-2
fully_connected中提到的张量流函数没有参数为最后一层添加dropout。有没有办法?如何为TF完全连接的完全连接图层添加dropout?
fully_connected中提到的张量流函数没有参数为最后一层添加dropout。有没有办法?如何为TF完全连接的完全连接图层添加dropout?
我这样做:
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
请看教程Deep MNIST for Experts和mnist_deep.py
# Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
# is down to 7x7x64 feature maps -- maps this to 1024 features.
with tf.name_scope('fc1'):
W_fc1 = weight_variable([7 * 7 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Dropout - controls the complexity of the model, prevents co-adaptation of
# features.
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Map the 1024 features to 10 classes, one for each digit
with tf.name_scope('fc2'):
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
源代码,或者,如果你想使用tf.contrib.layers.fully_connected
你可以做这样的事情:
h_pool2_flatten = tf.contrib.layers.flatten.flatten(h_pool2)
h_fc1 = tf.contrib.layers.fully_connected(h_pool2_flatten, 1024, scope='fc1')
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.contrib.layers.dropout(h_fc1, keep_prob)
y_conv = tf.contrib.layers.fully_connected(h_fc1_drop, 10, activation_fn=None, scope='fc2')
你能否详细解释你的问题,你想做什么?通常最后一层是预测某个类或值的那个层,你想在那里使用drop_out来实现什么。 –
@VivekKumar人已经正确回答了。为什么仍然是-2? –