toshihiroryuu

import random
import math
import os

PATH=os.getcwd()
print("This is where the train, val and test files will be at  {}".format(PATH))


DATASET_FILE = '/home/Pictures/udacity_driving_datasets/labels_trainval.csv'
FILE_TRAIN = os.path.join(PATH, 'train.csv')

toshihiroryuu

import csv

PATH='/home/udacity_driving_datasets'

f1 = open('/home/quest/train.csv')
csv_f = csv.reader(f1)

toshihiroryuu

import csv

PATH='/home/quest'

f1 = open('/home/train.csv')
csv_f = csv.reader(f1)

for row in csv_f:
  name=row[0]
  listt=''

toshihiroryuu

This is a guide on how to install Caffe for Ubuntu 16.04 and above, without GPU support (No CUDA required).

Prerequisites:

OpenCV

sudo apt-get install libopencv-dev python-opencv

OpenBLAS OR Atlas

toshihiroryuu

import matplotlib.pyplot as plt
import cv2
import os
import csv

from skimage.draw import random_shapes

PATH='/home/generated_shapes'

# result = random_shapes((128, 128), max_shapes=1, shape='rectangle',

toshihiroryuu

from keras.models import Sequential
from keras.optimizers import SGD
from keras.layers import Input, Dense, Convolution2D, MaxPooling2D, AveragePooling2D, ZeroPadding2D, Dropout, Flatten, merge, Reshape, Activation

from sklearn.metrics import log_loss



def vgg16_model(img_rows, img_cols, channel=1, num_classes=None):
    """VGG 16 Model for Keras

toshihiroryuu

import os

try:
    import Augmentor
except ImportError:
    os.system('pip install Augmentor')

PATH="/path/to/image/folder"                  # path for images to be augmented 
n=200                                    # no of images after augmentation

toshihiroryuu

# Image Loading Code used for these examples
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt

img = Image.open('/home/cat.jpg')
img = np.array(img)
plt.imshow(img)
plt.show()

toshihiroryuu

# Parameters

# image : ndarray
#     Input image data. Will be converted to float.
# mode : str
#     One of the following strings, selecting the type of noise to add:

#     'gauss'     Gaussian-distributed additive noise.
#     'poisson'   Poisson-distributed noise generated from the data.
#     'saltandpepper'       Replaces random pixels with 0 or 1.

toshihiroryuu

from PIL import Image
import matplotlib.pyplot as plt
   
class pixel_transformation:
    
    def __init__(self):
        self.red_added=0
        self.green_added=0
        self.blue_added=0
        self.red_sub=0