Mohamed BERRIMI's repositories
Breast_cancer_API
This a RESTFUL API that runs over a deep CNN model that have been trained to classify image if it contains Breast cancer or not.
efficientnet_3D
EfficientNets in 3D variant for keras and TF.keras
Offensive-speech-detection-in-Arabic-text
This project is a code tutorial on how to build a good Text classification pipeline from text processing, data cleaning to train and test your deep learning mode using Tensorflow Keras
Sarcasm-detection-in-Arabic-text
Tensorflow tutorial to build a Sarcasm detection model trained on Arabic dataset.
Deploying-Tensorflow-NLP-models
this project can be used to deploy an text classification pipeline using Tensorflow as a webservice using Flask.
keras_application_3D
'keras_applications_3D' is 3D-image deep learning models based on popular 2D models. (Based on the Keras)
BERT-related-papers
BERT-related papers
fake_news_detection_LSTM-TF
This notebook will guide throw the process of detecting Fake news on Social media using Machine learning algorithms and Deep LSTM using Tensorflow[]
Oct-classification-Keras
This kernel shows you how to accuratly classify retinal diseases from Optical Coherence Tomography scans using Convolutional neural nets.
Toxic-comments-detection
Toxic comments classification using LSTM ( no pretrained embeddings )
COVID-19-CNN
Classifying Covid scans using Tensorflow and Keras libraries.
Facial_expression
Detecing emotion from facial expressions using Tensorflow , keras an Sklearn
DSC-UFAS1-Solution-challange
This repo was created by DSC University of Ferhat Abbas 1 UFAS1 team to participate at the solution challenge 2020.
ORL-face-recog
Face recognition using ORL dataset in R language.
AI-Hack-Individual-
#AI Hack Tunisia #4 - Predictive analytics challenge #1 This challenge was designed specifically for the AI Tunisia Hack 2019, which takes place from 20 to 22 September. Welcome to the AI Tunisia Hack participants! The Tunisian Company of Electricity and Gas (STEG) is a public and a non-administrative company, it is responsible for delivering electricity and gas across Tunisia. The company suffered tremendous losses in the order of 200 million Tunisian Dinars due to fraudulent manipulations of meters by consumers. Using the client’s billing history, the aim of the challenge is to detect and recognize clients involved in fraudulent activities. The solution will enhance the company’s revenues and reduce the losses caused by such fraudulent activities.