jy00002 Goto Github PK

gluon-cv

Gluon CV Toolkit

google-research

Google AI Research

guided-attention-inference-network

Contains implementation of Guided Attention Inference Network (GAIN) presented in Tell Me Where to Look(CVPR 2018). This repository aims to apply GAIN on fcn8 architecture used for segmentation.

homework

store the homeworks in master course

how-to-python-and-machine-learning-book

How to Python and Machine Learning book code repository

human_protein_atlas_image_classification

icassp19

Public repository for the paper "Learning Sound Event Classifiers from Web Audio with Noisy Labels"

ict

image-enhancment

Image Enhancment project to improve the image through some implemented algorithms like Denosing , Dehazing , Color-Balancing and Low-Light Enhancement

imbalanced-learn

A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning

intelligent_anti_jamming

A simulation framework for anti-jamming communication, which includes some intellgient anti-jamming examples.

jinnan2019

Jinnan2019 Restricted product monitoring

kaggle-ensemble-guide

Code for the Kaggle Ensembling Guide Article on MLWave

kaggle-freesound-audio-tagging

8th place solution to the Freesound General-Purpose Audio Tagging Challenge on Kaggle

kaggle-imaterialist

The First Place Solution of Kaggle iMaterialist (Fashion) 2019 at FGVC6

kaggle-ndsb

Winning solution for the National Data Science Bowl competition on Kaggle (plankton classification)

kaggle-nips-2017-adversarial-attack

5th place solution in "NIPS 2017: Non-targeted Adversarial Attack" (with solution in targeted attack and defence)

kaggle-vsb-baseline

kaggle-vsb-power

:zap: Abandoned but interesting attempt

kaggle_freesound

Code for Freesound General-Purpose Audio Tagging Challenge

kaggle_ndsb2017

Kaggle datascience bowl 2017

kapre

kapre: Keras Audio Preprocessors

keras-attention-mechanism

Attention mechanism Implementation for Keras.

keras-nas-pgrl

Neural Architecture Search (NAS) using policy gradient Reinforcement Learning (RL)

keras-nasnet

"NASNet" models in Keras 2.0+ with weights

l-gm_loss_pytorch

Rethinking Feature Distribution for Loss Functions in Image Classification

learning_invariances_in_speech_recognition

In this work I investigate the speech command task developing and analyzing deep learning models. The state of the art technology uses convolutional neural networks (CNN) because of their intrinsic nature of learning correlated represen- tations as is the speech. In particular I develop different CNNs trained on the Google Speech Command Dataset and tested on different scenarios. A main problem on speech recognition consists in the differences on pronunciations of words among different people: one way of building an invariant model to variability is to augment the dataset perturbing the input. In this work I study two kind of augmentations: the Vocal Tract Length Perturbation (VTLP) and the Synchronous Overlap and Add (SOLA) that locally perturb the input in frequency and time respectively. The models trained on augmented data outperforms in accuracy, precision and recall all the models trained on the normal dataset. Also the design of CNNs has impact on learning invariances: the inception CNN architecture in fact helps on learning features that are invariant to speech variability using different kind of kernel sizes for convolution. Intuitively this is because of the implicit capability of the model on detecting different speech pattern lengths in the audio feature.

lenet-for-amc

A Family of Automatic Modulation Recognition Models Based on Domain Knowledge for Various Platforms source code

lightnet

LightNet: Light-weight Networks for Semantic Image Segmentation (Cityscapes and Mapillary Vistas Dataset)

lstm_attention

attention-based LSTM/Dense implemented by Keras