1
L'ensemble de données d'apprentissage est constitué d'images de visage prises à partir de la base de données youtube avec une seule et unique image provenant de 256 catégories d'objets. 25k images sont choisies pour les données positives et négatives. donc totalement 50k pour la formation et une autre 10k images est prise à partir de visages yooutube et 256 catégories d'objets qui ne sont pas répétés. Le problème, c'est que j'obtiens une précision de 99% après seulement 12k itérations à la première époque et que j'imprime la valeur de coût aussi, elle commence aussi de très haute valeur comme 596014.000 comme ça. Quand il est testé contre les autres images de visage, il fonctionne très mal. cost vs epoch graphJ'ai construit un CNN pour détecter les visages humains. Dès la première époque, j'obtiens une plus grande précision. Quelle pourrait en être la raison?
import tensorflow as tf
import read_data
from sklearn import metrics
import numpy as np
import os
import graph_plotter as gp
# Parameters
learning_rate = 0.001
epochs = 30
batch_size = 100
display_step = 5
# tf Graph input
input_data = tf.placeholder(tf.float32, [None, 27, 31, 3])
output_data = tf.placeholder(tf.float32, [None, 1])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# Getting train and test data
train_data, train_label , test_data, test_label = read_data.getData()
def conv2d(x, w, bias, k=1):
x = tf.nn.conv2d(x, w, strides=[1, k, k, 1], padding='SAME')
x = tf.nn.bias_add(x, bias)
return tf.nn.relu(x)
# Performs max pooling on the convolution layer output
def maxpool2d(x, k=2):
return tf.nn.max_pool(x,
ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')
# Weights generated randomly according to layer
weights = {
# Conv 4*4 , 1 input , 32 outputs
'wc1': tf.Variable(tf.random_normal([4, 4, 3, 32])),
# Conv 3*3 , 32 inputs , 32 outputs
'wc2': tf.Variable(tf.random_normal([3, 3, 32, 64])),
# Conv 5*6 , 64 input , 128 outputs
'wc3': tf.Variable(tf.random_normal([5, 6, 64, 128])),
# Conv 1*1 , 128 inputs , 256 outputs
'wc4': tf.Variable(tf.random_normal([1, 1, 128, 256])),
# Conv 1*1 , 256 inputs , 256 outputs
'wc5': tf.Variable(tf.random_normal([1, 1, 256, 512])),
# Output Layer 7*8*256 inputs and 1 output (face or non-face)
'out': tf.Variable(tf.random_normal([7*8*512, 1]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bc3': tf.Variable(tf.random_normal([128])),
'bc4': tf.Variable(tf.random_normal([256])),
'bc5': tf.Variable(tf.random_normal([512])),
'out': tf.Variable(tf.random_normal([1]))
}
def model(x, weight, bias, dropout):
# Layer 1
conv1 = conv2d(x, weight['wc1'], bias['bc1'])
conv1 = maxpool2d(conv1, k=2)
# Layer 2
conv2 = conv2d(conv1, weight['wc2'], bias['bc2'])
conv2 = maxpool2d(conv2, k=2)
# Layer 3
conv3 = conv2d(conv2, weight['wc3'], bias['bc3'])
# Layer 4
conv4 = conv2d(conv3, weight['wc4'], bias['bc4'])
# Layer 5
conv5 = conv2d(conv4, weight['wc5'], bias['bc5'])
#conv5 = tf.nn.dropout(conv5, dropout)
# Flattening data
intermediate = tf.reshape(conv5, shape=[-1, 7*8*512])
# Output Layer
output = tf.add(tf.matmul(intermediate, weight['out']), bias['out'])
return output
pred = model(input_data, weights, biases, keep_prob)
l2_loss = 0.001*(
tf.nn.l2_loss(weights.get('wc4')) +
tf.nn.l2_loss(weights.get('wc5')) +
tf.nn.l2_loss(weights.get('out')))
cost = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(
pred, output_data)) + l2_loss
tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
correct_pred = tf.equal(
tf.greater(sigmoid_output, 0.5), tf.greater(output_data, 0.5))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
y_p = tf.cast(tf.greater(sigmoid_output, 0.5), tf.int32)
saver = tf.train.Saver()
tf.add_to_collection('y_p', y_p)
tf.add_to_collection('pred', pred)
tf.add_to_collection('x', input_data)
tf.add_to_collection('y', output_data)
init = tf.global_variables_initializer()
with tf.device("/gpu:0"):
with tf.Session() as sess:
sess.run(init)
train_data_minibatches = [train_data[k:k + batch_size]
for k in range(0, len(train_data), batch_size)]
train_label_minibatches = [train_label[k:k + batch_size]
for k in range(0, len(train_label), batch_size)]
step = 0
batch_count = 0
avg_cost_list = []
avg_accuracy_list = []
for epoch in range(epochs):
print('Epoch '+epoch.__str__())
cost_list = []
accuracy_list = []
for batch_x, batch_y in zip(
train_data_minibatches, train_label_minibatches):
batch_count += 1
sess.run(optimizer, feed_dict={
input_data: batch_x, output_data: batch_y,
keep_prob: 0.75})
# if epoch % display_step == 0:
loss, acc, output = sess.run([cost, accuracy, sig],
feed_dict={input_data: batch_x, output_data: batch_y, keep_prob: 0.75})
cost_list.append(loss)
accuracy_list.append(acc)
print("Iter " + str(step * batch_size) +" Loss "+ "{:.5f}".format(loss)+ ", Training Accuracy= " +
"{:.5f}".format(acc))
step += 1
average_cost = sum(cost_list)/len(cost_list)
average_acc = sum(accuracy_list)/len(accuracy_list)
avg_cost_list.append(average_cost)
avg_accuracy_list.append(average_acc)
if epoch % display_step == 0:
test_acc, y_pred = sess.run([accuracy, y_p], feed_dict={input_data: test_data,
output_data: test_label,
keep_prob: 0.75})
print(metrics.confusion_matrix(test_label, y_pred))
print("Testing Accuracy : " + "{:.5f}".format(test_acc))
print("Optimization finished !!")
# Saving cost Vs epoch graph, and accuracy Vs epoch graphs.
gp.cost_vs_epoch(avg_cost_list)
gp.accuracy_vs_epoch(avg_accuracy_list)
save_path = saver.save(sess=sess, save_path=save_path, write_meta_graph=True)