[英]How to plot Graph-neural-network model-graph when using tensorflow Model Subclass API with spektral layers?
[英]How is the Model Made in Tensorflow Using Graph
我試圖了解如何在 tensorflow 中制作以下 model。 我更習慣於看到使用 Tensorflow.kera.Sequential() 制作的多層感知器。 如果有人可以解釋如何創建 model 或如何了解有關其架構的更多信息 - 例如 model.summary() - 我將非常感激。 謝謝!
來源: https://github.com/github/CodeSearchNet/blob/master/src/models/model.py
class 的完整定義可以在上面的鏈接中找到。
def make_model(self, is_train: bool):
with self.__sess.graph.as_default():
random.seed(self.hyperparameters['seed'])
np.random.seed(self.hyperparameters['seed'])
tf.set_random_seed(self.hyperparameters['seed'])
self._make_model(is_train=is_train)
self._make_loss()
if is_train:
self._make_training_step()
self.__summary_writer = tf.summary.FileWriter(self.__tensorboard_dir, self.__sess.graph)
def _make_model(self, is_train: bool) -> None:
"""
Create the actual model.
Note: This has to create self.ops['code_representations'] and self.ops['query_representations'],
tensors of the same shape and rank 2.
"""
self.__placeholders['dropout_keep_rate'] = tf.placeholder(tf.float32,
shape=(),
name='dropout_keep_rate')
self.__placeholders['sample_loss_weights'] = \
tf.placeholder_with_default(input=np.ones(shape=[self.hyperparameters['batch_size']],
dtype=np.float32),
shape=[self.hyperparameters['batch_size']],
name='sample_loss_weights')
with tf.variable_scope("code_encoder"):
language_encoders = []
for (language, language_metadata) in sorted(self.__per_code_language_metadata.items(), key=lambda kv: kv[0]):
with tf.variable_scope(language):
self.__code_encoders[language] = self.__code_encoder_type(label="code",
hyperparameters=self.hyperparameters,
metadata=language_metadata)
language_encoders.append(self.__code_encoders[language].make_model(is_train=is_train))
self.ops['code_representations'] = tf.concat(language_encoders, axis=0)
with tf.variable_scope("query_encoder"):
self.__query_encoder = self.__query_encoder_type(label="query",
hyperparameters=self.hyperparameters,
metadata=self.__query_metadata)
self.ops['query_representations'] = self.__query_encoder.make_model(is_train=is_train)
code_representation_size = next(iter(self.__code_encoders.values())).output_representation_size
query_representation_size = self.__query_encoder.output_representation_size
assert code_representation_size == query_representation_size, \
f'Representations produced for code ({code_representation_size}) and query ({query_representation_size}) cannot differ!'
如果您想獲得 model 架構,您可以簡單地使用 tensorboard。 正如您在這一行中看到的,
self.__summary_writer = tf.summary.FileWriter(self.__tensorboard_dir, self.__sess.graph)
它將 session 圖形寫入self.__tensorboard_dir
位置中的文件。您只需啟動張量板並通過給定的 url 訪問它。
要啟動 tensorboard,請打開終端並使用此命令。
tensorboard --logdir="<file path (url of self.__tensorboard_dir)>"
這將啟動服務器並將 URL 顯示到 tensorboard。在 tensorboard 中,您有Graph選項卡,它將顯示整個架構。
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.