Keras - 保存mnist数据集的图像嵌入

Question

我为MNISTdb 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(如此处所示)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,以便使用嵌入投影,但我没有在Keras找到一个很好的教程,任何帮助将不胜感激.

Answer 1

callbacks.TensorBoard从广义上讲,所谓的"嵌入" 是指任何层重.据Keras文件说:

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.

因此,默认情况下,它会监视Embedding图层,但您实际上并不需要Embedding图层来使用此可视化工具.

在您提供的MLP示例中,缺少的是embeddings_layer_names参数.你必须弄清楚你要想象的层.假设您想要显示kernel所有Dense图层的权重(或者,在Keras中),您可以embeddings_layer_names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(...)

然后,您可以在TensorBoard中看到类似的内容:

如果你想弄清楚发生了什么,你可以在Keras源中看到相关的行embeddings_layer_names.

编辑:

所以这是一个用于可视化图层输出的脏解决方案.由于最初的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.

由于这里需要占用大量的页面空间来重写整个TensorBoard回调,我只需要扩展原始版本TensorBoard,然后写出不同的部分(已经非常冗长).但是为了避免重复计算和模型保存,重写TensorBoard回调将是一种更好,更清洁的方式.

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)

要使用它:

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])

在启动TensorBoard之前,您需要保存标签和图像以log_dir进行可视化:

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')

这是结果: