Keras - 保存mnist数据集的图像嵌入
我为MNIST db编写了以下简单的MLP网络。
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras import callbacks
batch_size = 100
num_classes = 10
epochs = 20
tb = callbacks.TensorBoard(log_dir='/Users/shlomi.shwartz/tensorflow/notebooks/logs/minist', histogram_freq=10, batch_size=32,
write_graph=True, write_grads=True, write_images=True,
embeddings_freq=10, embeddings_layer_names=None,
embeddings_metadata=None)
early_stop = callbacks.EarlyStopping(monitor='val_loss', min_delta=0,
patience=3, verbose=1, mode='auto')
# the data, shuffled and split between train and test sets
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Dense(200, activation='relu', input_shape=(784,)))
model.add(Dropout(0.2))
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(60, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(30, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
history = model.fit(x_train, y_train,
callbacks=[tb,early_stop],
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(x_test, y_test))
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])
模型运行正常，我可以看到TensorBoard上的标量信息。但是，当我更改 embeddings_freq = 10 以尝试可视化图像时（如seen here），我收到以下错误：
Traceback (most recent call last):
File "/Users/shlomi.shwartz/IdeaProjects/TF/src/minist.py", line 65, in <module>
validation_data=(x_test, y_test))
File "/Users/shlomi.shwartz/tensorflow/lib/python3.6/site-packages/keras/models.py", line 870, in fit
initial_epoch=initial_epoch)
File "/Users/shlomi.shwartz/tensorflow/lib/python3.6/site-packages/keras/engine/training.py", line 1507, in fit
initial_epoch=initial_epoch)
File "/Users/shlomi.shwartz/tensorflow/lib/python3.6/site-packages/keras/engine/training.py", line 1117, in _fit_loop
callbacks.set_model(callback_model)
File "/Users/shlomi.shwartz/tensorflow/lib/python3.6/site-packages/keras/callbacks.py", line 52, in set_model
callback.set_model(model)
File "/Users/shlomi.shwartz/tensorflow/lib/python3.6/site-packages/keras/callbacks.py", line 719, in set_model
self.saver = tf.train.Saver(list(embeddings.values()))
File "/usr/local/Cellar/python3/3.6.1/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1139, in __init__
self.build()
File "/usr/local/Cellar/python3/3.6.1/Frameworks/Python.framework/Versions/3.6/lib/python3.6/site-packages/tensorflow/python/training/saver.py", line 1161, in build
raise ValueError("No variables to save")
ValueError: No variables to save
问：我错过了什么？这是在Keras这样做的正确方法吗？
更新：我知道有一些先决条件才能使用嵌入投影，但是我没有在Keras找到一个很好的教程，任何帮助都将不胜感激。
3 个答案:
答案 0 :(得分：17)
什么叫做＆＃34;嵌入＆＃34;从广义上讲，callbacks.TensorBoard中的任何图层权重都是Embedding。根据{{3}}：
embeddings_layer_names：要关注的图层名称列表。如果为None或空列表，则将监视所有嵌入层。
默认情况下 ，它会监控Embedding图层，但您真的不需要embeddings_layer_names图层来使用此可视化工具。
在您提供的MLP示例中，缺少的是kernel参数。您必须弄清楚您要进行可视化的图层。假设您想要显示所有Dense图层的权重（或Keras中的embeddings_layer_names），您可以像这样指定model = Sequential()
model.add(Dense(200, activation='relu', input_shape=(784,)))
model.add(Dropout(0.2))
model.add(Dense(100, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(60, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(30, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(10, activation='softmax'))
embedding_layer_names = set(layer.name
for layer in model.layers
if layer.name.startswith('dense_'))
tb = callbacks.TensorBoard(log_dir='temp', histogram_freq=10, batch_size=32,
write_graph=True, write_grads=True, write_images=True,
embeddings_freq=10, embeddings_metadata=None,
embeddings_layer_names=embedding_layer_names)
model.compile(...)
model.fit(...)
：
embeddings_layer_names然后，您可以在TensorBoard中看到类似的内容： Keras documentation
如果您想了解TensorBoard发生了什么，可以看到
。
编辑：
所以这是一个可视化图层输出的脏解决方案。由于原始的TensorBoard回调不支持这一点，因此实现新的回调似乎是不可避免的。
由于此处会占用大量页面空间来重新编写整个TensorBoard回调，因此我只会扩展原始TensorBoard，并写出不同的部分（这已经相当冗长了）。但是为了避免重复计算和模型保存，重写import tensorflow as tf
from tensorflow.contrib.tensorboard.plugins import projector
from keras import backend as K
from keras.models import Model
from keras.callbacks import TensorBoard
class TensorResponseBoard(TensorBoard):
def __init__(self, val_size, img_path, img_size, **kwargs):
super(TensorResponseBoard, self).__init__(**kwargs)
self.val_size = val_size
self.img_path = img_path
self.img_size = img_size
def set_model(self, model):
super(TensorResponseBoard, self).set_model(model)
if self.embeddings_freq and self.embeddings_layer_names:
embeddings = {}
for layer_name in self.embeddings_layer_names:
# initialize tensors which will later be used in `on_epoch_end()` to
# store the response values by feeding the val data through the model
layer = self.model.get_layer(layer_name)
output_dim = layer.output.shape[-1]
response_tensor = tf.Variable(tf.zeros([self.val_size, output_dim]),
name=layer_name + '_response')
embeddings[layer_name] = response_tensor
self.embeddings = embeddings
self.saver = tf.train.Saver(list(self.embeddings.values()))
response_outputs = [self.model.get_layer(layer_name).output
for layer_name in self.embeddings_layer_names]
self.response_model = Model(self.model.inputs, response_outputs)
config = projector.ProjectorConfig()
embeddings_metadata = {layer_name: self.embeddings_metadata
for layer_name in embeddings.keys()}
for layer_name, response_tensor in self.embeddings.items():
embedding = config.embeddings.add()
embedding.tensor_name = response_tensor.name
# for coloring points by labels
embedding.metadata_path = embeddings_metadata[layer_name]
# for attaching images to the points
embedding.sprite.image_path = self.img_path
embedding.sprite.single_image_dim.extend(self.img_size)
projector.visualize_embeddings(self.writer, config)
def on_epoch_end(self, epoch, logs=None):
super(TensorResponseBoard, self).on_epoch_end(epoch, logs)
if self.embeddings_freq and self.embeddings_ckpt_path:
if epoch % self.embeddings_freq == 0:
# feeding the validation data through the model
val_data = self.validation_data[0]
response_values = self.response_model.predict(val_data)
if len(self.embeddings_layer_names) == 1:
response_values = [response_values]
# record the response at each layers we're monitoring
response_tensors = []
for layer_name in self.embeddings_layer_names:
response_tensors.append(self.embeddings[layer_name])
K.batch_set_value(list(zip(response_tensors, response_values)))
# finally, save all tensors holding the layer responses
self.saver.save(self.sess, self.embeddings_ckpt_path, epoch)
回调将是一种更好，更清洁的方式。
tb = TensorResponseBoard(log_dir=log_dir, histogram_freq=10, batch_size=10,
write_graph=True, write_grads=True, write_images=True,
embeddings_freq=10,
embeddings_layer_names=['dense_1'],
embeddings_metadata='metadata.tsv',
val_size=len(x_test), img_path='images.jpg', img_size=[28, 28])
使用它：
log_dir在启动TensorBoard之前，您需要将标签和图像保存到from PIL import Image
img_array = x_test.reshape(100, 100, 28, 28)
img_array_flat = np.concatenate([np.concatenate([x for x in row], axis=1) for row in img_array])
img = Image.fromarray(np.uint8(255 * (1. - img_array_flat)))
img.save(os.path.join(log_dir, 'images.jpg'))
np.savetxt(os.path.join(log_dir, 'metadata.tsv'), np.where(y_test)[1], fmt='%d')
以进行可视化：
$mainbgimage: image url;
.page-title {
padding: 0;
min-height: 200px;
background-image: $mainbgimage;
}
结果如下：
答案 1 :(得分：1)
在Keras中至少需要一个嵌入层。关于统计数据是一个很好的解释。它不直接用于Keras，但概念大致相同。 What is an embedding layer in a neural network
答案 2 :(得分：1)
所以，我得出结论，你真正想要的是（你的帖子中并不完全清楚）是以类似于this Tensorboard demo的方式可视化模型的预测。
首先，复制这些东西是非平凡的even in Tensorflow，更不用说Keras了。所述演示非常简短并传递对metadata & sprite images之类的内容的引用，这些内容是获得此类可视化所必需的。
底线：尽管非常重要，但确实可以用Keras做到这一点。你不需要Keras回调;您所需要的只是您的模型预测，必要的元数据和精灵图像，以及一些纯TensorFlow代码。所以，
第1步 - 获取测试集的模型预测：
emb = model.predict(x_test) # 'emb' for embedding
步骤2a - 使用测试集的真实标签构建元数据文件：
import numpy as np
LOG_DIR = '/home/herc/SO/tmp' # FULL PATH HERE!!!
metadata_file = os.path.join(LOG_DIR, 'metadata.tsv')
with open(metadata_file, 'w') as f:
for i in range(len(y_test)):
c = np.nonzero(y_test[i])[0][0]
f.write('{}\n'.format(c))
第二步 - 获取TensorFlow人员here提供的精灵图片mnist_10k_sprite.png，并将其放入LOG_DIR
第3步 - 写一些Tensorflow代码：
import tensorflow as tf
from tensorflow.contrib.tensorboard.plugins import projector
embedding_var = tf.Variable(emb, name='final_layer_embedding')
sess = tf.Session()
sess.run(embedding_var.initializer)
summary_writer = tf.summary.FileWriter(LOG_DIR)
config = projector.ProjectorConfig()
embedding = config.embeddings.add()
embedding.tensor_name = embedding_var.name
# Specify the metadata file:
embedding.metadata_path = os.path.join(LOG_DIR, 'metadata.tsv')
# Specify the sprite image:
embedding.sprite.image_path = os.path.join(LOG_DIR, 'mnist_10k_sprite.png')
embedding.sprite.single_image_dim.extend([28, 28]) # image size = 28x28
projector.visualize_embeddings(summary_writer, config)
saver = tf.train.Saver([embedding_var])
saver.save(sess, os.path.join(LOG_DIR, 'model2.ckpt'), 1)
然后，在LOG_DIR中运行Tensorboard，并按标签选择颜色，这是您得到的：
为了获得其他图层的预测，修改它很简单，尽管在这种情况下Keras Functional API可能是更好的选择。
- 我写了这段代码，但我无法理解我的错误
- 我无法从一个代码实例的列表中删除 None 值，但我可以在另一个实例中。为什么它适用于一个细分市场而不适用于另一个细分市场？
- 是否有可能使 loadstring 不可能等于打印？卢阿
- java中的random.expovariate()
- Appscript 通过会议在 Google 日历中发送电子邮件和创建活动
- 为什么我的 Onclick 箭头功能在 React 中不起作用？
- 在此代码中是否有使用“this”的替代方法？
- 在 SQL Server 和 PostgreSQL 上查询，我如何从第一个表获得第二个表的可视化
- 每千个数字得到
- 更新了城市边界 KML 文件的来源？