I've created an application to predict emotions. But I think the application is being over fitted. And I cannot figure out how to solve the overfitting. I'm using a small data set of 107 images spread across 6 emotions.
Train.py
#Adding Seed so that random initialization is consistent
from numpy.random import seed
seed(1)
tf.set_random_seed(2)
batch_size = 3
#Prepare input data
classes = ['Anger','Disgust','Fear','Happy','Neutral','Sad','Surprise']
num_classes = len(classes)
# 20% of the data will automatically be used for validation
validation_size = 0.2
img_size = 128
num_channels = 3
train_path='C:\\Users\\Jack\\source\\repos\\Emotion Prediction\\Emotion Prediction\\training_images'
# We shall load all the training and validation images and labels into memory using openCV and use that during training
data = dataset.read_train_sets(train_path, img_size, classes, validation_size=validation_size)
print("Complete reading input data. Will Now print a snippet of it")
print("Number of files in Training-set:\t\t{}".format(len(data.train.labels)))
print("Number of files in Validation-set:\t{}".format(len(data.valid.labels)))
session = tf.Session()
x = tf.placeholder(tf.float32, shape=[None, img_size,img_size,num_channels], name='x')
## labels
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true')
y_true_cls = tf.argmax(y_true, dimension=1)
##Network graph params
filter_size_conv1 = 3
num_filters_conv1 = 32
filter_size_conv2 = 3
num_filters_conv2 = 32
filter_size_conv3 = 3
num_filters_conv3 = 64
fc_layer_size = 128
def create_weights(shape):
return tf.Variable(tf.truncated_normal(shape, stddev=0.05))
def create_biases(size):
return tf.Variable(tf.constant(0.05, shape=[size]))
def create_convolutional_layer(input,
num_input_channels,
conv_filter_size,
num_filters):
## We shall define the weights that will be trained using create_weights function.
weights = create_weights(shape=[conv_filter_size, conv_filter_size, num_input_channels, num_filters])
## We create biases using the create_biases function. These are also trained.
biases = create_biases(num_filters)
## Creating the convolutional layer
layer = tf.nn.conv2d(input=input,
filter=weights,
strides=[1, 1, 1, 1],
padding='SAME')
layer += biases #gets input and weights. strides = filter moves 1 step in both x and y directions (width and height)
## We shall be using max-pooling.
layer = tf.nn.max_pool(value=layer,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], #middle values define shape of max pooling in x and y directions, same with strides as this while down-sample and halve the input size
padding='SAME')
## Output of pooling is fed to Relu which is the activation function for us.
layer = tf.nn.relu(layer)
return layer
def create_flatten_layer(layer):
#We know that the shape of the layer will be [batch_size img_size img_size num_channels]
# But let's get it from the previous layer.
layer_shape = layer.get_shape()
## Number of features will be img_height * img_width* num_channels. But we shall calculate it in place of hard-coding it.
num_features = layer_shape[1:4].num_elements()
## Now, we Flatten the layer so we shall have to reshape to num_features
layer = tf.reshape(layer, [-1, num_features])
return layer
def create_fc_layer(input,
num_inputs,
num_outputs,
use_relu=True):
#Let's define trainable weights and biases.
weights = create_weights(shape=[num_inputs, num_outputs])
biases = create_biases(num_outputs)
# Fully connected layer takes input x and produces wx+b.Since, these are matrices, we use matmul function in Tensorflow
layer = tf.matmul(input, weights) + biases
#all_weights=[]
#w=layer.get_weights()
#all_weights.append(w)
if use_relu:
layer = tf.nn.relu(layer)
return layer
layer_conv1 = create_convolutional_layer(input=x,
num_input_channels=num_channels,
conv_filter_size=filter_size_conv1,
num_filters=num_filters_conv1)
layer_conv2 = create_convolutional_layer(input=layer_conv1,
num_input_channels=num_filters_conv1,
conv_filter_size=filter_size_conv2,
num_filters=num_filters_conv2)
layer_conv3= create_convolutional_layer(input=layer_conv2,
num_input_channels=num_filters_conv2,
conv_filter_size=filter_size_conv3,
num_filters=num_filters_conv3)
layer_flat = create_flatten_layer(layer_conv3)
layer_fc1 = create_fc_layer(input=layer_flat,
num_inputs=layer_flat.get_shape()[1:4].num_elements(),
num_outputs=fc_layer_size,
use_relu=True)
layer_fc2 = create_fc_layer(input=layer_fc1,
num_inputs=fc_layer_size,
num_outputs=num_classes,
use_relu=False)
y_pred = tf.nn.softmax(layer_fc2,name='y_pred')
y_pred_cls = tf.argmax(y_pred, dimension=1)
session.run(tf.global_variables_initializer())
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(logits=layer_fc2,
labels=y_true)
cost = tf.reduce_mean(cross_entropy) #takes in softmax of matrix multiplication and compares it to the training target via cross-entropy
optimizer = tf.train.AdamOptimizer(learning_rate=1e-4).minimize(cost)
correct_prediction = tf.equal(y_pred_cls, y_true_cls)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
session.run(tf.global_variables_initializer())
def show_progress(epoch, feed_dict_train, feed_dict_validate, val_loss):
acc = session.run(accuracy, feed_dict=feed_dict_train)
val_acc = session.run(accuracy, feed_dict=feed_dict_validate)
msg = "Training Epoch {0} --- Training Accuracy: {1:>6.1%}, Validation Accuracy: {2:>6.1%}, Validation Loss: {3:.3f}"
print(msg.format(epoch + 1, acc, val_acc, val_loss))
total_iterations = 0
saver = tf.train.Saver()
def train(num_iteration):
global total_iterations
for i in range(total_iterations,
total_iterations + num_iteration):
x_batch, y_true_batch, _, cls_batch = data.train.next_batch(batch_size)
x_valid_batch, y_valid_batch, _, valid_cls_batch = data.valid.next_batch(batch_size)
feed_dict_tr = {x: x_batch,
y_true: y_true_batch}
feed_dict_val = {x: x_valid_batch,
y_true: y_valid_batch}
session.run(optimizer, feed_dict=feed_dict_tr)
if i % int(data.train.num_examples/batch_size) == 0:
val_loss = session.run(cost, feed_dict=feed_dict_val)
epoch = int(i / int(data.train.num_examples/batch_size))
show_progress(epoch, feed_dict_tr, feed_dict_val, val_loss)
saver.save(session, './emotions-model')
total_iterations += num_iteration
train(num_iteration=3000)
Dataset.py
def load_train(train_path, image_size, classes):
images = []
labels = []
img_names = []
cls = []
print('Going to read training images')
for fields in classes:
index = classes.index(fields)
print('Now going to read {} files (Index: {})'.format(fields, index))
path = os.path.join(train_path, fields, '*g')
files = glob.glob(path)
for fl in files:
image = cv2.imread(fl)
imag
e = cv2.resize(image, (image_size, image_size),0,0, cv2.INTER_LINEAR)
image = image.astype(np.float32)
image = np.multiply(image, 1.0 / 255.0)
images.append(image)
label = np.zeros(len(classes))
label[index] = 1.0
labels.append(label)
flbase = os.path.basename(fl)
img_names.append(flbase)
cls.append(fields)
images = np.array(images)
labels = np.array(labels)
img_names = np.array(img_names)
cls = np.array(cls)
return images, labels, img_names, cls
class DataSet(object):
def __init__(self, images, labels, img_names, cls):
self._num_examples = images.shape[0]
self._images = images
self._labels = labels
self._img_names = img_names
self._cls = cls
self._epochs_done = 0
self._index_in_epoch = 0
@property
def images(self):
return self._images
@property
def labels(self):
return self._labels
@property
def img_names(self):
return self._img_names
@property
def cls(self):
return self._cls
@property
def num_examples(self):
return self._num_examples
@property
def epochs_done(self):
return self._epochs_done
def next_batch(self, batch_size):
"""Return the next `batch_size` examples from this data set."""
start = self._index_in_epoch
self._index_in_epoch += batch_size
if self._index_in_epoch > self._num_examples:
# After each epoch we update this
self._epochs_done += 1
start = 0
self._index_in_epoch = batch_size
assert batch_size <= self._num_examples
end = self._index_in_epoch
return self._images[start:end], self._labels[start:end], self._img_names[start:end], self._cls[start:end]
def read_train_sets(train_path, image_size, classes, validation_size):
class DataSets(object):
pass
data_sets = DataSets()
images, labels, img_names, cls = load_train(train_path, image_size, classes)
images, labels, img_names, cls = shuffle(images, labels, img_names, cls)
if isinstance(validation_size, float):
validation_size = int(validation_size * images.shape[0])
validation_images = images[:validation_size]
validation_labels = labels[:validation_size]
validation_img_names = img_names[:validation_size]
validation_cls = cls[:validation_size]
train_images = images[validation_size:]
train_labels = labels[validation_size:]
train_img_names = img_names[validation_size:]
train_cls = cls[validation_size:]
data_sets.train = DataSet(train_images, train_labels, train_img_names, train_cls)
data_sets.valid = DataSet(validation_images, validation_labels, validation_img_names, validation_cls)
return data_sets
Log
Training Epoch 1 --- Training Accuracy: 66.7%, Validation Accuracy: 33.3%, Validation Loss: 1.748
Training Epoch 2 --- Training Accuracy: 33.3%, Validation Accuracy: 0.0%, Validation Loss: 1.646
Training Epoch 3 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.817
Training Epoch 4 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.625
Training Epoch 5 --- Training Accuracy: 33.3%, Validation Accuracy: 0.0%, Validation Loss: 1.912
Training Epoch 6 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.750
Training Epoch 7 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.307
Training Epoch 8 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.583
Training Epoch 9 --- Training Accuracy: 33.3%, Validation Accuracy: 0.0%, Validation Loss: 1.462
Training Epoch 10 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.722
Training Epoch 11 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.644
Training Epoch 12 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.390
Training Epoch 13 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.851
Training Epoch 14 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.318
Training Epoch 15 --- Training Accuracy: 33.3%, Validation Accuracy: 33.3%, Validation Loss: 1.612
Training Epoch 16 --- Training Accuracy: 66.7%, Validation Accuracy: 33.3%, Validation Loss: 1.054
Training Epoch 17 --- Training Accuracy: 66.7%, Validation Accuracy: 66.7%, Validation Loss: 1.386
Training Epoch 18 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 2.472
Training Epoch 19 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 1.062
Training Epoch 20 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.774
Training Epoch 21 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 1.122
Training Epoch 22 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 2.418
Training Epoch 23 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 1.389
Training Epoch 24 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 2.487
Training Epoch 25 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 4.330
Training Epoch 26 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 0.823
Training Epoch 27 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 2.173
Training Epoch 28 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 1.558
Training Epoch 29 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 3.549
Training Epoch 30 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 2.107
Training Epoch 31 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 4.092
Training Epoch 32 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 6.280
Training Epoch 33 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 2.862
Training Epoch 34 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 3.318
Training Epoch 35 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 0.827
Training Epoch 36 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 3.734
Training Epoch 37 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 2.328
Training Epoch 38 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 5.210
Training Epoch 39 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 6.896
Training Epoch 40 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 4.436
Training Epoch 41 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 4.195
Training Epoch 42 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.137
Training Epoch 43 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 4.350
Training Epoch 44 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 2.736
Training Epoch 45 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 6.058
Training Epoch 46 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 7.786
Training Epoch 47 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 5.402
Training Epoch 48 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 4.846
Training Epoch 49 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.314
Training Epoch 50 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 4.814
Training Epoch 51 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 3.047
Training Epoch 52 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 6.672
Training Epoch 53 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 8.441
Training Epoch 54 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 6.159
Training Epoch 55 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 5.220
Training Epoch 56 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.452
Training Epoch 57 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 5.171
Training Epoch 58 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 3.304
Training Epoch 59 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 7.131
Training Epoch 60 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 8.937
Training Epoch 61 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 6.786
Training Epoch 62 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 5.584
Training Epoch 63 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.554
Training Epoch 64 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 5.472
Training Epoch 65 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 3.526
Training Epoch 66 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 7.537
Training Epoch 67 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 9.353
Training Epoch 68 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 7.322
Training Epoch 69 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 5.857
Training Epoch 70 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.651
Training Epoch 71 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 5.719
Training Epoch 72 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 3.716
Training Epoch 73 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 7.873
Training Epoch 74 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 9.711
Training Epoch 75 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 7.728
Training Epoch 76 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 6.105
Training Epoch 77 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.723
Training Epoch 78 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 5.940
Training Epoch 79 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 3.877
Training Epoch 80 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 8.170
Training Epoch 81 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 10.021
Training Epoch 82 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 8.164
Training Epoch 83 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 6.326
Training Epoch 84 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.792
Training Epoch 85 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 6.139
Training Epoch 86 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 4.036
Training Epoch 87 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 8.436
Training Epoch 88 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 10.302
Training Epoch 89 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 8.543
Training Epoch 90 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 6.520
Training Epoch 91 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.853
Training Epoch 92 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 6.312
Training Epoch 93 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 4.167
Training Epoch 94 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 8.675
Training Epoch 95 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 10.554
Training Epoch 96 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 8.883
Training Epoch 97 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 6.700
Training Epoch 98 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 1.906
Training Epoch 99 --- Training Accuracy: 100.0%, Validation Accuracy: 66.7%, Validation Loss: 6.469
Training Epoch 100 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 4.293
Training Epoch 101 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 8.899
Training Epoch 102 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 10.787
Training Epoch 103 --- Training Accuracy: 100.0%, Validation Accuracy: 0.0%, Validation Loss: 9.221
Training Epoch 104 --- Training Accuracy: 100.0%, Validation Accuracy: 33.3%, Validation Loss: 6.876
