我正在尝试使用tensorflow实现一个简单的深度卷积神经网络性别分类器。我找到了这个模型并进行了实现。
def create_model_v2(data):
cl1_desc = {'weights':weight_variable([7,7,3,96]), 'biases':bias_variable([96])}
cl2_desc = {'weights':weight_variable([5,5,96,256]), 'biases':bias_variable([256])}
cl3_desc = {'weights':weight_variable([3,3,256,384]), 'biases':bias_variable([384])}
fc1_desc = {'weights':weight_variable([240000, 128]), 'biases':bias_variable([128])}
fc2_desc = {'weights':weight_variable([128,128]), 'biases':bias_variable([128])}
fc3_desc = {'weights':weight_variable([128,2]), 'biases':bias_variable([2])}
cl1 = conv2d(data,cl1_desc['weights'] + cl1_desc['biases'])
cl1 = tf.nn.relu(cl1)
pl1 = max_pool_nxn(cl1,3,[1,2,2,1])
lrm1 = tf.nn.local_response_normalization(pl1)
cl2 = conv2d(lrm1, cl2_desc['weights'] + cl2_desc['biases'])
cl2 = tf.nn.relu(cl2)
pl2 = max_pool_nxn(cl2,3,[1,2,2,1])
lrm2 = tf.nn.local_response_normalization(pl2)
cl3 = conv2d(lrm2, cl3_desc['weights'] + cl3_desc['biases'])
cl3 = tf.nn.relu(cl3)
pl3 = max_pool_nxn(cl3,3,[1,2,2,1])
fl = tf.contrib.layers.flatten(cl3)
fc1 = tf.add(tf.matmul(fl, fc1_desc['weights']), fc1_desc['biases'])
drp1 = tf.nn.dropout(fc1,0.5)
fc2 = tf.add(tf.matmul(drp1, fc2_desc['weights']), fc2_desc['biases'])
drp2 = tf.nn.dropout(fc2,0.5)
fc3 = tf.add(tf.matmul(drp2, fc3_desc['weights']), fc3_desc['biases'])
return fc3
需要注意的是，我已经完成了论文中描述的所有预处理步骤，但我的图像大小调整为100x100x3而不是277x277x3。
我定义逻辑回归对于女性为[0,1]，对于男性为[1,0]。
x = tf.placeholder('float',[None,100,100,3])
y = tf.placeholder('float',[None,2])
并且已经确定了以下的培训流程：
def train(x, hm_epochs, LR):
#prediction = create_model_v2(x)
prediction = create_model_v2(x)
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits = prediction, labels = y) )
optimizer = tf.train.AdamOptimizer(learning_rate=LR).minimize(cost)
batch_size = 50
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print("hello")
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
i = 0
while i < (len(x_train)):
start = i
end = i + batch_size
batch_x = x_train[start:end]
batch_y = y_train[start:end]
whatever, vigen = sess.run([optimizer, cost], feed_dict = {x:batch_x, y:batch_y})
epoch_loss += vigen
i+=batch_size
print('Epoch', epoch ,'loss:',epoch_loss/len(x_train))
if (epoch+1) % 2 == 0:
j = 0
acc = []
while j < len(x_test):
acc += [accuracy.eval(feed_dict = {x:x_test[j:j + 10], y:y_test[j:j+10]})]
j+= 10
print ('accuracy after', epoch + 1, 'epochs on test set: ', sum(acc)/len(acc))
j = 0
acc = []
while j < len(x_train):
acc += [accuracy.eval(feed_dict = {x:x_train[j:j + 10], y:y_train[j:j+10]})]
j+= 10
print ('accuracy after', epoch, ' epochs on train set:', sum(acc)/len(acc))
以上代码的一半只是为了每两个epoch输出测试和训练准确率。
无论如何，损失在第一个epoch开始时很高
('Epoch', 0, 'loss:', 148.87030902462453)
('Epoch', 1, 'loss:', 0.01549744715988636)
('accuracy after', 2, 'epochs on test set: ', 0.33052011888510396)
('accuracy after', 1, ' epochs on train set:', 0.49607501227222384)
('Epoch', 2, 'loss:', 0.015493246909976005)
我错过了什么？
并且像这样继续保持训练集的准确性为0.5。
编辑：函数权重变量、conv2d和max_pool_nn是
def bias_variable(shape):
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def avg_pool_nxn(x, n, strides):
return tf.nn.avg_pool(x, ksize=[1,n,n,1], strides = strides,padding = 'SAME')
def max_pool_nxn(x, n, strides):
return tf.nn.max_pool(x, ksize=[1,n,n,1], strides = strides, padding = 'SAME')
def conv2d(x, W,stride = [1,1,1,1]):
return tf.nn.conv2d(x, W, strides = stride, padding = 'SAME')
编辑2 - 问题已解决
问题与参数初始化有关。将权重初始化从正态分布更改为Xavier初始化后，准确度提高到了约86％。如果有人感兴趣，这是原始论文http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf，如果有人知道并愿意解释Xavier为什么适用于卷积神经网络和图像，请随时发布答案。
tf.nn.bias_add函数是否有区别。 - Vahagn Tumanyan