我正在尝试设计一个卷积神经网络来检测一个小红色足球。我已经拍摄了不同配置的场景的aproxx 4000照片（添加了椅子，瓶子等......），没有球内部和场景的4000张照片也有不同的配置，但球在某处。 我使用的是32x32像素分辨率。在存在的情况下，可以在视觉上看到球。 这些是一些积极的示例图片（这里是颠倒的）：
我尝试了很多设计Convolutional NN的组合，但我找不到合适的。我将介绍我尝试过的两种架构（一种是“普通”，另一种是非常小）。我一直在设计小型和小型网络，因为它认为我会帮助我解决过度拟合的问题。 所以，我试过了： 普通网络设计
Input: 32x32x3
First Conv Layer:
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 3, 32], stddev=0.1), name=“w1”)
b_conv1 = tf.Variable(tf.constant(0.1, shape=[32]), name=“b1”) _
h_conv1 = tf.nn.relu(tf.nn.conv2d(x, W_conv1, strides=[1, 1, 1, 1], padding=‘SAME’)+ b_conv1, name=“conv1”)
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding=‘SAME’, name=“pool1”)
第二个Conv层：
W_conv2 = tf.Variable(tf.truncated_normal([5, 5, 32, 16], stddev=0.1), name=“w2”)
b_conv2 = tf.Variable(tf.constant(0.1, shape=[16]), name=“b2”)
h_conv2 = tf.nn.relu(tf.nn.conv2d(h_pool1, W_conv2, strides=[1, 1, 1, 1], padding=‘SAME’)+ b_conv2, name=“conv2”)
h_pool2 = tf.nn.max_pool(h_conv2, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding=‘SAME’, name=“pool2”)
完全连接的层：
W_fc1 = tf.Variable(tf.truncated_normal([8 * 8* 16, 16], stddev=0.1), name=“w3”)
b_fc1 = tf.Variable(tf.constant(0.1, shape=[16]), name=“b3”)
h_pool2_flat = tf.reshape(h_pool2, [-1, 8816], name=“flat3”)
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1, name=“conv3”)
降
keep_prob = tf.placeholder(tf.float32, name=“keep3”)
h_fc2_drop = tf.nn.dropout(h_fc1, keep_prob, name=“drop3”)
读出图层
W_fc3 = tf.Variable(tf.truncated_normal([16, 2], stddev=0.1), name=“w4”)
b_fc3 = tf.Variable(tf.constant(0.1, shape=([2]), name=“b4”) )
y_conv = tf.matmul(h_fc2_drop, W_fc3, name=“yconv”) + b_fc3
其他信息
cross_entropy = tf.reduce_mean(
_ tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=y_conv)+ 0.005 * tf.nn.l2_loss(W_conv1)+ 0.005 * tf.nn.l2_loss(W_fc1) + 0.005 * tf.nn.l2_loss(W_fc3)) _
train_step = tf.train.AdamOptimizer(1e-5,name=“trainingstep”).minimize(cross_entropy)
_#Percentage of correct _
prediction = tf.nn.softmax(y_conv, name=“y_prediction”) _
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y,1), name=“correct_pred”)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name=“acc”)
参数
keep_prob: 0.4
batch_size=500
training time in generations=55
结果
Training set final accuracy= 90.2%
Validation set final accuracy= 52.2%
图表链接： Link to accuracy graph
小型网络设计
Input: 32x32x3
第一个Conv层：
W_conv1 = tf.Variable(tf.truncated_normal([5, 5, 3, 16], stddev=0.1), name=“w1”)
_b_conv1 = tf.Variable(tf.constant(0.1, shape=[16]), name=“b1”) _
h_conv1 = tf.nn.relu(tf.nn.conv2d(x, W_conv1, strides=[1, 1, 1, 1], padding=‘SAME’)+ b_conv1, name=“conv1”)
h_pool1 = tf.nn.max_pool(h_conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding=‘SAME’, name=“pool1”)
完全连接的层：
W_fc1 = tf.Variable(tf.truncated_normal([16 * 16* 16, 8], stddev=0.1), name=“w3”)
b_fc1 = tf.Variable(tf.constant(0.1, shape=[8]), name=“b3”)
h_pool2_flat = tf.reshape(h_pool1, [-1, 161616], name=“flat3”)
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1, name=“conv3”)
降
keep_prob = tf.placeholder(tf.float32, name=“keep3”)
h_fc2_drop = tf.nn.dropout(h_fc1, keep_prob, name=“drop3”)
读出图层
W_fc3 = tf.Variable(tf.truncated_normal([8, 2], stddev=0.1), name=“w4”)
b_fc3 = tf.Variable(tf.constant(0.1, shape=([2]), name=“b4”) )
y_conv = tf.matmul(h_fc2_drop, W_fc3, name=“yconv”) + b_fc3
其他信息
cross_entropy = tf.reduce_mean(
_ tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv)+ 0.005 * tf.nn.l2_loss(W_conv1)+ 0.005 * tf.nn.l2_loss(W_fc1) + 0.005 * tf.nn.l2_loss(W_fc3)) _
train_step = tf.train.AdamOptimizer(1e-5,name=“trainingstep”).minimize(cross_entropy)
_#Percentage of correct _
prediction = tf.nn.softmax(y_conv, name=“y_prediction”) _
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y,1), name=“correct_pred”)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name=“acc”)
参数
keep_prob: 0.4
batch_size=500
training time in generations=55
结果
Training set final accuracy= 87%
Validation set final accuracy= 60.6%
所以，我所做的一切，都无法在验证测试中获得相当的准确性。 我确信这是缺少的东西，但我无法确定是什么。我正在使用辍学和l2，但它似乎过度适合
感谢您在CNN阅读，业余或高级，请留下反馈
答案 0 :(得分：0)
您的结果和准确度曲线对我来说似乎很正常，因此模型正在学习。几点建议：
