Cannot improve accuracy of AlexNet on Oxford-102 (

Hi I tried to implement AlexNet without using pretrained weights. I tried to train the net on Oxford-102 dataset, but I keep getting 0.9% accuracy throughout the process and changing the parameters are not helping, below the code can someone help me out?

I was following this tutorial

I switched the given test set (which is larger) to use as training set, and given training to use as testing set. I used Gradient Descent as the optimizer.

I constructed pretty much the same AlexNet as the given article did, might be something wrong with the way I calculate the accuracy?

Below is the way I load data

import os
import sys
import warnings

import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
%matplotlib inline

from skimage.io import imread
from skimage.transform import resize

from scipy.io import loadmat

import tensorflow as tf

warnings.filterwarnings('ignore', category=UserWarning, module='skimage')

set_ids = loadmat('setid.mat')

set_ids

test_ids = set_ids['trnid'].tolist()[0]
train_ids = set_ids['tstid'].tolist()[0]

def indexes_processing(int_list):
    returned_list = []
    for index, element in enumerate(int_list):
        returned_list.append(str(element))
    for index, element in enumerate(returned_list):
        if int(element) < 10:
            returned_list[index] = '0000' + element
        elif int(element) < 100:
            returned_list[index] = '000' + element
        elif int(element) < 1000:
            returned_list[index] = '00' + element
        else:
            returned_list[index] = '0' + element
    return returned_list

raw_train_ids = indexes_processing(train_ids)
raw_test_ids = indexes_processing(test_ids)

train_images = []
test_images = []
train_labels = []
test_labels = []

image_labels = (loadmat('imagelabels.mat')['labels'] - 1).tolist()[0]

labels = ['pink primrose', 'hard-leaved pocket orchid', 'canterbury bells', 'sweet pea', 'english marigold', 'tiger lily', 'moon orchid', 'bird of paradise', 'monkshood', 'globe thistle', 'snapdragon', "colt's foot", 'king protea', 'spear thistle', 'yellow iris', 'globe-flower', 'purple coneflower', 'peruvian lily', 'balloon flower', 'giant white arum lily', 'fire lily', 'pincushion flower', 'fritillary', 'red ginger', 'grape hyacinth', 'corn poppy', 'prince of wales feathers', 'stemless gentian', 'artichoke', 'sweet william', 'carnation', 'garden phlox', 'love in the mist', 'mexican aster', 'alpine sea holly', 'ruby-lipped cattleya', 'cape flower', 'great masterwort', 'siam tulip', 'lenten rose', 'barbeton daisy', 'daffodil', 'sword lily', 'poinsettia', 'bolero deep blue', 'wallflower', 'marigold', 'buttercup', 'oxeye daisy', 'common dandelion', 'petunia', 'wild pansy', 'primula', 'sunflower', 'pelargonium', 'bishop of llandaff', 'gaura', 'geranium', 'orange dahlia', 'pink-yellow dahlia?', 'cautleya spicata', 'japanese anemone', 'black-eyed susan', 'silverbush', 'californian poppy', 'osteospermum', 'spring crocus', 'bearded iris', 'windflower', 'tree poppy', 'gazania', 'azalea', 'water lily', 'rose', 'thorn apple', 'morning glory', 'passion flower', 'lotus', 'toad lily', 'anthurium', 'frangipani', 'clematis', 'hibiscus', 'columbine', 'desert-rose', 'tree mallow', 'magnolia', 'cyclamen ', 'watercress', 'canna lily', 'hippeastrum ', 'bee balm', 'ball moss', 'foxglove', 'bougainvillea', 'camellia', 'mallow', 'mexican petunia', 'bromelia', 'blanket flower', 'trumpet creeper', 'blackberry lily']

labels[16]

def one_hot_encode(labels):
    '''
    One hot encode the output labels to be numpy arrays of 0s and 1s
    '''
    out = np.zeros((len(labels), 102))
    for index, element in enumerate(labels):
        out[index, element] = 1
    return out

class ProcessImage():

    def __init__(self):           
        self.i = 0

        self.training_images = np.zeros((6149, 227, 227, 3))
        self.training_labels = None

        self.testing_images = np.zeros((1020, 227, 227, 3))
        self.testing_labels = None

    def set_up_images(self):
        print('Processing Training Images...')
        i = 0
        for element in raw_train_ids:
            img = imread('jpg/image_{}.jpg'.format(element))
            img = resize(img, (227, 227))
            self.training_images[i] = img
            i += 1
        print('Done!')

        i = 0
        print('Processing Testing Images...')
        for element in raw_test_ids:
            img = imread('jpg/image_{}.jpg'.format(element))
            img = resize(img, (227, 227))
            self.testing_images[i] = img
            i += 1
        print('Done!')

        print('Processing Training and Testing Labels...')
        encoded_labels = one_hot_encode(image_labels)
        for train_id in train_ids:
            train_labels.append(encoded_labels[train_id - 1])
        for test_id in test_ids:
            test_labels.append(encoded_labels[test_id - 1])
        self.training_labels = train_labels
        self.testing_labels = test_labels
        print('Done!')

    def next_batch(self, batch_size):
        x = self.training_images[self.i:self.i + batch_size]
        y = self.training_labels[self.i:self.i + batch_size]
        self.i = (self.i + batch_size) % len(self.training_images)
        return x, y

image_processor = ProcessImage()

image_processor.set_up_images()

My Graph

# Helper Functions for AlexNet
def init_weights(filter_height, filter_width, num_channels, num_filters):
    init_random_dist = tf.truncated_normal([filter_height, filter_width, num_channels, num_filters], stddev=0.1)
    return tf.Variable(init_random_dist)

def init_bias(shape):
    init_bias_vals = tf.constant(0.1, shape=shape)
    return tf.Variable(init_bias_vals)

def conv2d(x, W, stride_y, stride_x, padding='SAME'):
    return tf.nn.conv2d(x, W, strides=[1,stride_y,stride_x,1], padding=padding)

def max_pool(x, filter_height, filter_width, stride_y, stride_x, padding='SAME'):
    return tf.nn.max_pool(x, ksize=[1,filter_height,filter_width,1], strides=[1,stride_y,stride_x,1], padding=padding)

def conv_layer(input_x, filter_height, filter_width, num_channels, num_filters, stride_y, stride_x, padding='SAME', groups=1):
    W = init_weights(filter_height, filter_width, int(num_channels/groups), num_filters)
    b = init_bias([num_filters])
    convolve = lambda i, k: tf.nn.conv2d(i, k, strides=[1,stride_y,stride_x,1], padding=padding)
    if groups == 1:
        conv = convolve(input_x, W)
    else:
        input_groups = tf.split(axis=3, num_or_size_splits=groups, value=input_x)
        weight_groups = tf.split(axis=3, num_or_size_splits=groups, value=W)
        output_groups = [convolve(i, k) for i, k in zip(input_groups, weight_groups)]
        conv = tf.concat(axis=3, values=output_groups)
    bias = tf.reshape(tf.nn.bias_add(conv, b), tf.shape(conv))
    return tf.nn.relu(bias)

def lrn(x, radius, alpha, beta, bias=1.0):
    return tf.nn.local_response_normalization(x, depth_radius=radius, alpha=alpha, beta=beta, bias=bias)

def fully_connected(input_layer, num_in, num_out, relu=True):
    W = tf.truncated_normal([num_in, num_out], stddev=0.1)
    W = tf.Variable(W)
    b = init_bias([num_out])
    out = tf.nn.xw_plus_b(input_layer, W, b)
    if relu:
        return tf.nn.relu(out)
    else:
        return out

def drop_out(x, keep_prob):
    return tf.nn.dropout(x, keep_prob=keep_prob)

x = tf.placeholder(tf.float32, shape=[None, 227, 227, 3])
y_true = tf.placeholder(tf.float32, shape=[None, 102])
keep_prob = tf.placeholder(tf.float32)

# Create the graph

# 1st Layer: Conv (w ReLu) -> Lrn -> Pool
conv_1 = conv_layer(x, filter_height=11, filter_width=11, num_channels=3, num_filters=96, stride_y=4, stride_x=4, padding='VALID')
norm_1 = lrn(conv_1, radius=2, alpha=1e-05, beta=0.75)
pool_1 = max_pool(norm_1, filter_height=3, filter_width=3, stride_y=2, stride_x=2, padding='VALID')
pool_1.get_shape()

# 2nd Layer: Conv (w ReLu) -> Lrn -> Pool
conv_2 = conv_layer(pool_1, filter_height=5, filter_width=5, num_channels=96, num_filters=256, stride_y=1, stride_x=1, groups=2)
norm_2 = lrn(conv_2, radius=2, alpha=1e-05, beta=0.75)
pool_2 = max_pool(norm_2, filter_height=3, filter_width=3, stride_y=2, stride_x=2, padding='VALID')

# 3rd Layer: Conv (w ReLu)
conv_3 = conv_layer(pool_2, filter_height=3, filter_width=3, num_channels=256, num_filters=384, stride_y=1, stride_x=1)

# 4th Layer: Conv (w ReLu)
conv_4 = conv_layer(conv_3, filter_height=3, filter_width=3, num_channels=384, num_filters=384, stride_y=1, stride_x=1, groups=2)

# 5th Layer: Conv (w ReLu) -> Pool
conv_5 = conv_layer(conv_4, filter_height=3, filter_width=3, num_channels=384, num_filters=256, stride_y=1, stride_x=1, groups=2)
pool_5 = max_pool(conv_5, filter_height=3, filter_width=3, stride_y=2, stride_x=2, padding='VALID')

# 6th Layer: Flatten -> FC (w ReLu) -> Dropout
pool_6_flat = tf.reshape(pool_5, [-1, 6*6*256])
full_6 = fully_connected(pool_6_flat, 6*6*256, 4096)
full_6_dropout = drop_out(full_6, keep_prob)

# 7th Layer: FC (w ReLu) -> Dropout
full_7 = fully_connected(full_6_dropout, 4096, 4096)
full_7_dropout = drop_out(full_7, keep_prob)

# 8th Layer: FC and return unscaled activations
y_pred = fully_connected(full_7_dropout, 4096, 102, relu=False)

The loss function and the optimizer

cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_true,logits=y_pred))

optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.01)
train = optimizer.minimize(cross_entropy)

init = tf.global_variables_initializer()
saver = tf.train.Saver()

Run the session

with tf.Session() as sess:
    sess.run(init)
    for i in range(15000):
        batches = image_processor.next_batch(128)
        sess.run(train, feed_dict={x:batches[0], y_true:batches[1], keep_prob:0.5})

        if (i%1000 == 0):
            print('On Step {}'.format(i))
            print('Accuracy is: ')
            matches = tf.equal(tf.argmax(y_pred, 1), tf.argmax(y_true, 1))
            acc = tf.reduce_mean(tf.cast(matches, tf.float32))

            print(sess.run(acc, feed_dict={x:image_processor.testing_images, y_true:image_processor.testing_labels, keep_prob:1.0}))

            print('Saving model...')
            saver.save(sess, 'models/model_iter.ckpt', global_step=i)
            print('Saved at step: {}'.format(i))
            print('\n')
    print('Saving final model...')
    saver.save(sess, 'models/model_final.ckpt')
    print('Saved')

I kept getting the same accuracy of 0.00903922 over and over again (throughout the 15000 epochs) no matter how hard I tried to change the parameters, I even tried to change the size of the images from 224 to 227 but it still gave me the same accuracy of 0.00903922.

Your accuracy looks fine to me although it's a bit strange to be defined each time in the loop.

What does bother me is the fact that you train for only ten steps. It seems that your training set consists of 6149 images and you are training 128 images in a batch. Doing this ten times, you have looked at 1280 out of 6000 images - way too few to see an effect in the accuracy.

Instead, you want to look at all the training data - that's around 48 training steps, or one epoch - and you better want to do this a couple of times. The exact number of epochs depends on multiple factors like the data and network but you should at least take 10 epochs - so that's 480 training steps.