本文整理匯總了Python中cifar10_model.ResNetCifar10方法的典型用法代碼示例。如果您正苦於以下問題：Python cifar10_model.ResNetCifar10方法的具體用法？Python cifar10_model.ResNetCifar10怎麽用？Python cifar10_model.ResNetCifar10使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類cifar10_model的用法示例。
在下文中一共展示了cifar10_model.ResNetCifar10方法的3個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: _tower_fn
# 需要導入模塊: import cifar10_model [as 別名]
# 或者: from cifar10_model import ResNetCifar10 [as 別名]
def _tower_fn(is_training, weight_decay, feature, label, tower_losses,
tower_gradvars, tower_preds, is_cpu):
"""Build computation tower for each device (CPU or GPU).
Args:
is_training: true if is for training graph.
weight_decay: weight regularization strength, a float.
feature: a Tensor.
label: a Tensor.
tower_losses: a list to be appended with current tower's loss.
tower_gradvars: a list to be appended with current tower's gradients.
tower_preds: a list to be appended with current tower's predictions.
is_cpu: true if build tower on CPU.
"""
data_format = 'channels_last' if is_cpu else 'channels_first'
model = cifar10_model.ResNetCifar10(
FLAGS.num_layers, is_training=is_training, data_format=data_format)
logits = model.forward_pass(feature, input_data_format='channels_last')
tower_pred = {
'classes': tf.argmax(input=logits, axis=1),
'probabilities': tf.nn.softmax(logits)
}
tower_preds.append(tower_pred)
tower_loss = tf.losses.sparse_softmax_cross_entropy(
logits=logits, labels=label)
tower_loss = tf.reduce_mean(tower_loss)
tower_losses.append(tower_loss)
model_params = tf.trainable_variables()
tower_loss += weight_decay * tf.add_n(
[tf.nn.l2_loss(v) for v in model_params])
tower_losses.append(tower_loss)
tower_grad = tf.gradients(tower_loss, model_params)
tower_gradvars.append(zip(tower_grad, model_params)) 示例2: _tower_fn
# 需要導入模塊: import cifar10_model [as 別名]
# 或者: from cifar10_model import ResNetCifar10 [as 別名]
def _tower_fn(is_training, weight_decay, feature, label, tower_losses,
tower_gradvars, tower_preds, is_cpu):
"""Build computation tower for each device (CPU or GPU).
Args:
is_training: true if is for training graph.
weight_decay: weight regularization strength, a float.
feature: a Tensor.
label: a Tensor.
tower_losses: a list to be appended with current tower's loss.
tower_gradvars: a list to be appended with current tower's gradients.
tower_preds: a list to be appended with current tower's predictions.
is_cpu: true if build tower on CPU.
"""
data_format = 'channels_last' if is_cpu else 'channels_first'
model = cifar10_model.ResNetCifar10(
FLAGS.num_layers, is_training=is_training, data_format=data_format)
logits = model.forward_pass(feature, input_data_format='channels_last')
tower_pred = {
'classes': tf.argmax(input=logits, axis=1),
'probabilities': tf.nn.softmax(logits)
}
tower_preds.append(tower_pred)
tower_loss = tf.losses.sparse_softmax_cross_entropy(
logits=logits, labels=label)
tower_loss = tf.reduce_mean(tower_loss)
model_params = tf.trainable_variables()
tower_loss += weight_decay * tf.add_n(
[tf.nn.l2_loss(v) for v in model_params])
tower_losses.append(tower_loss)
tower_grad = tf.gradients(tower_loss, model_params)
tower_gradvars.append(zip(tower_grad, model_params)) 示例3: _tower_fn
# 需要導入模塊: import cifar10_model [as 別名]
# 或者: from cifar10_model import ResNetCifar10 [as 別名]
def _tower_fn(is_training, weight_decay, feature, label, data_format,
num_layers, batch_norm_decay, batch_norm_epsilon):
"""Build computation tower (Resnet).
Args:
is_training: true if is training graph.
weight_decay: weight regularization strength, a float.
feature: a Tensor.
label: a Tensor.
data_format: channels_last (NHWC) or channels_first (NCHW).
num_layers: number of layers, an int.
batch_norm_decay: decay for batch normalization, a float.
batch_norm_epsilon: epsilon for batch normalization, a float.
Returns:
A tuple with the loss for the tower, the gradients and parameters, and
predictions.
"""
model = cifar10_model.ResNetCifar10(
num_layers,
batch_norm_decay=batch_norm_decay,
batch_norm_epsilon=batch_norm_epsilon,
is_training=is_training,
data_format=data_format)
logits = model.forward_pass(feature, input_data_format='channels_last')
tower_pred = {
'classes': tf.argmax(input=logits, axis=1),
'probabilities': tf.nn.softmax(logits)
}
tower_loss = tf.losses.sparse_softmax_cross_entropy(
logits=logits, labels=label)
tower_loss = tf.reduce_mean(tower_loss)
model_params = tf.trainable_variables()
tower_loss += weight_decay * tf.add_n(
[tf.nn.l2_loss(v) for v in model_params])
tower_grad = tf.gradients(tower_loss, model_params)
return tower_loss, zip(tower_grad, model_params), tower_pred