Deep-Learning-in-Python

Deep learning in Python, datacamp courses, udacity courses, own little projects

99_Python_Datacamp_21_Deep_Learning_In_Python.ipynb

Datacamp course 1

99_Python_Datacamp_29_Introduction_to_TensorFlow_In_Python.ipynb

Datacamp course 2

99_Python_Linear_Regression_with_TensorFlow.ipynb

https://medium.com/coinmonks/linear-regression-with-tensorflow-canned-estimators-6cc4ffddd14f This project is about implementing Linear Regression using TensorFlow using canned estimators. Canned Estimators are a high-level API, different from the low-level API that requires you program everything yourself. Starting by importing the required libraries.

King County housing transaction dataset. I will develop and train a machine learning model to predict house prices

99_Python_Datacamp_31_Introduction_to_Deep_Learning_with_PyTorch.ipynb

01 Introduction to PyTorch

In this first chapter, we introduce basic concepts of neural networks and deep learning using PyTorch library.

introduction to PyTorch, creating tensors in PyTorch, Matrix multiplication, forward propagation, forward pass, backpropagation by hand, backpropagation using PyTorch, Calculating gradiens in Pytorch, introduction to neural networks, your first neural network, your first PyTorch neural network.

02 Artificial Neural Networks

In this second chapter, we delve deeper into Artificial Neural Networks, learning how to train them with real datasets. Activation functions, Neural networks, ReLU activation, Loss functions, Calculation Loss function by hand, calculating loss function in PyTorch, Loss function of random scores, Preparing a dataset in PyTorch, Preparing MNist DATASET, inspecting the dataloaders, training neural networks, building a neural network, training a neural network, using the network to make predictions

03 Convolutional Neural Networks (CNNs)

In this third chapter, we introduce convolutional neural networks, learning how to train them and how to use them to make predictions Convolution operators, convolution operator - OOP way, convolution operator - functional way, pooling operators, max-pooling operator, convolutional neural networks, your first CNN - init method, your first CNN - forward() method Training Convolutional Neural Networks, Training CNNs, Using CNNs to make predictions

04 Using Convolutional Neural Networks

In this last chapter, we learn how to make neural networks work well in practice, using concepts like regularization, batch-normalization and transfer learning. The sequential module, sequential module - init method, sequential module -forward() method, the problem of overfitting, validation set, detecting overfitting, regulatization techniques, L2 - regulatization, dropout, batch-normalization, transfer learning, Finetunning a CNN, torchvision module

99_Udacity_Deep_Learning_01_PyTorch_tensors.ipynb

99_Udacity_Deep_Learning_02_PyTorch_neuralnetworks.ipynb

99_Udacity_Deep_Learning_03_PyTorch_training_NN

99_Udacity_Deep_Learning_04_PyTorch_Fashion_MNIST

99_Udacity_Deep_Learning_05_PyTorch_inference_validation

99_Udacity_Deep_Learning_06_PyTorch_saving_loading_models

99_Udacity_Deep_Learning_07_PyTorch_loading_image_data

99_Udacity_Deep_Learning_08_PyTorch_transfer_learning

Loading other models from library and using them for image classification

99_Udacity_Deep_Learning_09_PyTorch_RNN_LSTM_char

text processing with RNN LSTM

99_Udacity_Deep_Learning_10_PyTorch_RNN_time_series_prediction_simple

99_Udacity_Deep_Learning_11_PyTorch_RNN_sentiment_prediction

Predicting text reviews of movies and their negative or positive reviews

99_Udacity_Deep_Learning_12_PyTorch_in_production_Cpp

Converting PyTorch models to use in C++ production environment

99_Udacity_Deep_Learning_13_PyTorch_CNN_MNIST_no_validation

99_Udacity_Deep_Learning_14_PyTorch_CNN_with_validation

99_Udacity_Deep_Learning_15_PyTorch_CNN_custom_filters

applying filters to images for better image recognition

99_Udacity_Deep_Learning_16_PyTorch_CNN_conv_visualization

99_Udacity_Deep_Learning_17_PyTorch_CNN_maxpooling_padding

99_Udacity_Deep_Learning_18_PyTorch_CNN_CIFAR_classification

99_Udacity_Deep_Learning_19_PyTorch_CNN_classification_augmentation

99_Udacity_Deep_Learning_20_PyTorch_CNN_style_transfer_vgg19

Reading 2 images, and applying style from image1 to image2

99_Udacity_Deep_Learning_21_Keras_cels_to_farenheit

Simple prediction with tensorflow in keras convertion from celsius to farenheit using convertion data 1 layer - producing linear function that is very similar to actual conversion.

99_Udacity_Deep_Learning_21_MNIST_fashion

Fashion dataset - tshirts, shirts, skirts...etc