blocks|key|24043|text|配置用于培训的模型。文档|type|blockquote|depth|inlineStyleRanges|entityRanges|offset|length|data|24044|就我个人而言，我不认为它是编译，因为它所做的与编译无关，用计算机科学的术语来说，同时考虑机器学习和编译是非常令人困惑/难以抗拒的。|unstyled|24045|它只是一种进行配置的方法：|24046|它只设置传递它的参数:优化器、丢失函数、度量、急切的执行。您可以多次运行它，它只会覆盖以前设置的设置。|24047|我对TensorFlow开发人员的建议是，在短期内将其重命名为configure，也许在将来(不太重要)，为每个配置参数设置一个setter+(或使用工厂/构建器模式)。|style|CODE|24048|这是它的代码：|24049|++++base_layer.keras_api_gauge.get_cell('compile').set(True)
++++with+self.distribute_strategy.scope():
++++++if+'experimental_steps_per_execution'+in+kwargs:
++++++++logging.warn('The+argument+`steps_per_execution`+is+no+longer+'
+++++++++++++++++++++'experimental.+Pass+`steps_per_execution`+instead+of+'
+++++++++++++++++++++'`experimental_steps_per_execution`.')
++++++++if+not+steps_per_execution:
++++++++++steps_per_execution+=+kwargs.pop('experimental_steps_per_execution')

++++++self._validate_compile(optimizer,+metrics,+**kwargs)
++++++self._run_eagerly+=+run_eagerly

++++++self.optimizer+=+self._get_optimizer(optimizer)
++++++self.compiled_loss+=+compile_utils.LossesContainer(
++++++++++loss,+loss_weights,+output_names=self.output_names)
++++++self.compiled_metrics+=+compile_utils.MetricsContainer(
++++++++++metrics,+weighted_metrics,+output_names=self.output_names)

++++++self._configure_steps_per_execution(steps_per_execution+or+1)

++++++#+Initializes+attrs+that+are+reset+each+time+`compile`+is+called.
++++++self._reset_compile_cache()
++++++self._is_compiled+=+True

++++++self.loss+=+loss+or+{}++#+Backwards+compat.|code-block|syntax|javascript|24050|entityMap|0|LINK|mutability|MUTABLE|url|https://keras.io/api/models/model_training_apis/#compile-method^0|A|2|0|0|0|0|0|V|9|0|0|0^^$0|@$1|2|3|4|5|6|7|13|8|@]|9|@$A|14|B|15|1|16]]|C|$]]|$1|D|3|E|5|F|7|17|8|@]|9|@]|C|$]]|$1|G|3|H|5|F|7|18|8|@]|9|@]|C|$]]|$1|I|3|J|5|F|7|19|8|@]|9|@]|C|$]]|$1|K|3|L|5|F|7|1A|8|@$A|1B|B|1C|M|N]]|9|@]|C|$]]|$1|O|3|P|5|F|7|1D|8|@]|9|@]|C|$]]|$1|Q|3|R|5|S|7|1E|8|@]|9|@]|C|$T|U]]|$1|V|3|-4|5|F|7|1F|8|@]|9|@]|C|$]]]|W|$X|$5|Y|Z|10|C|$11|12]]]]

<blockquote>
Configures the model for training. <a href="https://keras.io/api/models/model_training_apis/#compile-method" rel="nofollow noreferrer">documentation</a>
</blockquote>
Personally, I wouldn't call it compile, because what it does has got nothing to do with compilation, in computer science terms, and this is very confusing/ overwhelming to think about machine learning and compilation at the same time.
<h2>Its just a method which does configuration:</h2>
It just sets the arguments you pass it: optimizer, loss function, metrics, eager execution. You can run it multiple times, it will just overwrite the settings you set previously.
My suggestion to developers of TensorFlow would be to rename it to <code>configure</code> in the short term, and perhaps in the future (not that important), move to having 1 setter (or use the factory/ builder pattern) for each configuration argument.
<h2>Heres the code for it:</h2>
<pre class="lang-py prettyprint-override"><code> base_layer.keras_api_gauge.get_cell('compile').set(True)
 with self.distribute_strategy.scope():
 if 'experimental_steps_per_execution' in kwargs:
 logging.warn('The argument `steps_per_execution` is no longer '
 'experimental. Pass `steps_per_execution` instead of '
 '`experimental_steps_per_execution`.')
 if not steps_per_execution:
 steps_per_execution = kwargs.pop('experimental_steps_per_execution')

 self._validate_compile(optimizer, metrics, **kwargs)
 self._run_eagerly = run_eagerly

 self.optimizer = self._get_optimizer(optimizer)
 self.compiled_loss = compile_utils.LossesContainer(
 loss, loss_weights, output_names=self.output_names)
 self.compiled_metrics = compile_utils.MetricsContainer(
 metrics, weighted_metrics, output_names=self.output_names)

 self._configure_steps_per_execution(steps_per_execution or 1)

 # Initializes attrs that are reset each time `compile` is called.
 self._reset_compile_cache()
 self._is_compiled = True

 self.loss = loss or {} # Backwards compat.
</code></pre>

blocks|key|243484|text|model.compile与培训您的模型有关。实际上，你的权重需要优化，这个函数可以优化它们。在某种程度上提高了你的准确性。这只是一个叫做‘优化器’的输入参数。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|243485|model.compile(
optimizer='rmsprop',+loss='sparse_categorical_crossentropy',+metrics='acc'
)|code-block|syntax|javascript|243486|这些是主要的投入。此外，您还可以在下面的链接中找到TensorFlow文档中的更多细节：|243487|docs/python/tf/keras/Model#编译|offset|length|243488|entityMap|0|LINK|mutability|MUTABLE|url|https://www.tensorflow.org/api_docs/python/tf/keras/Model#compile^0|0|0|0|0|T|0|0^^$0|@$1|2|3|4|5|6|7|U|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|V|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|W|8|@]|9|@]|A|$]]|$1|I|3|J|5|6|7|X|8|@]|9|@$K|Y|L|Z|1|10]]|A|$]]|$1|M|3|-4|5|6|7|11|8|@]|9|@]|A|$]]]|N|$O|$5|P|Q|R|A|$S|T]]]]

model.compile is related to training your model. Actually, your weights need to optimize and this function can optimize them. In a way that your accuracy make increases. This was just one of the input parameters called 'optimizer'.
<pre><code>model.compile(
optimizer='rmsprop', loss='sparse_categorical_crossentropy', metrics='acc'
)
</code></pre>
These are the main inputs. Also you can find more details in TensorFlow documentation in link below:
<a href="https://www.tensorflow.org/api_docs/python/tf/keras/Model#compile" rel="nofollow noreferrer">https://www.tensorflow.org/api_docs/python/tf/keras/Model#compile</a>

According to <a href="https://keras.io/api/models/model/" rel="noreferrer">keras.io</a>:
<blockquote>
Once the model is created, you can config the model with losses and
metrics with model.compile().
</blockquote>
But this explanation does not provide enough information about what exactly compiling model does.

What does model.compile() do in keras tensorflow?

翻译质量差，导致语言生硬或混乱。

没有提供实际的解决方法或示例。

解答不清晰，无法理解或解决问题。

页面排版不美观，阅读体验差。

文章

问答

视频

学习中心

腾讯云实验室

直播

竞赛

腾讯云代码分析专区

腾讯iOA零信任安全管理系统专区

腾讯云架构师技术同盟交流圈

腾讯云数据库专区

腾讯云顾问专区

腾讯云原生专区

腾讯混元专区

腾讯云TCE专区

腾讯云Lighthouse专区

腾讯云HAI专区

腾讯云Edgeone专区

腾讯云存储专区

腾讯云智能专区

腾讯轻联专区 

腾讯云开发专区

TAPD专区

腾讯轻量云游戏服专区

腾讯云最具价值专家

腾讯云架构师技术同盟

腾讯云创作之星

腾讯云开发者先锋

腾讯云代码助手

云原生构建

TAPD 敏捷项目管理

Cloud Studio

SDK中心

API中心

命令行工具

涵盖代码开发、场景应用、自动测试全流程，助你从零构建专属AI助手

一站式MCP教程库，解锁AI应用新玩法

根据一旦创建了模型，您就可以用model.compile().配置模型中的损失和度量。但是这个解释并没有提供足够的信息来说明编译模型到底是做什么的。

问model.compile()在keras中做什么？
EN

Stack Overflow用户

社区

活动

圈层

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问model.compile()在keras中做什么？EN