full-stack-deep-learning / Fsdl Text Recognizer 2021 Labs
Licence: mit
Complete deep learning project developed in Full Stack Deep Learning, Spring 2021
Stars: ✭ 158
Labels
Projects that are alternatives of or similar to Fsdl Text Recognizer 2021 Labs
Hitchhikers Guide Machine Learning
Guide explaining and implementing fundamental machine learning algorithms in Python
Stars: ✭ 161 (+1.9%)
Mutual labels: jupyter-notebook
Real Time Facial Expression Recognition
A Deep Learning Case Study to detect one of the Seven Human Facial Expressions in Still Images and in Real Time. This model is also trained enough to Detect Facial Expressions of Animated Images.
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Pix2pix Film
An implementation of Pix2Pix in Tensorflow for use with frames from films
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Py
Repository to store sample python programs for python learning
Stars: ✭ 4,154 (+2529.11%)
Mutual labels: jupyter-notebook
Contrastivelosses4vrd
Implementation for the CVPR2019 paper "Graphical Contrastive Losses for Scene Graph Generation"
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Pytket
Python module for interfacing with the CQC t|ket> library of quantum software
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Visualizing Cnn Feature Maps
Visualizing CNN filters using PyTorch
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Load forecasting
Load forcasting on Delhi area electric power load using ARIMA, RNN, LSTM and GRU models
Stars: ✭ 160 (+1.27%)
Mutual labels: jupyter-notebook
Lolita
Using github's issue system as lightweight notes & blog.
Stars: ✭ 161 (+1.9%)
Mutual labels: jupyter-notebook
Dd Net
A lightweight network for body/hand action recognition
Stars: ✭ 161 (+1.9%)
Mutual labels: jupyter-notebook
Cs231n
My assignment solutions for CS231n - Convolutional Neural Networks for Visual Recognition
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Machine learning
Estudo e implementação dos principais algoritmos de Machine Learning em Jupyter Notebooks.
Stars: ✭ 161 (+1.9%)
Mutual labels: jupyter-notebook
Image keras
Building an image classifier using keras
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Nlp With Python
Scikit-Learn, NLTK, Spacy, Gensim, Textblob and more
Stars: ✭ 2,197 (+1290.51%)
Mutual labels: jupyter-notebook
Sas kernel
A Jupyter kernel for SAS. This opens up all the data manipulation and analytics capabilities of your SAS system within a notebook interface. Use the Jupyter Notebook interface to execute SAS code and view results inline.
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Feature Engineering Made Easy
Feature Engineering Made Easy, published by Packt
Stars: ✭ 162 (+2.53%)
Mutual labels: jupyter-notebook
Full Stack Deep Learning Spring 2021 Labs
Welcome!
As part of Full Stack Deep Learning 2021, we will incrementally develop a complete deep learning codebase to understand the content of handwritten paragraphs.
We will use the modern stack of PyTorch and PyTorch-Ligtning
We will use the main workhorses of DL today: CNNs, RNNs, and Transformers
We will manage our experiments using what we believe to be the best tool for the job: Weights & Biases
We will set up continuous integration system for our codebase using CircleCI
We will package up the prediction system as a REST API using FastAPI, and deploy it as a Docker container on AWS Lambda.
We will set up monitoring that alerts us when the incoming data distribution changes.
Sequence:
- Lab Setup: Set up our computing environment.
- Lab 1: Intro: Formulate problem, structure codebase, train an MLP for MNIST.
- Lab 2: CNNs: Introduce EMNIST, generate synthetic handwritten lines, and train CNNs.
- Lab 3: RNNs: Using CNN + LSTM with CTC loss for line text recognition.
- Lab 4: Transformers: Using Transformers for line text recognition.
- Lab 5: Experiment Management: Real handwriting data, Weights & Biases, and hyperparameter sweeps.
- Lab 6: Line Detection: Train and evaluate line detection model (or paragraph recognition).
- Lab 7: Data Management: Label our own handwriting data and properly store it.
- Lab 8: Continuous Integration: Add continuous linting and testing of our code.
- Lab 9: Deployment: Run as a REST API locally, then in Docker, then put in production using AWS Lambda.
- Lab 10: Monitoring: Set up monitoring that alerts us when the incoming data distribution changes.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].