import sys
import itertools
import numpy as np
import tensorflow as tf
from mlp.data_providers import CIFAR10DataProvider, CIFAR100DataProvider
# check necessary environment variables are defined
assert 'MLP_DATA_DIR' in os.environ, (
'An environment variable MLP_DATA_DIR must be set to the path containing'
' MLP data before running script.')
assert 'OUTPUT_DIR' in os.environ, (
'An environment variable OUTPUT_DIR must be set to the path to write'
' output to before running script.')
# load data
train_data = CIFAR100DataProvider('train', batch_size=50, shuffle_order=False)
valid_data = CIFAR100DataProvider('valid', batch_size=50, shuffle_order=False)
train_data_coarse = CIFAR100DataProvider('train', batch_size=50, use_coarse_targets=True, shuffle_order=False)
train_data.inputs = train_data.inputs.reshape(train_data.inputs.shape[0], 32, 32, 3)
valid_data.inputs = valid_data.inputs.reshape(valid_data.inputs.shape[0], 32, 32, 3)
valid_inputs = valid_data.inputs
valid_targets = valid_data.to_one_of_k(valid_data.targets)
# ---------------- define helper functions -------------------------------------------------------------------
def fully_connected_layer(l_inputs, input_dim, output_dim, nonlinearity=tf.nn.relu):
weights = tf.Variable(
tf.truncated_normal(
[input_dim, output_dim], stddev=2. / (input_dim + output_dim) ** 0.5),
'weights')
biases = tf.Variable(tf.zeros([output_dim]), 'biases')
import datetime
import numpy as np
import tensorflow as tf
from mlp.data_providers import CIFAR10DataProvider, CIFAR100DataProvider
'''VGG_10'''
# check necessary environment variables are defined
assert 'MLP_DATA_DIR' in os.environ, (
'An environment variable MLP_DATA_DIR must be set to the path containing'
' MLP data before running script.')
assert 'OUTPUT_DIR' in os.environ, (
'An environment variable OUTPUT_DIR must be set to the path to write'
' output to before running script.')
'''In this section, I will load the data and reshape them for RGB channels'''
train_data_100 = CIFAR100DataProvider('train', batch_size=128)
valid_data_100 = CIFAR100DataProvider('valid', batch_size=128)
'''Reshape the train and valid data to -1X32X32X3'''
train_data_100.inputs = train_data_100.inputs.reshape((40000, -1, 3),
order='F')
train_data_100.inputs = train_data_100.inputs.reshape((40000, 32, 32, 3))
valid_data_100.inputs = valid_data_100.inputs.reshape((10000, -1, 3),
order='F')
valid_data_100.inputs = valid_data_100.inputs.reshape((10000, 32, 32, 3))
#change the valid targets to one hot coding
valid_targets = valid_data_100.to_one_of_k(valid_data_100.targets)
# Prepare some function for the net
def conv2d_stride1(x, W):
# # object recognition with CIFAR-100
# In[1]:
import os
import tensorflow as tf
import numpy as np
from mlp.data_providers import CIFAR10DataProvider, CIFAR100DataProvider
import matplotlib.pyplot as plt
import time
# In[2]:
seed = 10102016
rng = np.random.RandomState(seed)
train_data = CIFAR100DataProvider('train', batch_size=50, rng=rng)
valid_data = CIFAR100DataProvider('valid', batch_size=50, rng=rng)
# # Regularisation
# ## Experiment Baseline
# ### CIFAR-10
# In[3]:
def fully_connected_layer(inputs,
input_dim,
output_dim,
nonlinearity=tf.nn.relu,
dropout=False,