juanlp

from keras.callbacks import Callback
import keras.backend as K
import numpy as np

class SGDRScheduler(Callback):
    '''Cosine annealing learning rate scheduler with periodic restarts.

    # Usage
        ```python
            schedule = SGDRScheduler(min_lr=1e-5,

juanlp

# Convert SE-ResNet-50 from Caffe to Keras
# Using the model from https://github.com/shicai/SENet-Caffe

import os
import numpy as np

# The caffe module needs to be on the Python path; we'll add it here explicitly.
import sys
caffe_root = "/path/to/caffe"
sys.path.insert(0, caffe_root + "python")

juanlp

from keras.applications.resnet50 import ResNet50, preprocess_input
from keras.preprocessing import image
import numpy as np


resnet = ResNet50(include_top=False)

def extract_features(img_paths, batch_size=64):
    """ This function extracts image features for each image in img_paths using ResNet50 bottleneck layer.
        Returned features is a numpy array with shape (len(img_paths), 2048).

juanlp

import numpy
from scipy.ndimage.interpolation import map_coordinates
from scipy.ndimage.filters import gaussian_filter

def elastic_transform(image, alpha, sigma, random_state=None):
    """Elastic deformation of images as described in [Simard2003]_.


    .. [Simard2003] Simard, Steinkraus and Platt, "Best Practices for
       Convolutional Neural Networks applied to Visual Document Analysis", in

juanlp

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.

It uses data that can be downloaded at:
https://www.kaggle.com/c/dogs-vs-cats/data

In our setup, we:
- created a data/ folder
- created train/ and validation/ subfolders inside data/

juanlp

library(shiny)
library(dplyr)
library(lubridate)

# Load libraries and functions needed to create SQLite databases.
library(RSQLite)
library(RSQLite.extfuns)
saveSQLite <- function(data, name){
  path <- dplyr:::db_location(filename=paste0(name, ".sqlite"))