dnkirill

dnkirill

def augmented_batch_generator(X, y, batch_size, rotations=True, affine=True,
                              shear_angle=0.0, scale_margins=[0.8, 1.5], p=0.35):
    """Augmented batch generator. Splits the dataset into batches and augments each
    batch independently.
    
    Args:
        X: numpy array with images.
        y: list of labels.
        batch_size: the size of the output batch.
        rotations: whether to apply `flips_rotations_augmentation` function to dataset.

dnkirill

import numpy as np

def flips_rotations_augmentation(X, y):
    """A pipeline for applying augmentation functions listed in `augmentation_table`
    to a numpy array with images X.
    """
    # Initializing empty arrays to accumulate intermediate results of augmentation
    X_out, y_out = np.empty([0] + list(X.shape[1:]), dtype=np.float32), np.empty([0])
    
    # Cycling through all label classes and applying all available transformations

dnkirill

import pandas as pd

# Generate an augmented dataset using a transform table
augmentation_table = pd.read_csv('augmentation_table.csv', index_col='label_class')

augmentation_table.drop('label_name', axis=1, inplace=True)
augmentation_table.dropna(axis=0, how='all', inplace=True)

# Collect all global functions in global namespace
namespace = __import__(__name__)

dnkirill

dnkirill

import numpy as np
from skimage import transform
from skimage.transform import warp, AffineTransform

def rotate_90_deg(X):    
    X_aug = np.zeros_like(X)
    for i,img in enumerate(X):
        X_aug[i] = transform.rotate(img, 270.0)
    return X_aug

dnkirill

import multiprocessing
import ipyparallel as ipp
import numpy as np

def preprocess_equalize(X, y, bins=256, cpu=multiprocessing.cpu_count()):
    """ A simplified version of a function which manages multiprocessing logic. 
    This function always grayscales input images, though it can be generalized
    to apply any arbitrary function to batches.

    Args:

dnkirill

from skimage import exposure

def grayscale_exposure_equalize(batch_x_y):
    """Processes a batch with images by grayscaling, normalization and
    histogram equalization.
    
    Args:
        batch_x_y: a single batch of data containing a numpy array of images
            and a list of corresponding labels.
    

dnkirill

echo
echo "This installation sets up a P2 instance on AWS (Ubuntu 14.04 only), installs all necessary packages"
echo "which are required for CUDA, TensorFlow, Keras, Caffe and Torch."
echo

# Install dependencies
sudo apt-get update
sudo apt-get --assume-yes upgrade
sudo apt-get install -y build-essential git python-pip libfreetype6-dev libxft-dev libncurses-dev libopenblas-dev gfortran python-matplotlib libblas-dev liblapack-dev libatlas-base-dev python-dev python-pydot linux-headers-generic linux-image-extra-virtual unzip python-numpy swig python-pandas python-sklearn zip
sudo pip install -U pip

dnkirill

#luarocks install loadcaffe 
#luarocks install hdf5

#git clone https://github.com/karpathy/neuraltalk2; cd neuraltalk2

#wget http://cs.stanford.edu/people/karpathy/neuraltalk2/checkpoint_v1.zip
#unzip checkpoint_v1.zip -d data
#mkdir samples; cd samples
#wget https://s3-eu-west-1.amazonaws.com/dl-npl/img.zip
#unzip img.zip