joeyism

import numpy as np
import pickle
import os
import math


def __extract_file__(fname):
    with open(fname, 'rb') as fo:
        d = pickle.load(fo, encoding='bytes')
    return d

joeyism

from cifar import Cifar
from tqdm import tqdm
import tensorflow as tf
import model
import helper

learning_rate = 0.001
batch_size = 16
no_of_epochs = 10

joeyism

import tensorflow as tf

n_classes = 10
image_size = 32

dropout = tf.placeholder(tf.float32, name="dropout_rate")
input_images = tf.placeholder(tf.float32,
                              shape=[None, image_size, image_size, 3],
                              name="input_images")

joeyism

import tensorflow as tf

n_classes = 10
image_size = 32

dropout = tf.placeholder(tf.float32, name="dropout_rate")
input_images = tf.placeholder(tf.float32,
                              shape=[None, image_size, image_size, 3],
                              name="input_images")

joeyism

from cifar import Cifar
from tqdm import tqdm
import tensorflow as tf
import model
import helper

learning_rate = 0.001
batch_size = 16
no_of_epochs = 10
dropout_rate = 0.8

joeyism

import numpy as np
import pickle
import os
import math


def __extract_file__(fname):
    with open(fname, 'rb') as fo:
        d = pickle.load(fo, encoding='bytes')
    return d

joeyism

import tensorflow as tf

n_classes = 10
image_size = 32

dropout = tf.placeholder(tf.float32, name="dropout_rate")
input_images = tf.placeholder(tf.float32,
                              shape=[None, image_size, image_size, 3],
                              name="input_images")

joeyism

from numpy import *
import tensorflow as tf


image_size = 224
train_x = zeros((1, image_size, image_size ,3)).astype(float32)
xdim = train_x.shape[1:]

net_data = load(open("pretrained/bvlc_alexnet.npy", "rb"), encoding="latin1").item()

joeyism

import numpy as np


def __one_hot__(num, dim=1000):
    vec = np.zeros(dim)
    vec[num] = 1
    return vec


def transform_to_input_output(input_output, dim=1000):

joeyism

import numpy as np
import pickle
import os
import math


def __extract_file__(fname):
    with open(fname, 'rb') as fo:
        d = pickle.load(fo, encoding='bytes')
    return d