cantonioupao

pytorch-human_action_recognition_breakfast_dataset-C3D_model_implementation

This repository implements the Breakfast Action Dataset in Pytorch and aims to achieve a high human action recognition using the C3D model

cervical_cancer_detection

A deep learning framework for cervical cancer detection to allow improved accuracy for PAP smear test results

face-depth-3D-reconstruction

This is the repository for the face depth regressor implementation. Given a single-view input image, the neural network regressor, predicts dense depth pixel values, and achieves 3D reconstruction of the entire face. The model is trained on synthetic EG3D generated data.

generate-synthetic-face-data

This repository, generates photorealistic face synthetic data, as well as the the corresponding depthmaps and 3D face structure/mesh

3d-virtual-chatbot

This is the repository for the master thesis project of a 3D virtual chatbot

multimodal-driving-data

This is part of the DLAD (Deep Learning for Autonomous Driving) course from ETH. This is part of the 1st project that aims to deepen the understanding on multimodal driving data

3d-player-pose-estimation

This is a novel implementation of 3D player pose estimation, using the so called Super Triangulation method, to find pose correspondences in multi-view streams and perform the 3D reconstruction

eg3d-code-regressor

Given a single'view face image, our regressor model predicts the intermediate latent code w of the EG3D generator model.

MTCNN-KerasForMCU

This is a Keras implementation (Python) of a tweaked version of MTCNN for suitable MCU deployment

susDAO-saveMe

SaveMe: A token for health

angular-app-as-electron-native-app

This is a repository for turning a simple Angular App into an Electron App, that can be packaged into a native app, for any OS

ecg-classification

Raw ECG classification of a time-series imbalanced NaN dataset

eg3d

Face_Detection-Serial-Image-Sender

face_normals

FIN4Xplorer

Demonstrator-Frontend to explore the post-monetary design space

HRNet-Semantic-Segmentation

This is an official implementation of semantic segmentation for our TPAMI paper "Deep High-Resolution Representation Learning for Visual Recognition". https://arxiv.org/abs/1908.07919

MGCDA

Domain Adaptation for Semantic Segmentation at Nighttime

Microcontroller-Image-Sender

Simple Python GUI to resize and send via serial, images to Microcontrollers

MTCNN-C-Implementation

These are 2 different implementation of MTCNN in C. The code was generated using CubeAI and the source project is built on KeiluVision5. The 3 CNN model architectures and model weights initially generated by CubeAI can be found under "". The full implementation is found in the main.c file.

OwnDataset-Face-Calssification-withSVM

This is a fast implementation of a face classification system trained from scratch to your own dataset. The implementation is based on Facenet from keras, on MTCNN for face extraction and on an SVM for face identification/recognition/verification.

prosopo-dataset

Prosopo: A dataset for face 3D reconstruction evaluation of real high quality face images

pytorch-video-recognition

PyTorch implemented C3D, R3D, R2Plus1D models for video activity recognition.

saveMe-a-token-for-health

SaveMe: A token for health

SuperGluePretrainedNetwork

SuperGlue: Learning Feature Matching with Graph Neural Networks (CVPR 2020, Oral)

text-to-image-generator-webapp

This is a collection of useful notebooks to build an ML application that focuses on generating images from text, without explicit content policy. The application is also hosted online using ngrok, directly on your google colab notebook.

unet-depth-prediction

predicting depth from single rgb images using u-net architecture

Yolo-Tiny-Face-Classification-Keras

This is a Yolo Implementation of the Tiny Darknet architecture for Face Classification and Detection