我有一个CNN用于带有图层的CIFAR-10数据集：
[IN] -> [CONV] -> [POOL] -> [CONV] -> [POOL] -> [FC] -> [DROPOUT] -> [LOGITS] -> [OUT]
\-> [EMBEDDINGS]
估算代码：
config = tf.contrib.learn.RunConfig(save_checkpoints_secs=30)
# Create the Estimator
classifier = tf.estimator.Estimator(model_fn=inference, config=config, model_dir=LOG_DIR)
train_images, train_labels, train_labels_onehot = Utils.load_training_data()
hooks = [
# logging hook
tf.train.LoggingTensorHook(tensors=tensors_to_log, every_n_iter=50),
]
train_input_fn = tf.estimator.inputs.numpy_input_fn(x={'x': train_images}, y=train_labels)
classifier.train(input_fn=train_input_fn, steps=FLAGS.steps, hooks=hooks)
推理功能代码：
def inference(self, features, labels, mode):
try:
images = tf.cast(features['x'], tf.float32)
# Input Layer
with tf.name_scope('Data'):
input_layer = tf.reshape(images, [-1, img_width, img_height, num_channels])
# Convolutional Layer 1
with tf.variable_scope('ConvLayer1'):
conv1 = tf.layers.conv2d(inputs=input_layer, filters=32, kernel_size=[5, 5],
padding="same", activation=tf.nn.relu)
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)
logging.info('Convolutional Layer 1 build successful..')
# Convolutional Layer 1
with tf.variable_scope('ConvLayer2'):
conv2 = tf.layers.conv2d(inputs=pool1, filters=64, kernel_size=[5, 5],
padding="same", activation=tf.nn.relu)
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
logging.info('Convolutional Layer 2 build successful..')
# Fully Connected Layer
with tf.variable_scope('FullyConnectedLayer'):
pool2_flat = tf.reshape(pool2, [-1, 8 * 8 * 64])
dense = tf.layers.dense(inputs=pool2_flat, units=1024, activation=tf.nn.relu)
dropout = tf.layers.dropout(inputs=dense, rate=0.4,
training=(mode == tf.estimator.ModeKeys.TRAIN))
logging.info('Fully Connected Layer build successful..')
tf.summary.histogram('dropout', dropout)
# Logits Layer
logits = tf.layers.dense(inputs=dropout, units=10)
tf.summary.histogram('logits', logits)
logging.info('Logits Layer build successful..')
predictions = {
# Generate predictions (for PREDICT and EVAL mode)
"classes": tf.argmax(input=logits, axis=1),
# Add `softmax_tensor` to the graph. It is used for PREDICT and by the
# `logging_hook`.
"probabilities": tf.nn.softmax(logits, name="softmax_tensor")
}
if mode == tf.estimator.ModeKeys.PREDICT:
return tf.estimator.EstimatorSpec(mode=mode, predictions=predictions,
evaluation_hooks=[])
# Calculate Loss (for both TRAIN and EVAL modes)
onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=10)
loss = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels,
logits=logits)
tf.summary.histogram('loss', loss)
logging.info('Losses build successful..')
# Configure the Training Op (for TRAIN mode)
if mode == tf.estimator.ModeKeys.TRAIN:
learning_rate = tf.train.exponential_decay(start_learning_rate,
tf.train.get_global_step(), 1000, 0.9, staircase=True)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
train_op = optimizer.minimize(loss=loss, global_step=tf.train.get_global_step())
return tf.estimator.EstimatorSpec(mode=mode, loss=loss, train_op=train_op,
scaffold=tf.train.Scaffold(
summary_op=tf.summary.merge_all(),
))
# Add evaluation metrics (for EVAL mode)
accuracy = tf.metrics.accuracy(labels=labels, predictions=predictions["classes"])
tf.summary.histogram('accuracy', accuracy)
logging.info('Accuracy metric build successful..')
return tf.estimator.EstimatorSpec(mode=mode, loss=loss,
train_op=train_op,
scaffold=tf.train.Scaffold(
summary_op=tf.summary.merge_all()
))
我正在尝试在tensorflow中使用Embeddings Visualization，在这里我想将dropout输出可视化为嵌入。
我发现使用嵌入的代码：
sess = tf.InteractiveSession()
# Input set for Embedded TensorBoard visualization
# Performed with cpu to conserve memory and processing power
with tf.device("/cpu:0"):
embedding = tf.Variable(self._data, trainable=False, name='embedding')
sess.run(embedding.initializer)
writer = tf.summary.FileWriter(LOG_DIR + '/projector', sess.graph)
config = projector.ProjectorConfig()
embed = config.embeddings.add()
embed.tensor_name = embedding.name
embed.metadata_path = os.path.join(LOG_DIR + '/projector/metadata.tsv')
embed.sprite.image_path = os.path.join(DATA_DIR + '/cifar_10k_sprite.png')
embed.sprite.single_image_dim.extend([img_width, img_height])
projector.visualize_embeddings(writer, config)
saver = tf.train.Saver([embedding])
saver.save(sess, os.path.join(LOG_DIR, 'projector/a_model.ckpt'))
它在我的情况下不起作用，因为我使用Estimator类而我无法访问会话。
我尝试的方式：
将numpy.array变量传递给Estimator的model_fn，我可以将值设置为该变量，然后将该变量传递给SessionRunHook，在那里我可以访问会话并将数据保存到文件中。没有用，因为传递给Estimator的所有论据都成了张量。所以这种方式不起作用，因为我已经有了辍学层张量。
创建全局变量，我可以在其中放置dropout图层的所有值。也没有用，因为我需要访问张量值。
据我所知，Estimator架构的主要问题是将丢失层输出信号输出到Estimator之外并以某种方式将其传递给SessionRunHook以将它们保存为嵌入。但我认为这不是最好的方式。
在Estimator中使用嵌入的正确方法是什么？
答案 0 :(得分：1)
这就是我这样做的方式（但它可能不是最有效的方式）：
SessinRunHook：
import tensorflow as tf
from classes.Utils import Utils
class EmbeddingSaverHook(tf.train.SessionRunHook):
def __init__(self, values, labels, captions):
self._saver = None
self._classes = Utils.get_classnames()
self._dense3 = None
self._labels = None
self._emb_values = values
self._emb_labels = labels
self._emb_captions = captions
def begin(self):
self._dense3 = tf.get_default_graph().get_tensor_by_name("dense3/BiasAdd:0")
self._labels = tf.get_default_graph().get_tensor_by_name("labels:0")
def before_run(self, run_context):
return tf.train.SessionRunArgs([self._dense3, self._labels])
def after_run(self, run_context, run_values):
self._emb_values.extend(run_values[0][0])
self._emb_labels.extend(run_values[0][1])
self._emb_captions.extend([self._classes[x] for x in run_values[0][1]])
def end(self, session):
pass
完整代码，您可以看到in my github repo