question Answering
HyeonwooNoh/my_ubuntu_settings
HyeonwooNoh/RAU_VQA
Training Recurrent Answering Units with Joint Loss Minimization for VQA
HyeonwooNoh/HyeonwooNoh.github.io
HyeonwooNoh/Gumbel-Softmax-VAE-in-tensorflow
Semi-Supervised Learning with Categorical VAE (experimented on MNIST)
HyeonwooNoh/ViZDoomDeterministic
HyeonwooNoh/bi-att-flow
Bidirectional Attention Flow
HyeonwooNoh/bottom-up-attention
Bottom-up attention model for image captioning and VQA, based on Faster R-CNN and Visual Genome
HyeonwooNoh/bottom-up-attention-vqa
An efficient PyTorch implementation of the winning entry of the 2017 VQA Challenge.
HyeonwooNoh/clevr-dataset-gen
A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
HyeonwooNoh/densecap
Dense image captioning in Torch
HyeonwooNoh/ffjpeg
a simple jpeg codec.
HyeonwooNoh/gym-minigrid
Minimalistic gridworld package for OpenAI Gym
HyeonwooNoh/maml
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
HyeonwooNoh/MulLowBiVQA
Hadamard Product for Low-rank Bilinear Pooling
HyeonwooNoh/NerveNet
HyeonwooNoh/nmt
TensorFlow Neural Machine Translation Tutorial
HyeonwooNoh/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
HyeonwooNoh/pytorch-vqa
Strong baseline for visual question answering
HyeonwooNoh/Relation-Network-Tensorflow
Tensorflow implementations of Relational Networks and a VQA dataset named Sort-of-CLEVR proposed by DeepMind.
HyeonwooNoh/rl-starter-files
RL starter files in order to immediatly train, visualize and evaluate an agent without writing any line of code
HyeonwooNoh/sac
Soft Actor-Critic
HyeonwooNoh/Settings
HyeonwooNoh/Temporary
HyeonwooNoh/tensorflow_hw
Computation using data flow graphs for scalable machine learning
HyeonwooNoh/torch-ac
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms: A2C and PPO
HyeonwooNoh/Visual-Question-Answering
CNN+LSTM, Attention based, and MUTAN-based models for Visual Question Answering
HyeonwooNoh/wide-residual-networks-iwdrop
3.8% and 18.3% on CIFAR-10 and CIFAR-100