def softmax_classifier(tensor_in,
labels,
weights,
biases,
class_weight=None,
name=None):
"""Returns prediction and loss for softmax classifier.
Args:
tensor_in: Input tensor, [batch_size, feature_size], features.
labels: Tensor, [batch_size, n_classes], labels of the output classes.
weights: Tensor, [batch_size, feature_size], linear transformation
matrix.
biases: Tensor, [batch_size], biases.
class_weight: Tensor, optional, [n_classes], weight for each class.
If not given, all classes are supposed to have weight one.
name: Operation name.
Returns:
Prediction and loss tensors.
"""
with ops.name_scope(name, "softmax_classifier", [tensor_in, labels]):
logits = nn.xw_plus_b(tensor_in, weights, biases)
if class_weight is not None:
logits = math_ops.mul(logits, class_weight)
return nn.softmax(logits), loss_ops.softmax_cross_entropy(logits, labels)
def softmax_classifier(tensor_in,
labels,
weights,
biases,
class_weight=None,
name=None):
"""Returns prediction and loss for softmax classifier.
Args:
tensor_in: Input tensor, [batch_size, feature_size], features.
labels: Tensor, [batch_size, n_classes], labels of the output classes.
weights: Tensor, [batch_size, feature_size], linear transformation
matrix.
biases: Tensor, [batch_size], biases.
class_weight: Tensor, optional, [n_classes], weight for each class.
If not given, all classes are supposed to have weight one.
name: Operation name.
Returns:
Prediction and loss tensors.
"""
with ops.op_scope([tensor_in, labels], name, "softmax_classifier"):
logits = nn.xw_plus_b(tensor_in, weights, biases)
if class_weight is not None:
logits = math_ops.mul(logits, class_weight)
return nn.softmax(logits), loss_ops.softmax_cross_entropy(
logits, labels)
def softmax_classifier(tensor_in,
labels,
weights,
biases,
class_weight=None,
name=None):
"""Returns prediction and loss for softmax classifier.
This function returns "probabilities" and a cross entropy loss. To obtain
predictions, use `tf.argmax` on the returned probabilities.
This function requires labels to be passed in one-hot encoding.
Args:
tensor_in: Input tensor, [batch_size, feature_size], features.
labels: Tensor, [batch_size, n_classes], one-hot labels of the output
classes.
weights: Tensor, [batch_size, feature_size], linear transformation
matrix.
biases: Tensor, [batch_size], biases.
class_weight: Tensor, optional, [n_classes], weight for each class.
If not given, all classes are supposed to have weight one.
name: Operation name.
Returns:
`tuple` of softmax predictions and loss `Tensor`s.
"""
with ops.name_scope(name, 'softmax_classifier', [tensor_in, labels]):
logits = nn.xw_plus_b(tensor_in, weights, biases)
if class_weight is not None:
logits = math_ops.multiply(logits, class_weight)
return nn.softmax(logits), loss_ops.softmax_cross_entropy(
logits, labels)
def softmax_classifier(tensor_in,
labels,
weights,
biases,
class_weight=None,
name=None):
"""Returns prediction and loss for softmax classifier.
This function returns "probabilities" and a cross entropy loss. To obtain
predictions, use `tf.argmax` on the returned probabilities.
This function requires labels to be passed in one-hot encoding.
Args:
tensor_in: Input tensor, [batch_size, feature_size], features.
labels: Tensor, [batch_size, n_classes], one-hot labels of the output
classes.
weights: Tensor, [batch_size, feature_size], linear transformation
matrix.
biases: Tensor, [batch_size], biases.
class_weight: Tensor, optional, [n_classes], weight for each class.
If not given, all classes are supposed to have weight one.
name: Operation name.
Returns:
`tuple` of softmax predictions and loss `Tensor`s.
"""
with ops.name_scope(name, "softmax_classifier", [tensor_in, labels]):
logits = nn.xw_plus_b(tensor_in, weights, biases)
if class_weight is not None:
logits = math_ops.mul(logits, class_weight)
return nn.softmax(logits), loss_ops.softmax_cross_entropy(logits, labels)
def __init__(self):
x = tf.placeholder(tf.float32, shape=[None, IMG_SIZE * IMG_SIZE * 3])
y_ = tf.placeholder(tf.float32, shape=[None, 2])
x_image = tf.reshape(x, [-1, IMG_SIZE, IMG_SIZE, 3]) # 128
W_conv1 = tf.get_variable("W_conv1", shape=[3, 3, 3, 6], initializer=xavier())
b_conv1 = tf.get_variable('b_conv1', [1, 1, 1, 6])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1) # 64
W_conv2 = tf.get_variable("W_conv2", shape=[3, 3, 6, 6], initializer=xavier())
b_conv2 = tf.get_variable('b_conv2', [1, 1, 1, 6])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2) # 32
W_conv3 = tf.get_variable("W_conv3", shape=[3, 3, 6, 12], initializer=xavier())
b_conv3 = tf.get_variable('b_conv3', [1, 1, 1, 12])
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3) # 16
W_conv4 = tf.get_variable("W_conv4", shape=[3, 3, 12, 24], initializer=xavier())
b_conv4 = tf.get_variable('b_conv4', [1, 1, 1, 24])
h_conv4 = tf.nn.relu(conv2d(h_pool3, W_conv4) + b_conv4)
h_pool4 = max_pool_2x2(h_conv4) # 8
h_pool4_flat = tf.reshape(h_pool4, [-1, 8 * 8 * 24])
W_fc1 = tf.get_variable("W_fc1", shape=[8 * 8 * 24, 1024], initializer=xavier())
b_fc1 = tf.get_variable('b_fc1', [1024], initializer=init_ops.zeros_initializer)
h_fc1 = tf.nn.relu(tf.matmul(h_pool4_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fcO = tf.get_variable("W_fcO", shape=[1024, 2], initializer=xavier())
b_fcO = tf.get_variable('b_fcO', [2], initializer=init_ops.zeros_initializer)
logits = tf.matmul(h_fc1_drop, W_fcO) + b_fcO
y_conv = tf.nn.softmax(logits)
cross_entropy = loss_ops.softmax_cross_entropy(logits, y_)
train_step = tf.train.AdagradOptimizer(0.01).minimize(cross_entropy)
self.predictions = predictions = tf.argmax(y_conv, 1)
self.pp = y_conv
correct_prediction = tf.equal(predictions, tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
self.x = x
self.y_ = y_
self.keep_prob = keep_prob
self.trainStep = train_step
self.accuracy = accuracy
def __init__(self):
x = tf.placeholder(tf.float32, shape=[None, IMG_SIZE * IMG_SIZE * 3])
y_ = tf.placeholder(tf.float32, shape=[None, 2])
x_image = tf.reshape(x, [-1, IMG_SIZE, IMG_SIZE, 3]) # 128
W_conv1 = tf.get_variable("W_conv1", shape=[3, 3, 3, 6], initializer=xavier())
b_conv1 = tf.get_variable('b_conv1', [1, 1, 1, 6])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1) # 64
W_conv2 = tf.get_variable("W_conv2", shape=[3, 3, 6, 6], initializer=xavier())
b_conv2 = tf.get_variable('b_conv2', [1, 1, 1, 6])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2) # 32
W_conv3 = tf.get_variable("W_conv3", shape=[3, 3, 6, 12], initializer=xavier())
b_conv3 = tf.get_variable('b_conv3', [1, 1, 1, 12])
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3) # 16
W_conv4 = tf.get_variable("W_conv4", shape=[3, 3, 12, 24], initializer=xavier())
b_conv4 = tf.get_variable('b_conv4', [1, 1, 1, 24])
h_conv4 = tf.nn.relu(conv2d(h_pool3, W_conv4) + b_conv4)
h_pool4 = max_pool_2x2(h_conv4) # 8
h_pool4_flat = tf.reshape(h_pool4, [-1, 8 * 8 * 24])
W_fc1 = tf.get_variable("W_fc1", shape=[8 * 8 * 24, 1024], initializer=xavier())
b_fc1 = tf.get_variable('b_fc1', [1024], initializer=init_ops.zeros_initializer)
h_fc1 = tf.nn.relu(tf.matmul(h_pool4_flat, W_fc1) + b_fc1)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fcO = tf.get_variable("W_fcO", shape=[1024, 2], initializer=xavier())
b_fcO = tf.get_variable('b_fcO', [2], initializer=init_ops.zeros_initializer)
logits = tf.matmul(h_fc1_drop, W_fcO) + b_fcO
y_conv = tf.nn.softmax(logits)
cross_entropy = loss_ops.softmax_cross_entropy(logits, y_)
train_step = tf.train.AdagradOptimizer(0.01).minimize(cross_entropy)
self.predictions = predictions = tf.argmax(y_conv, 1)
correct_prediction = tf.equal(predictions, tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
self.x = x
self.y_ = y_
self.keep_prob = keep_prob
self.trainStep = train_step
self.accuracy = accuracy
def __init__(self):
self.x = tf.placeholder(tf.float32,
shape=[None, IMG_SIZE * IMG_SIZE * 3])
self.y_ = tf.placeholder(tf.float32, shape=[None, 3])
x_image = tf.reshape(self.x,
[-1, IMG_SIZE, IMG_SIZE, 3]) # 128 * 128 * 3
W_conv1 = tf.get_variable("W_conv1",
shape=[3, 3, 3, 6],
initializer=xavier()) #定義遮罩 (高度、寬度、通道數，遮罩數量)
b_conv1 = tf.get_variable('b_conv1', [1, 1, 1, 6])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1) # 64
W_conv2 = tf.get_variable("W_conv2",
shape=[3, 3, 6, 6],
initializer=xavier())
b_conv2 = tf.get_variable('b_conv2', [1, 1, 1, 6])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2) # 32
W_conv3 = tf.get_variable("W_conv3",
shape=[3, 3, 6, 12],
initializer=xavier())
b_conv3 = tf.get_variable('b_conv3', [1, 1, 1, 12])
h_conv3 = tf.nn.relu(conv2d(h_pool2, W_conv3) + b_conv3)
h_pool3 = max_pool_2x2(h_conv3) # 16
W_conv4 = tf.get_variable("W_conv4",
shape=[3, 3, 12, 24],
initializer=xavier())
b_conv4 = tf.get_variable('b_conv4', [1, 1, 1, 24])
h_conv4 = tf.nn.relu(conv2d(h_pool3, W_conv4) + b_conv4)
h_pool4 = max_pool_2x2(h_conv4) # 8
h_pool4_flat = tf.reshape(h_pool4, [-1, 8 * 8 * 24])
W_fc1 = tf.get_variable("W_fc1",
shape=[8 * 8 * 24, 1024],
initializer=xavier())
b_fc1 = tf.get_variable('b_fc1', [1024],
initializer=init_ops.zeros_initializer)
h_fc1 = tf.nn.relu(tf.matmul(h_pool4_flat, W_fc1) + b_fc1)
self.keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, self.keep_prob)
W_fcO = tf.get_variable("W_fcO", shape=[1024, 3], initializer=xavier())
b_fcO = tf.get_variable('b_fcO', [3],
initializer=init_ops.zeros_initializer)
logits = tf.matmul(h_fc1_drop, W_fcO) + b_fcO
y_conv = tf.nn.softmax(logits)
self.cross_entropy = loss_ops.softmax_cross_entropy(logits, self.y_)
self.train_step = tf.train.AdagradOptimizer(0.01).minimize(
self.cross_entropy)
self.predictions = predictions = tf.argmax(y_conv, 1)
correct_prediction = tf.equal(predictions, tf.argmax(self.y_, 1))
self.accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# for tensorboard
tf.summary.scalar('loss', self.cross_entropy)
tf.summary.scalar('acc', self.accuracy)
self.summary_op = tf.summary.merge_all()
