piyush2896

from keras import layers as ls
from keras import models
from keras.regularizers import l2

def bn_relu_conv(in_tensor,
                 filters,
                 kernel_size,
                 strides=1,
                 padding='same',
                 weight_decay=1e-4):

piyush2896

from keras import layers as ls
from keras.models import Model

def conv_relu(in_tensor, kernel_size, filters):
    # A simple Convolution, BatchNormalization and Relu Stack
    conv = ls.Conv2D(filters, kernel_size,
                     strides=1, padding='same',
                     kernel_initializer='he_normal')(in_tensor)
    return ls.Activation('relu')(conv)

piyush2896

from keras import layers as ls
from keras.regularizers import l2
from keras.models import Model


def conv_bn_relu(in_tensor, kernel_size,
                 filters, strides,
                 padding='same', apply_relu=True,
                 weight_decay=5e-4):
    # A simple Convolution, BatchNormalization and Relu Stack

piyush2896

import keras.layers as ls #import Conv2D, DepthwiseConv2D, BatchNormalization, Dense
from keras.models import Model
from functools import partial

def depthwise_separable_conv(in_tensor, filters_pw, strides):
    l1_1 = ls.DepthwiseConv2D(3, strides=strides,
                            depth_multiplier=1, padding='same')(in_tensor)
    l1_2 = ls.BatchNormalization()(l1_1)
    l1_3 = ls.Activation('relu')(l1_2)

piyush2896

from keras import layers
from keras.models import Model

from functools import partial

conv1x1 = partial(layers.Conv2D, kernel_size=1, activation='relu')
conv3x3 = partial(layers.Conv2D, kernel_size=3, padding='same', activation='relu')
conv5x5 = partial(layers.Conv2D, kernel_size=5, padding='same', activation='relu')

def inception_module(in_tensor, c1, c3_1, c3, c5_1, c5, pp):

piyush2896

from keras import layers
from keras.models import Model

def _after_conv(in_tensor):
    norm = layers.BatchNormalization()(in_tensor)
    return layers.Activation('relu')(norm)

def conv1(in_tensor, filters):
    conv = layers.Conv2D(filters, kernel_size=1, strides=1)(in_tensor)
    return _after_conv(conv)

piyush2896

from keras import layers
from keras.models import Model, Sequential

from functools import partial

conv3 = partial(layers.Conv2D,
                kernel_size=3,
                strides=1,
                padding='same',
                activation='relu')

piyush2896

from keras import layers
from keras.models import Model

def alexnet(in_shape=(227,227,3), n_classes=1000, opt='sgd'):
    in_layer = layers.Input(in_shape)
    conv1 = layers.Conv2D(96, 11, strides=4, activation='relu')(in_layer)
    pool1 = layers.MaxPool2D(3, 2)(conv1)
    conv2 = layers.Conv2D(256, 5, strides=1, padding='same', activation='relu')(pool1)
    pool2 = layers.MaxPool2D(3, 2)(conv2)
    conv3 = layers.Conv2D(384, 3, strides=1, padding='same', activation='relu')(pool2)

piyush2896

from keras import layers
from keras.models import Model

def lenet_5(in_shape=(32,32,1), n_classes=10, opt='sgd'):
    in_layer = layers.Input(in_shape)
    conv1 = layers.Conv2D(filters=20, kernel_size=5,
                          padding='same', activation='relu')(in_layer)
    pool1 = layers.MaxPool2D()(conv1)
    conv2 = layers.Conv2D(filters=50, kernel_size=5,
                          padding='same', activation='relu')(pool1)

piyush2896

def check_armstrong(num):
    cube_sum = 0
    temp = num
    while temp >= 0:
        digit = temp % 10
        cube_sum = cube_sum + digit ** 3
        temp = temp / 10
    return cube_sum == num