Usiigaci: stain-free cell tracking in phase contrast microscopy enabled by supervised machine learning

An easy implementation of Faster R-CNN (https://arxiv.org/pdf/1506.01497.pdf) in PyTorch.

An easy implementation of FPN (https://arxiv.org/pdf/1612.03144.pdf) in PyTorch.

Detect traffic lights and classify the state of them, then give the commands "go" or "stop".

This project was made for nails segmentation using deep learning models. __DeepLabV3Plus__ was used for segmentation problem. ResNet101 were used as encoder and imagenet weights were used as encoder weights.

Implemented image caption generation method propossed in Show, Attend, and Tell paper using the Fastai framework to describe the content of images. Achieved 24 BLEU score for Beam search size of 5. Designed a Web application for model deployment using the Flask framework.

Build a image classification python web app with Streamlit and PyTorch 🐱 🐶

This is an implementation of ResNet-50/101/152.

PyTorch implementation of "Pyramid Scene Parsing Network".

My PyTorch implementation of CNNs. All networks in this repository are using CIFAR-100 dataset for training.

Contains the implementation of HyperFace: A deep multi task learning framework for facial recognition, landmark detection, pose and gender detection

[Open Source]. ARGAN - The improved version of AnimeGAN. Landscape photos/videos to anime

Pre-trained 3D CNNs

An unofficial DeepLabV2 with the pre-train weight of ImageNet.

MATLAB Fashion Classification with Deep Learning.

Implementation of DeepLabv3 in TensorFlow

Explainable Image Caption Bot: Gives captions for images with explanations for each word in the caption (The part of the image where the AI model looks to generate a word). Uses Seq-to-Seq with attention model

The objective of this project is to classify explicit content that contains inappropriate images like pornography and Hentai. The classifier used for this is ResNet50 and ResNet101 also known as Residual Neural Network. There are five categories that the model is trained on which are Porn, Hentai, Sexy, Drawing, and Neutral. Porn, Hentai, and Se…

"Advanced Machine Learning" project @ Politecnico di Torino, a.y. 2021/2022.

Drone Instance Segmentation using Mask RCNNN