shamanez Goto Github PK

distiller

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller

dmn-tensorflow

Dynamic Memory Networks (https://arxiv.org/abs/1603.01417) in Tensorflow

dnc

A TensorFlow implementation of the Differentiable Neural Computer.

domain-specific-ir

Information retrieval improved by a lot over the last year specially with pretrained language models. But the main bottleneck is scarcity of domain specific QA pairs.

dqfd

An implement of DQfD（Deep Q-learning from Demonstrations) raised by DeepMind:Learning from Demonstrations for Real World Reinforcement Learning

driving-interactions

dropblock

Implementation of DropBlock: A regularization method for convolutional networks in PyTorch.

dsr

dsr-1

Deep Successor Representation

easy21

Assignment of David Silver's course on Reinforcement Learning

easy21-rl

solutions to David Silver's RL course project Easy21

end-to-end-negotiator

Deal or No Deal? End-to-End Learning for Negotiation Dialogues

environment--rl

State-Action-Next State distribution to design an environment . Here is a csv Consist of a Trajectory Data

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fastmaskrcnn

Mask RCNN in TensorFlow

five-video-classification-methods

Code that accompanies my blog post outlining five video classification methods in Keras and TensorFlow

gail-tf

Tensorflow implementation of generative adversarial imitation learning

gail-with-wgan-loss-for-the-discriminator

This is about imitation learning using PPO and WGAN-GP loss. This is heavily influenced by GAIL-PPO repository in following link - https://github.com/uidilr/gail_ppo_tf. My agent will get converged to perform his task around 3384 iterations.

gail_ppo_tf

Tensorflow implementation of Generative Adversarial Imitation Learning(GAIL) with discrete action

gesture_sweep-

This is the data visualization for the gesture recognition part

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

graph_freezing_obj_detect

Script file has 8 steps . Please read them !

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-easy21

OpenAI Gym environment of the RL Assignment Easy21 together with my solution

hands-on-reinforcement-learning-with-python

Master Reinforcement and Deep Reinforcement Learning using OpenAI Gym and TensorFlow

hdf5-data_loader-tf-1.14

This is a simple testing implementation for a data-loader function in TF with hdf5 file.

hdf5-with-python

hdf5_dataloader

DataLoader subclass for PyTorch to work with HDF5 files (BETA)

home-platform

HoME: a Household Multimodal Environment is a platform for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.

how-to-learn-from-little-data

This is the code for "How to Learn from Little Data - Intro to Deep Learning #17' by Siraj Raval on YouTube