Caffe's configuration for Cohn-Kanade dataset - image-processing

I'm trying to make a facial expression recognizer using Caffe and the Cohn-Kanade database.
This is my train prototxt configuration:
def configureTrainProtoTxt(lmdb, batch_size):
n = caffe.NetSpec()
n.data, n.label = L.Data(batch_size=batch_size, backend=P.Data.LMDB, source=lmdb,
transform_param=dict(scale= 1 / 126.0), ntop=2)
n.conv1 = L.Convolution(n.data, kernel_size=2, pad=1, param=dict(lr_mult=1), num_output=10, weight_filler=dict(type='xavier'))
n.conv1 = L.Convolution(n.data, kernel_size=2, pad=1, param=dict(lr_mult=1), num_output=10, weight_filler=dict(type='xavier'))
n.conv1 = L.Convolution(n.data, kernel_size=5, pad=0, num_output=20, weight_filler=dict(type='xavier'))
n.pool1 = L.Pooling(n.conv1, kernel_size=5, stride=2, pool=P.Pooling.MAX)
n.conv2 = L.Convolution(n.pool1, kernel_size=3, num_output=10, weight_filler=dict(type='xavier'))
n.pool2 = L.Pooling(n.conv2, kernel_size=2, stride=2, pool=P.Pooling.MAX)
n.ip1 = L.InnerProduct(n.pool2, num_output=100, weight_filler=dict(type='xavier'))
n.relu1 = L.ReLU(n.ip1, in_place=True)
n.ip2 = L.InnerProduct(n.relu1, num_output=2, weight_filler=dict(type='xavier'))
n.loss = L.SoftmaxWithLoss(n.ip2, n.label)
return n.to_proto()
This is my trainning function, that I got it from lenet example:
def train(solver):
niter = 200
test_interval = 10
train_loss = zeros(niter)
test_acc = zeros(int(np.ceil(niter / test_interval)))
output = zeros((niter, 32, 2))
for it in range(niter):
solver.step(1)
train_loss[it] = solver.net.blobs['loss'].data
solver.test_nets[0].forward(start='conv1')
output[it] = solver.test_nets[0].blobs['ip2'].data[:32]
if it % test_interval == 0:
print 'Iteration', it, 'testing...'
correct = 0
for test_it in range(100):
solver.test_nets[0].forward()
correct += sum(solver.test_nets[0].blobs['ip2'].data.argmax(1) == solver.test_nets[0].blobs['label'].data)
test_acc[it // test_interval] = correct / 1e4
_, ax1 = subplots()
ax2 = ax1.twinx()
ax1.plot(arange(niter), train_loss)
ax2.plot(test_interval * arange(len(test_acc)), test_acc, 'r')
ax1.set_xlabel('iteration')
ax1.set_ylabel('train loss')
ax2.set_ylabel('test accuracy')
show()
I'm only using the Neutral and Surprise faces (if I solve my problem I'll use more emotions). But my net has only 28% of accuracy. I'd like to know the low accuracy has to with a problem in the network configuration, with the logic inside my train function or if my training db is too small?. This is my dataset discription:
Train dataset: 56 images of Neutral faces. 60 images of Surprise faces.
Test dataset: 15 images of Neutral faces. 15 images of Surprise faces.
All images are 32x32 and in grayscale.
And my batch_size is 32.
Please, can someone help me to known what is my problem?

Related

Accuracy value goes up and down on the training process

After training the network I noticed that accuracy goes up and down. Initially I thought it is caused by the learning rate, but it is set to quite small value. Please check the screenshot attached.
Plot Accuracy Screenshot
My network (in Pytorch) looks as follow:
class Network(nn.Module):
def __init__(self):
super(Network,self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(3,16,kernel_size=3),
nn.ReLU(),
nn.MaxPool2d(2)
)
self.layer2 = nn.Sequential(
nn.Conv2d(16,32, kernel_size=3),
nn.ReLU(),
nn.MaxPool2d(2)
)
self.layer3 = nn.Sequential(
nn.Conv2d(32,64, kernel_size=3),
nn.ReLU(),
nn.MaxPool2d(2)
)
self.fc1 = nn.Linear(17*17*64,512)
self.fc2 = nn.Linear(512,1)
self.relu = nn.ReLU()
self.sigmoid = nn.Sigmoid()
def forward(self,x):
out = self.layer1(x)
out = self.layer2(out)
out = self.layer3(out)
out = out.view(out.size(0),-1)
out = self.relu(self.fc1(out))
out = self.fc2(out)
out = torch.sigmoid(out)
return out
I am using RMSprop as optimizer and BCELoss as criterion. The learning rate is set to 0.001
Here is the training process:
epochs = 15
itr = 1
p_itr = 100
model.train()
total_loss = 0
loss_list = []
acc_list = []
for epoch in range(epochs):
for samples, labels in train_loader:
samples, labels = samples.to(device), labels.to(device)
optimizer.zero_grad()
output = model(samples)
labels = labels.unsqueeze(-1)
labels = labels.float()
loss = criterion(output, labels)
loss.backward()
optimizer.step()
total_loss += loss.item()
scheduler.step()
if itr%p_itr == 0:
pred = torch.argmax(output, dim=1)
correct = pred.eq(labels)
acc = torch.mean(correct.float())
print('[Epoch {}/{}] Iteration {} -> Train Loss: {:.4f}, Accuracy: {:.3f}'.format(epoch+1, epochs, itr, total_loss/p_itr, acc))
loss_list.append(total_loss/p_itr)
acc_list.append(acc)
total_loss = 0
itr += 1
My dataset is quite small - 2000 train and 1000 validation (binary classification 0/1). I wanted to do the 80/20 split but I was asked to keep it like that. I was thinking that the architecture might be too complex for such a small dataset.
Any hits what may cause such jumps in the training process?
Your code here is wrong: pred = torch.argmax(output, dim=1)
This line using for multiclass classification with Cross-Entropy Loss.
Your task is binary classification so the pred values are wrong. Change to:
if itr%p_itr == 0:
pred = torch.round(output)
....
You can change your optimizer to Adam, SGD, or RMSprop to find the suitable optimizer that helps your model coverage faster.
Also change the forward() function:
def forward(self,x):
out = self.layer1(x)
out = self.layer2(out)
out = self.layer3(out)
out = out.view(out.size(0),-1)
out = self.relu(self.fc1(out))
out = self.fc2(out)
return self.sigmoid(out) #use your forward is ok, but this cleaner

When training a multi class CNN with PyTorch displays extraordinarily large loss

I am currently trying train a CNN using PyTorch to predict a subject's age. The age group ranges from 0 to 116. I used the same model to train it on gender classification with two options: male or female.
I ported the same code for the age classification, I was getting errors. The error was due to our last fully connected layer not return a large enough output (in terms of matrix size, it was initially returning a 50 x 2 matrix due to our gender classifier but I switched it to 50 x 117 for the age classification based on the total age options.)
My issue now is that the training loop prints epochs with a huge loss (~3.5 while before, when training the gender classification, it was sub zero.)
Below is my code:
DataLoader class:
class MyDataset(Dataset):
def __init__(self, root_directory, csv_file, image_path, transform = None):
annotated_path = os.path.relpath(csv_file) # Path to UTKFace Dataset and Annotations
self.read_in_csv = pd.read_csv(annotated_path, index_col=False)
self.image_path = os.path.join(root_directory, image_path)
self.transform = transform
self.labels = np.asarray(self.read_in_csv.loc[:,'age'])
def __getitem__(self, index):
attr = self.labels[index]
image_name = str(self.read_in_csv.loc[index, 'file'])
image = Image.open(image_name)
if self.transform:
image = self.transform(image)
dict = {'image':image, 'label':attr}
return dict
def __len__(self):
return len(self.read_in_csv.index)
CNN Architecture:
class ConvolutionalNN(nn.Module):
def __init__(self):
super(ConvolutionalNN,self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(3,96,kernel_size=7,stride=4),
nn.BatchNorm2d(96), # Number of Features
nn.ReLU(),
nn.MaxPool2d(kernel_size=3,stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(96,256,kernel_size=5,padding=2),
nn.BatchNorm2d(256),
nn.ReLU(), # Default = False
nn.MaxPool2d(kernel_size=3,stride=2))
self.layer3 = nn.Sequential(
nn.Conv2d(256,384,kernel_size=3,padding=1),
nn.BatchNorm2d(384),
nn.ReLU(),
nn.MaxPool2d(kernel_size=3,stride=2))
self.fc1 = nn.Linear(384*6*6,512)
self.fc2 = nn.Linear(512,512)
self.fc3 = nn.Linear(512,117)
def forward(self,x):
out = self.layer1(x)
out = self.layer2(out)
out = self.layer3(out)
out = out.view(out.size(0),-1)
#print out.size()
out = F.dropout(F.relu(self.fc1(out)))
out = F.dropout(F.relu(self.fc2(out)))
out = self.fc3(out)
return out
Training Loop:
def training_loop(checkpoint = None, best=False):
current_epoch = 1
num_epochs = 50
train_acc_history = []
val_acc_history = []
epoch_history = []
learning_rate = 0.001
best_val_acc = 0.0
is_best = False
criterion = nn.CrossEntropyLoss()
## Predict the Age and Gender of the Human in the Image
optimizer = torch.optim.SGD(cnn.parameters(),lr=0.001,momentum=0.9)
if checkpoint is not None:
is_best = best
current_epoch = checkpoint['epoch']
train_acc_history = checkpoint['train_acc_history']
val_acc_history = checkpoint['val_acc_history']
best_val_acc = checkpoint['best_val_acc']
optimizer.load_state_dict(checkpoint['optimizer'])
epoch_history = checkpoint['epoch_history']
print('Uploading our images now...')
for epoch in range(current_epoch, num_epochs + current_epoch):
print('Starting epoch %d / %d' % (epoch + 1, num_epochs + current_epoch))
print('Learning Rate for this epoch: {}'.format(learning_rate))
for i, batch in enumerate(train_loader):
images, labels = batch['image'], batch['label']
images = images.clone().detach()
labels = labels.clone().detach()
if use_gpu:
images = images.cuda()
labels = labels.cuda()
optimizer.zero_grad()
pred_labels = cnn(images)
loss = criterion(pred_labels,labels)
loss.backward()
optimizer.step()
So this is my code. It does not seem to be training well.
Please let me know on what could be done to fix this.

Transfer Learning using Keras and vgg16 on small dataset

I have to build a neural network that can recognize the face of 15 people. I'm using keras. My dataset is composed of 300 total images and is divided into Training, Validation and Test. For each of the 15 people I have the following subdivision:
Training: 13
Validation: 3
Test: 4
Since I couldn't build an efficient neural network from scratch, I also believe because my dataset is very small, I'm trying to solve my problem by doing transfer learning. I used the vgg16 network. In the training and validation phase I get good results but when I run the tests the results are disastrous.
I don't know what my problem is. Here is the code I used:
img_width, img_height = 256, 256
train_data_dir = 'dataset_biometria/face/training_set'
validation_data_dir = 'dataset_biometria/face/validation_set'
nb_train_samples = 20
nb_validation_samples = 20
batch_size = 16
epochs = 5
model = applications.VGG19(weights = "imagenet", include_top=False, input_shape = (img_width, img_height, 3))
for layer in model.layers:
layer.trainable = False
#Adding custom Layers
x = model.output
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
x = Dropout(0.4)(x)
x = Dense(1024, activation="relu")(x)
predictions = Dense(15, activation="softmax")(x)
# creating the final model
model_final = Model(input = model.input, output = predictions)
# compile the model
model_final.compile(loss = "categorical_crossentropy", optimizer = optimizers.SGD(lr=0.0001, momentum=0.9), metrics=["accuracy"])
# Initiate the train and test generators with data Augumentation
train_datagen = ImageDataGenerator(
rescale = 1./255,
horizontal_flip = True,
fill_mode = "nearest",
zoom_range = 0.3,
width_shift_range = 0.3,
height_shift_range=0.3,
rotation_range=30)
test_datagen = ImageDataGenerator(
rescale = 1./255,
horizontal_flip = True,
fill_mode = "nearest",
zoom_range = 0.3,
width_shift_range = 0.3,
height_shift_range=0.3,
rotation_range=30)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size = (img_height, img_width),
batch_size = batch_size,
class_mode = "categorical")
validation_generator = test_datagen.flow_from_directory(
validation_data_dir,
target_size = (img_height, img_width),
class_mode = "categorical")
# Save the model according to the conditions
checkpoint = ModelCheckpoint("vgg16_1.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
early = EarlyStopping(monitor='val_acc', min_delta=0, patience=10, verbose=1, mode='auto')
# Train the model
model_final.fit_generator(
train_generator,
samples_per_epoch = nb_train_samples,
epochs = epochs,
validation_data = validation_generator,
nb_val_samples = nb_validation_samples,
callbacks = [checkpoint, early])
model('model_face_classification.h5')
I also tried to train some layers instead of not training any, as in the example below:
for layer in model.layers[:10]:
layer.trainable = False
I also tried changing the number of epochs, batch size, nb_validation_samples, nb_validation_sample.
Unfortunately the result has not changed, in the testing phase my network cannot correctly recognize faces.
Without seeing the actual results or errors I can not say what the problem is here.
Definitely, small dataset is a problem, but there are many ways to get around it.
You can use image augmentation to increase the samples. You can refer augement.py.
But instead of modifying your above network, there is a really cool model : siamese network/one-shot learning. It does not need too many pics and the accuracies are great.
Therefore you can see below links to get some help :
Facial-Recognition-Using-FaceNet-Siamese-One-Shot-Learning
Face-recognition-using-deep-learning

Neural Network does not perform well on the CIFAR-10 dataset

I have been trying to implement a CNN on the CIFAR-10 dataset for a few days and my test set accuracy does not seem to go beyond the 10% and the error just hang around 69.07733. I have tweaking the model and few days but in vain. I haven't been able to spot out where I am going wrong. Please help me recognise the fault in the model. Here is the code for it:
import os
import sys
import pickle
import tensorflow as tf
import numpy as np
from matplotlib import pyplot as plt
data_root = './cifar-10-batches-py'
train_data = np.ndarray(shape=(50000,3072), dtype=np.float32)
train_labels = np.ndarray(shape=(50000), dtype=np.float32)
num_images = 0
test_data = np.ndarray(shape=(10000,3072),dtype = np.float32)
test_labels = np.ndarray(shape=(10000),dtype=np.float32)
meta_data = {}
for file in os.listdir(data_root):
file_path = os.path.join(data_root,file)
with open(file_path,'rb') as f:
temp = pickle.load(f,encoding ='bytes')
if file == 'batches.meta':
for i,j in enumerate(temp[b'label_names']):
meta_data[i] = j
if 'data_batch_' in file:
for i in range(10000):
train_data[num_images,:] = temp[b'data'][i]
train_labels[num_images] = temp[b'labels'][i]
num_images += 1
if 'test_batch' in file:
for i in range(10000):
test_data[i,:] = temp[b'data'][i]
test_labels[i] = temp[b'labels'][i]
'''
print('meta: \n',meta_data)
train_data = train_data.reshape(50000,3,32,32).transpose(0,2,3,1)
print('\ntrain data: \n',train_data.shape,'\nLabels: \n',train_labels[0])
print('\ntest data: \n',test_data[0].shape,'\nLabels: \n',train_labels[0])'''
#accuracy function acc = (no. of correct prediction/total attempts) * 100
def accuracy(predictions, labels):
return (100 * (np.sum(np.argmax(predictions,1)== np.argmax(labels, 1))/predictions.shape[0]))
#reformat the data
def reformat(data,labels):
data = data.reshape(data.shape[0],3,32,32).transpose(0,2,3,1).astype(np.float32)
labels = (np.arange(10) == labels[:,None]).astype(np.float32)
return data,labels
train_data, train_labels = reformat(train_data,train_labels)
test_data, test_labels = reformat(test_data, test_labels)
print ('Train ',train_data[0][1])
plt.axis("off")
plt.imshow(train_data[1], interpolation = 'nearest')
plt.savefig("1.png")
plt.show()
'''
print("Train: \n",train_data.shape,test_data[0],"\nLabels: \n",train_labels.shape,train_labels[:11])
print("Test: \n",test_data.shape,test_data[0],"\nLabels: \n",test_labels.shape,test_labels[:11])'''
image_size = 32
num_channels = 3
batch_size = 30
patch_size = 5
depth = 64
num_hidden = 256
num_labels = 10
graph = tf.Graph()
with graph.as_default():
#input data and labels
train_input = tf.placeholder(tf.float32,shape=(batch_size,image_size,image_size,num_channels))
train_output = tf.placeholder(tf.float32,shape=(batch_size,num_labels))
test_input = tf.constant(test_data)
#layer weights and biases
layer_1_weights = tf.Variable(tf.truncated_normal([patch_size,patch_size,num_channels,depth]))
layer_1_biases = tf.Variable(tf.zeros([depth]))
layer_2_weights = tf.Variable(tf.truncated_normal([patch_size,patch_size,depth,depth]))
layer_2_biases = tf.Variable(tf.constant(0.1, shape=[depth]))
layer_3_weights = tf.Variable(tf.truncated_normal([64*64, num_hidden]))
layer_3_biases = tf.Variable(tf.constant(0.1, shape=[num_hidden]))
layer_4_weights = tf.Variable(tf.truncated_normal([num_hidden, num_labels]))
layer_4_biases = tf.Variable(tf.constant(0.1, shape=[num_labels]))
def convnet(data):
conv_1 = tf.nn.conv2d(data, layer_1_weights,[1,1,1,1], padding = 'SAME')
hidden_1 = tf.nn.relu(conv_1+layer_1_biases)
norm_1 = tf.nn.lrn(hidden_1, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
pool_1 = tf.nn.max_pool(norm_1,[1,2,2,1],[1,2,2,1], padding ='SAME')
conv_2 = tf.nn.conv2d(pool_1,layer_2_weights,[1,1,1,1], padding = 'SAME')
hidden_2 = tf.nn.relu(conv_2+layer_2_biases)
norm_2 = tf.nn.lrn(hidden_2, 4, bias=1.0, alpha=0.001 / 9.0, beta=0.75)
pool_2 = tf.nn.max_pool(norm_2,[1,2,2,1],[1,2,2,1], padding ='SAME')
shape = pool_2.get_shape().as_list()
hidd2_trans = tf.reshape(pool_2,[shape[0],shape[1]*shape[2]*shape[3]])
hidden_3 = tf.nn.relu(tf.matmul(hidd2_trans,layer_3_weights) + layer_3_biases)
return tf.nn.relu(tf.matmul(hidden_3,layer_4_weights) + layer_4_biases)
logits = convnet(train_input)
loss = tf.reduce_sum(tf.nn.softmax_cross_entropy_with_logits(labels=train_output, logits = logits))
optimizer = tf.train.AdamOptimizer(1e-4).minimize(loss)
train_prediction = tf.nn.softmax(logits)
test_prediction = tf.nn.softmax(convnet(test_input))
num_steps = 100000
with tf.Session(graph=graph) as session:
tf.global_variables_initializer().run()
print('Initialized \n')
for step in range(num_steps):
offset = (step * batch_size) % (train_labels.shape[0] - batch_size)
batch = train_data[offset:(offset+batch_size),:,:,:]
batch_labels = train_labels[offset:(offset+batch_size),:]
feed_dict ={train_input: batch, train_output: batch_labels}
_,l,prediction = session.run([optimizer, loss, train_prediction], feed_dict = feed_dict)
if (step % 500 == 0):
print("Loss at step %d: %f" %(step, l))
print("Accuracy: %f" %(accuracy(prediction, batch_labels)))
print("Test accuracy: %f" %(accuracy(session.run(test_prediction), test_labels)))
On a first glance I would say the initialization of the CNN is the culprit. A convnet is an optimization algorithm in a highly non-convex space and therefore depends a lot on careful initialization to not get stuck on local minima or saddle points. Look at xavier initialization for an example on how to fix that.
Example Code:
W = tf.get_variable("W", shape=[784, 256],
initializer=tf.contrib.layers.xavier_initializer())
Problem is your network is having very high depth(number of filters = 64 for both layers). Also, you are training the network from scratch. And your dataset of CIFAR10 (50000 images) is very little. Moreover, each CIFAR10 image is only 32x32x3 size.
Couple of alternatives what I can suggest you is to retrain a pre-trained model, i.e do transfer learning.
Other better alternative is to reduce the number of filters in each layer. In this way, you will be able to train the model from scratch and also it will be faster. (Assuming you don't have GPU).
Next you are making use of local response normalization. I would suggest you to remove this layer and do mean normalization in pre-processing step.
Next, if you feel the learning is not picking up at all, try increasing the learning rate a little and see.
Lastly, just to reduce some operation in your code, you are reshaping your tensor and then doing transpose in many places like this:
data.reshape(data.shape[0],3,32,32).transpose(0,2,3,1)
Why not directly reshape it to something like this?
data.reshape(data.shape[0], 32, 32, 3)
Hope the answer helps you.

very large value of loss in AlexNet

Actually I am using AlexNet to classify my images in 2 groups , I am feeding images to the model in a batch of 60 images and the loss which I am getting after every batch is 6 to 7 digits large (for ex. 1428529.0) , here I am confused that why my loss is such a large value because on MNIST dataset the loss which I got was very small as compared to this. Can anyone explain me why I am getting such a large loss value.
Thanks in advance ;-)
Here is the code :-
import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
import os
img_size = 227
num_channels = 1
img_flat_size = img_size * img_size
num_classes = 2
drop = 0.5
x = tf.placeholder(tf.float32,[None,img_flat_size])
y = tf.placeholder(tf.float32,[None,num_classes])
drop_p = tf.placeholder(tf.float32)
def new_weight(shape):
return tf.Variable(tf.random_normal(shape))
def new_bias(size):
return tf.Variable(tf.random_normal(size))
def new_conv(x,num_input_channels,filter_size,num_filters,stride,padd="SAME"):
shape = [filter_size,filter_size,num_input_channels,num_filters]
weight = new_weight(shape)
bias = new_bias([num_filters])
conv = tf.nn.conv2d(x,weight,strides=[1,stride,stride,1],padding=padd)
conv = tf.nn.bias_add(conv,bias)
return tf.nn.relu(conv)
def new_max_pool(x,k,stride):
max_pool = tf.nn.max_pool(x,ksize=[1,k,k,1],strides=[1,stride,stride,1],padding="VALID")
return max_pool
def flatten_layer(layer):
layer_shape = layer.get_shape()
num_features = layer_shape[1:4].num_elements()
flat_layer = tf.reshape(layer,[-1,num_features])
return flat_layer,num_features
def new_fc_layer(x,num_input,num_output):
weight = new_weight([num_input,num_output])
bias = new_bias([num_output])
fc_layer = tf.matmul(x,weight) + bias
return fc_layer
def lrn(x, radius, alpha, beta, bias=1.0):
"""Create a local response normalization layer."""
return tf.nn.local_response_normalization(x, depth_radius=radius,
alpha=alpha, beta=beta,
bias=bias)
def AlexNet(x,drop,img_size):
x = tf.reshape(x,shape=[-1,img_size,img_size,1])
conv1 = new_conv(x,num_channels,11,96,4,"VALID")
max_pool1 = new_max_pool(conv1,3,2)
norm1 = lrn(max_pool1, 2, 2e-05, 0.75)
conv2 = new_conv(norm1,96,5,256,1)
max_pool2 = new_max_pool(conv2,3,2)
norm2 = lrn(max_pool2, 2, 2e-05, 0.75)
conv3 = new_conv(norm2,256,3,384,1)
conv4 = new_conv(conv3,384,3,384,1)
conv5 = new_conv(conv4,384,3,256,1)
max_pool3 = new_max_pool(conv5,3,2)
layer , num_features = flatten_layer(max_pool3)
fc1 = new_fc_layer(layer,num_features,4096)
fc1 = tf.nn.relu(fc1)
fc1 = tf.nn.dropout(fc1,drop)
fc2 = new_fc_layer(fc1,4096,4096)
fc2 = tf.nn.relu(fc2)
fc2 = tf.nn.dropout(fc2,drop)
out = new_fc_layer(fc2,4096,2)
return out #, tf.nn.softmax(out)
def read_and_decode(tfrecords_file, batch_size):
'''read and decode tfrecord file, generate (image, label) batches
Args:
tfrecords_file: the directory of tfrecord file
batch_size: number of images in each batch
Returns:
image: 4D tensor - [batch_size, width, height, channel]
label: 1D tensor - [batch_size]
'''
# make an input queue from the tfrecord file
filename_queue = tf.train.string_input_producer([tfrecords_file])
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
img_features = tf.parse_single_example(
serialized_example,
features={
'label': tf.FixedLenFeature([], tf.int64),
'image_raw': tf.FixedLenFeature([], tf.string),
})
image = tf.decode_raw(img_features['image_raw'], tf.uint8)
##########################################################
# you can put data augmentation here, I didn't use it
##########################################################
# all the images of notMNIST are 28*28, you need to change the image size if you use other dataset.
image = tf.reshape(image, [227, 227])
label = tf.cast(img_features['label'], tf.int32)
image_batch, label_batch = tf.train.batch([image, label],
batch_size= batch_size,
num_threads= 1,
capacity = 6000)
return tf.reshape(image_batch,[batch_size,227*227*1]), tf.reshape(label_batch, [batch_size])
pred = AlexNet(x,drop_p,img_size) #pred
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred,labels=y))
optimiser = tf.train.AdamOptimizer(learning_rate = 0.001).minimize(loss)
correct_pred = tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct_pred,tf.float32))
cost = tf.summary.scalar('loss',loss)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
merge_summary = tf.summary.merge_all()
summary_writer = tf.summary.FileWriter('./AlexNet',graph = tf.get_default_graph())
tf_record_file = 'train.tfrecords'
x_val ,y_val = read_and_decode(tf_record_file,20)
y_val = tf.one_hot(y_val,depth=2,on_value=1,off_value=0)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
x_val = x_val.eval()
y_val = y_val.eval()
epoch = 2
for i in range(epoch):
_, summary= sess.run([optimiser,merge_summary],feed_dict={x:x_val,y:y_val,drop_p:drop})
summary_writer.add_summary(summary,i)
loss_a,accu = sess.run([loss,accuracy],feed_dict={x:x_val,y:y_val,drop_p:1.0})
print "Epoch "+str(i+1) +', Minibatch Loss = '+ \
"{:.6f}".format(loss_a) + ', Training Accuracy = '+ \
'{:.5f}'.format(accu)
print "Optimization Finished!"
tf_record_file1 = 'test.tfrecords'
x_v ,y_v = read_and_decode(tf_record_file1,10)
y_v = tf.one_hot(y_v,depth=2,on_value=1,off_value=0)
coord1 = tf.train.Coordinator()
threads1 = tf.train.start_queue_runners(coord=coord1)
x_v = sess.run(x_v)
y_v = sess.run(y_v)
print "Testing Accuracy : "
print sess.run(accuracy,feed_dict={x:x_v,y:y_v,drop_p:1.0})
coord.request_stop()
coord.join(threads)
coord1.request_stop()
coord1.join(threads1)
Take a look a what a confusion matrix is. It is a performance evaluator. In addition, you should compare your precision versus your recall. Precision is the accuracy of your positive predictions and recall is the ratio of positive instances that are correctly detected by the classifier. By combining both precision and recall, you get the F_1 score which is keep in evaluating the problems of your model.
I would suggest you pick up the text Hands-On Machine Learning with Scikit-Learn and TensorFlow. It is a truly comprehensive book and covers what I describe above in more detail.

Resources