mohapatras

[{
	"name": "Albariño",
	"species": "Vitis vinifera 'Alvarinho'",
	"description": "Albariño or Alvarinho is a variety of white wine grape grown in Galicia (northwest Spain), Monção and Melgaço (northwest Portugal), where it is used to make varietal white wines. Albariño is the Galician name for the grape. In Portugal it is known as Alvarinho, and sometimes as Cainho Branco.It was presumably brought to Iberia by Cluny monks in the twelfth century[citation needed]. Its name 'Alba-Riño' means 'the white from the Rhine' and it has locally been thought to be a Riesling clone originating from the Alsace region of France, although earliest known records of Riesling as a grape variety date from the 15th, rather than the 12th, century. It is also theorized that the grape is a close relative of the French grape Petit Manseng.It should not be confused with the Alvarinho Liláz grape of Madeira.",
	"thumbnail": "https://raw.githubusercontent.com/Bhabani2077/images/master/varietalswine/albarino.png",
	"image": "https://raw

mohapatras

[{
	"thumbnail": "https://raw.githubusercontent.com/Bhabani2077/images/master/gallerybeer/american_amber_ale_thumb.jpg",
	"image": "https://raw.githubusercontent.com/Bhabani2077/images/master/gallerybeer/american_amber_ale_main.jpg",
	"caption": "Primarily a catch all for any beer less than a Dark Ale in color, ranging from amber (duh) to deep red hues. This style of beer tends to focus on the malts, but hop character can range from low to high."
}, {
	"thumbnail": "https://raw.githubusercontent.com/Bhabani2077/images/master/gallerybeer/american_dark_lager_main_thumb.png",
	"image": "https://raw.githubusercontent.com/Bhabani2077/images/master/gallerybeer/american_dark_lager_main.jpg",
	"caption": "This beer's malt aroma and flavor are low but notable. Its color ranges from a very deep copper to a deep, dark brown. It has a clean, light body with discreet contributions from caramel and roasted malts."
}, {
	"thumbnail": "https://raw.githubusercontent.com/Bhabani2077/images/master/gallerybeer/belgian_beer_thumb

mohapatras

[{
	"name": "Plan B",
	"latitude": 12.9716,
	"longitude": 77.5946
}, {
	"name": "Locals",
	"latitude": 12.933290,
	"longitude": 77.622964
}, {
	"name": "Toit",

mohapatras

// Use Gists to store code you would like to remember later on
console.log(window); // log the "window" object to the console

mohapatras

'''
I managed to export a Keras model for Tensorflow Serving (not sure whether it is the official way to do 
this). My first trial prior to creating my custom model was to use a trained model available on
Keras such as VGG19.
Here is how I did (I put in separate boxes to help understanding and because I use Jupyter :)):
'''

#Creating the model

import keras.backend as K

mohapatras

FROM: http://benanne.github.io/2015/03/17/plankton.html

Meta-Tricks:
	- Use %10 for validation with STRATIFIED SAMPLING (my mistake)
	- Cyclic Pooling 
	- Leaky ReLU = max(x, a*x) learned a
		- reduces overfitting with a ~= 1/3
	- Orthogonal initialization http://arxiv.org/pdf/1312.6120v3.pdf
	- Use larger weight decay for larger models since otherwise some layers might diverge

mohapatras

# memory growth options for keras and tensorflow.
from keras import backend as K
cfg = K.tf.ConfigProto()
cfg.gpu_options.allow_growth = True
K.set_session(K.tf.Session(config=cfg))

mohapatras

# CUDA version
nvcc --version
which nvcc
# CudaNN version
# Use the output of which nvcc to locate your cuda
cat /usr/include/x86_64-linux-gnu/cudnn_v*.h | grep CUDNN_MAJOR -A 2

mohapatras

import numpy as np
import warnings
import os
import tensorflow as tf

from keras.layers import Input
from keras import layers
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Flatten

mohapatras

# keras example imports
from keras.models import load_model
 
## extra imports to set GPU options
import tensorflow as tf
from keras import backend as k
 
###################################
# TensorFlow wizardry
config = tf.ConfigProto()