Skip to content

Instantly share code, notes, and snippets.

Avatar

Mohd Sanad Zaki Rizvi mohdsanadzakirizvi

View GitHub Profile
View fcnn_vgg.py
model2 = Sequential()
model2.add(Flatten(input_shape=(7,7,512)))
model2.add(Dense(100, activation='relu'))
model2.add(Dropout(0.5))
model2.add(BatchNormalization())
model2.add(Dense(10, activation='softmax'))
# compile the model
model2.compile(optimizer='adam', metrics=['accuracy'], loss='categorical_crossentropy')
View cnn_base.py
from keras.models import Sequential
from keras.layers import Conv2D, MaxPool2D, Flatten, Dense, InputLayer, BatchNormalization, Dropout
# build a sequential model
model = Sequential()
model.add(InputLayer(input_shape=(224, 224, 3)))
# 1st conv block
model.add(Conv2D(25, (5, 5), activation='relu', strides=(1, 1), padding='same'))
model.add(MaxPool2D(pool_size=(2, 2), padding='same'))
View datagen.py
from keras.preprocessing.image import ImageDataGenerator
# create a new generator
imagegen = ImageDataGenerator()
# load train data
train = imagegen.flow_from_directory("imagenette2/train/", class_mode="categorical", shuffle=False, batch_size=128, target_size=(224, 224))
# load val data
val = imagegen.flow_from_directory("imagenette2/val/", class_mode="categorical", shuffle=False, batch_size=128, target_size=(224, 224))
View imagenette_map.py
imagenette_map = {
"n01440764" : "tench",
"n02102040" : "springer",
"n02979186" : "casette_player",
"n03000684" : "chain_saw",
"n03028079" : "church",
"n03394916" : "French_horn",
"n03417042" : "garbage_truck",
"n03425413" : "gas_pump",
"n03445777" : "golf_ball",
View cnn_cifar10.py
# keras imports for the dataset and building our neural network
from keras.datasets import cifar10
from keras.models import Sequential
from keras.layers import Dense, Dropout, Conv2D, MaxPool2D, Flatten
from keras.utils import np_utils
# loading the dataset
(X_train, y_train), (X_test, y_test) = cifar10.load_data()
# # building the input vector from the 32x32 pixels
View cnn_mnist.py
# keras imports for the dataset and building our neural network
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Conv2D, MaxPool2D, Flatten
from keras.utils import np_utils
# to calculate accuracy
from sklearn.metrics import accuracy_score
# loading the dataset
View mnist_nn.py
# keras imports for the dataset and building our neural network
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Conv2D, MaxPool2D
from keras.utils import np_utils
# Flattening the images from the 28x28 pixels to 1D 787 pixels
X_train = X_train.reshape(60000, 784)
X_test = X_test.reshape(10000, 784)
View re_nlp.py
import re
import nltk
nltk.download('stopwords')
# download stopwords list from nltk
from nltk.corpus import stopwords
stop_words = set(stopwords.words('english'))
def clean_text(text):
View re_dates.py
import re
re.findall(r"(\d{4})-(\d{2})-(\d{2})", date)
View html.py
html = """<table class="vertical-navbox nowraplinks" style="float:right;clear:right;width:22.0em;margin:0 0 1.0em 1.0em;background:#f9f9f9;border:1px solid #aaa;padding:0.2em;border-spacing:0.4em 0;text-align:center;line-height:1.4em;font-size:88%"><tbody><tr><th style="padding:0.2em 0.4em 0.2em;font-size:145%;line-height:1.2em"><a href="/wiki/Machine_learning" title="Machine learning">Machine learning</a> and<br /><a href="/wiki/Data_mining" title="Data mining">data mining</a></th></tr><tr><td style="padding:0.2em 0 0.4em;padding:0.25em 0.25em 0.75em;"><a href="/wiki/File:Kernel_Machine.svg" class="image"><img alt="Kernel Machine.svg" src="//upload.wikimedia.org/wikipedia/commons/thumb/f/fe/Kernel_Machine.svg/220px-Kernel_Machine.svg.png" decoding="async" width="220" height="100" srcset="//upload.wikimedia.org/wikipedia/commons/thumb/f/fe/Kernel_Machine.svg/330px-Kernel_Machine.svg.png 1.5x, //upload.wikimedia.org/wikipedia/commons/thumb/f/fe/Kernel_Machine.svg/440px-Kernel_Machine.svg.png 2x" data-file-widt
You can’t perform that action at this time.