Blaizzy

from sklearn.linear_model import LogisticRegression

#Creating a classifier
clf = LogisticRegression()
# Traning a testing Accuracy
model = clf.fit(X_train, y_train.values.ravel())
acc = clf.score(X_train, y_train.values.ravel())
print('Model Accuracy: ', round(acc*100,3),'%')

Blaizzy

from keras.datasets import mnist

(train_images, train_labels),(test_images, test_labels) = mnist.load_data()

Blaizzy

from keras import models
from keras import layers

nn = models.Sequential()
nn.add(Dense(512, activation = 'relu', input_shape = (28*28,)))
nn.add(Dense(256, activation = 'relu'))
nn.add(Dense(10, activation = 'softmax'))

Blaizzy

nn.compile(optimizer = 'rmsprop', 
          loss= 'categorical_crossentropy',
          metrics = ['accuracy'])

Blaizzy

train_images  = train_images.reshape((60000,28*28))
train_images = train_images.astype('float32')/255

test_images = test_images.reshape((10000,28*28))
test_images = test_images.astype('floa32t')/255

from keras.utils import to_categorical

train_images = to_categorical(train_images)
test_images = to_categorical(test_images)

Blaizzy

model.fit(training_images, train_labels, epochs = 8, batch_size = 64)

Blaizzy

test_loss, test_acc = model.evaluate(training_images, train_labels)
print('Test accuracy', test_acc)

Blaizzy

# First you might want to install & import tf 2.0
!pip install -q tensorflow==2.0.0-alpha0
import tensorflow as tf

# Let's implement a simple Linear layer (mx+b) using tf.function 
@tf.function
def add(a,b):
  return a + b

@tf.function

Blaizzy

@tf.function
def f(x):
  for i in range(10):  # Static python loop, we'll not convert it
    do_stuff()
  for i in tf.range(10):  # depends on a tensor, we'll convert it

 # function call
 f(10)

  # If you're curious you can inspect the code autograph generates.

Blaizzy

# Imports
import torch
from skimage import io, transform
import numpy as np
import matplotlib.pyplot as plt
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms, utils
from pathlib import Path

# Dataset Subclassing