blocks|key|1407042|text|我遇到了同样的问题。改变后：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1407043|from+tensorflow+import+keras|offset|length|style|CODE|1407044|至：|1407045|import+keras|1407046|生活再一次值得活下去。|1407047|entityMap^0|0|0|S|0|0|0|C|0|0^^$0|@$1|2|3|4|5|6|7|P|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|Q|8|@$D|R|E|S|F|G]]|9|@]|A|$]]|$1|H|3|I|5|6|7|T|8|@]|9|@]|A|$]]|$1|J|3|K|5|6|7|U|8|@$D|V|E|W|F|G]]|9|@]|A|$]]|$1|L|3|M|5|6|7|X|8|@]|9|@]|A|$]]|$1|N|3|-4|5|6|7|Y|8|@]|9|@]|A|$]]]|O|$]]

I ran into the same issue. After changing:

<code>from tensorflow import keras</code>

to:

<code>import keras</code>

life is once again worth living.

blocks|key|2249729|text|我解决了这个问题：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2249730|在此之前：|2249731|from+keras.models+import+load_model
classifierLoad+=+load_model('model/modeltest.h5')|code-block|syntax|javascript|2249732|为我工作|2249733|import+tensorflow+as+tf+
classifierLoad+=+tf.keras.models.load_model('model/modeltest.h5')|2249734|entityMap^0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|O|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|P|8|@]|9|@]|A|$]]|$1|D|3|E|5|F|7|Q|8|@]|9|@]|A|$G|H]]|$1|I|3|J|5|6|7|R|8|@]|9|@]|A|$]]|$1|K|3|L|5|F|7|S|8|@]|9|@]|A|$G|H]]|$1|M|3|-4|5|6|7|T|8|@]|9|@]|A|$]]]|N|$]]

I fixed the problem:

Before:

<pre class="lang-py prettyprint-override"><code>from keras.models import load_model
classifierLoad = load_model('model/modeltest.h5')
</code></pre>

Works for me

<pre class="lang-py prettyprint-override"><code>import tensorflow as tf 
classifierLoad = tf.keras.models.load_model('model/modeltest.h5')
</code></pre>

blocks|key|517333|text|哇，我只是花了6个小时才弄明白.Dmitri在这里发布了一个解决方案：我在google上训练了一个keras模型。现在无法在我的系统上本地加载它。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|517334|我只是把它重新贴在这里因为它对我有用。|517335|这看起来像是keras中的某种序列化错误。如果你把你的load_model用下面的CustomObjectScope包裹起来.一切都应该工作..。|517336|import+keras
from+keras.models+import+load_model
from+keras.utils+import+CustomObjectScope
from+keras.initializers+import+glorot_uniform

with+CustomObjectScope({'GlorotUniform':+glorot_uniform()}):
++++++++model+=+load_model('imdb_mlp_model.h5')|code-block|syntax|javascript|517337|entityMap|0|LINK|mutability|MUTABLE|url|https://stackoverflow.com/questions/53051274/i-trained-a-keras-model-on-google-colab-now-not-able-to-load-it-locally-on-my-s^0|Z|12|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|U|8|@]|9|@$A|V|B|W|1|X]]|C|$]]|$1|D|3|E|5|6|7|Y|8|@]|9|@]|C|$]]|$1|F|3|G|5|6|7|Z|8|@]|9|@]|C|$]]|$1|H|3|I|5|J|7|10|8|@]|9|@]|C|$K|L]]|$1|M|3|-4|5|6|7|11|8|@]|9|@]|C|$]]]|N|$O|$5|P|Q|R|C|$S|T]]]]

Wow I, just spent 6 Hours of my life trying to figure this out.. Dmitri posted a solution to this here: <a href="https://stackoverflow.com/questions/53051274/i-trained-a-keras-model-on-google-colab-now-not-able-to-load-it-locally-on-my-s">I trained a keras model on google colab. Now not able to load it locally on my system.</a>

I'm just basically reposting it here because it worked for me.

This looks like some kind of a serialization bug in keras. 
If you wrap your load_model with the below CustomObjectScope thingy... all should work..

<pre><code>import keras
from keras.models import load_model
from keras.utils import CustomObjectScope
from keras.initializers import glorot_uniform

with CustomObjectScope({'GlorotUniform': glorot_uniform()}):
 model = load_model('imdb_mlp_model.h5')
</code></pre>

blocks|key|2249791|text|变换|type|unstyled|depth|inlineStyleRanges|offset|length|style|BOLD|entityRanges|data|2249792|from+keras.models+import+load_model|code-block|syntax|javascript|2249793|到|2249794|from+tensorflow.keras.models+import+load_model|2249795|解决了我的问题！|2249796|为了消除错误，直接从Keras或导入所有内容。将两者混合在同一个项目中可能会产生问题。|2249797|entityMap^0|0|2|0|0|0|1|0|0|0|8|0|G|2|0^^$0|@$1|2|3|4|5|6|7|U|8|@$9|V|A|W|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|X|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|Y|8|@$9|Z|A|10|B|C]]|D|@]|E|$]]|$1|M|3|N|5|H|7|11|8|@]|D|@]|E|$I|J]]|$1|O|3|P|5|6|7|12|8|@$9|13|A|14|B|C]]|D|@]|E|$]]|$1|Q|3|R|5|6|7|15|8|@$9|16|A|17|B|C]]|D|@]|E|$]]|$1|S|3|-4|5|6|7|18|8|@]|D|@]|E|$]]]|T|$]]

Changing

<pre class="lang-py prettyprint-override"><code>from keras.models import load_model
</code></pre>

to 

<pre class="lang-py prettyprint-override"><code>from tensorflow.keras.models import load_model
</code></pre>

solved my problem!

To eliminate errors, import all things directly from Keras or TensorFlow. Mixing both of them in same project may result in problems.

blocks|key|1407021|text|我也有同样的问题，就这样修好了。只是不要用模型来保存优化器！只需像下面这样更改保存行：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1407022|the_model.save(file_path,True/False,False)|code-block|syntax|javascript|1407023|第二个参数告诉Keras在文件是否存在时覆盖模型，第三个参数告诉它不要用模型保存优化器。|1407024|编辑：我今天在另一个系统上再次遇到了这个问题，这一次对我没有任何帮助。因此，我将模型conf保存为json，权重保存为h5，并使用它们在另一台机器中重新构建模型。你可以这样做。像这样存钱：|offset|length|style|BOLD|1407025|json+=+model.to_json()
#+Save+the+json+on+a+file
model.save_weights(weights_filepath,save_format="h5")|1407026|像这样重建模型：|1407027|#+load+the+json+file
#+here+i+use+json+as+loaded+content+of+json+file
model+=+keras.models.model_from_json(json)
model.load_weights(weights_file_path)|1407028|entityMap^0|0|0|0|0|2|0|0|0|0^^$0|@$1|2|3|4|5|6|7|W|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|X|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|Y|8|@]|9|@]|A|$]]|$1|I|3|J|5|6|7|Z|8|@$K|10|L|11|M|N]]|9|@]|A|$]]|$1|O|3|P|5|D|7|12|8|@]|9|@]|A|$E|F]]|$1|Q|3|R|5|6|7|13|8|@]|9|@]|A|$]]|$1|S|3|T|5|D|7|14|8|@]|9|@]|A|$E|F]]|$1|U|3|-4|5|6|7|15|8|@]|9|@]|A|$]]]|V|$]]

I had a same problem and was fixed this way. just don't save the optimizer with the model!
just change the save line like this:

<pre><code>the_model.save(file_path,True/False,False)
</code></pre>

Second parameter tells Keras to overwrite the model if the file existed or not and the 3rd one tells it not to save the optimizer with the model.

<hr>

Edit:
I ran over the problem again on another system today and this did not helped me this time. so i saved the model conf as json and weights as h5 and used them to rebuild the model in another machine. you can do it like this.
save like this:

<pre><code>json = model.to_json()
# Save the json on a file
model.save_weights(weights_filepath,save_format="h5")
</code></pre>

rebuild the model like this:

<pre><code># load the json file
# here i use json as loaded content of json file
model = keras.models.model_from_json(json)
model.load_weights(weights_file_path)
</code></pre>

blocks|key|517345|text|某物帮了我的忙，但在任何一个答案中都没有：|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|517346|custom_objects={'GlorotUniform':+glorot_uniform()}|style|CODE|517347|entityMap|0|LINK|mutability|MUTABLE|url|https://github.com/tensorflow/tfjs/issues/798#issuecomment-452442569^0|0|2|0|0|0|1E|0^^$0|@$1|2|3|4|5|6|7|P|8|@]|9|@$A|Q|B|R|1|S]]|C|$]]|$1|D|3|E|5|6|7|T|8|@$A|U|B|V|F|G]]|9|@]|C|$]]|$1|H|3|-4|5|6|7|W|8|@]|9|@]|C|$]]]|I|$J|$5|K|L|M|C|$N|O]]]]

<a href="https://github.com/tensorflow/tfjs/issues/798#issuecomment-452442569" rel="nofollow noreferrer">Something</a> that helped me which wasn't in any of the answers:

<code>custom_objects={'GlorotUniform': glorot_uniform()}</code>

blocks|key|2249871|text|无论是在kaggle还是colabs|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2249872|tf.keras.models.load_model("model_path")|code-block|syntax|javascript|2249873|效果很好|2249874|entityMap^0|0|0|0^^$0|@$1|2|3|4|5|6|7|K|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|L|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|M|8|@]|9|@]|A|$]]|$1|I|3|-4|5|6|7|N|8|@]|9|@]|A|$]]]|J|$]]

In either kaggle or colabs

<pre><code>tf.keras.models.load_model("model_path")
</code></pre>

works well

blocks|key|2249850|text|from+tensorflow.keras.initializers+import+glorot_uniform

loaded_model+=+tf.keras.models.load_model("pruned.h5",custom_objects={'GlorotUniform':+glorot_uniform()})|type|code-block|depth|inlineStyleRanges|entityRanges|data|syntax|javascript|2249851|当我进口tensorflow角时，这对我有用。|unstyled|2249852|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$B|C]]|$1|D|3|E|5|F|7|J|8|@]|9|@]|A|$]]|$1|G|3|-4|5|F|7|K|8|@]|9|@]|A|$]]]|H|$]]

<pre><code>from tensorflow.keras.initializers import glorot_uniform

loaded_model = tf.keras.models.load_model("pruned.h5",custom_objects={'GlorotUniform': glorot_uniform()})

</code></pre>

this worked for me when importing tensorflow keras

blocks|key|517415|text|如果您正在加载体系结构和权重，同时加载模型更改的结构：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|517416|models.model_from_json(json)|code-block|syntax|javascript|517417|致：|517418|tf.keras.models.model_from_json(json)|517419|问题就解决了|517420|entityMap^0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|O|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|P|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|Q|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|R|8|@]|9|@]|A|$E|F]]|$1|K|3|L|5|6|7|S|8|@]|9|@]|A|$]]|$1|M|3|-4|5|6|7|T|8|@]|9|@]|A|$]]]|N|$]]

if you are loading the architecture and weights separtly, while loading archtiecture of the model change :

<pre><code>models.model_from_json(json)
</code></pre>

to : 

<pre><code>tf.keras.models.model_from_json(json)
</code></pre>

and the problem is solved

blocks|key|2249776|text|使用tensorflow+1.11.0构建的模型(使用tensorflow.python.keras.models.save_model)和使用tensoflow+1.11.0加载的模型(使用tensorflow.python.keras.models.load_model)也存在同样的问题。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2249777|我通过将所有东西升级到tensorflow+1.13.1来解决这个问题，在用新版本重新构建模型之后，我可以在没有这个错误的情况下加载它。|2249778|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|F|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|G|8|@]|9|@]|A|$]]|$1|D|3|-4|5|6|7|H|8|@]|9|@]|A|$]]]|E|$]]

I had the same problem with a model built with tensorflow 1.11.0 (using tensorflow.python.keras.models.save_model) and loaded with tensoflow 1.11.0 (using tensorflow.python.keras.models.load_model).

I solved it by upgrading everything to tensorflow 1.13.1, after building the model again with the new version, I could load it without this error.

blocks|key|517440|text|对于@Derk在其中一个注释中提到的json文件问题，可以编写以下内容：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|517441|model_from_json(model_path,+custom_objects+=+{'GlorotUniform':+glorot_uniform()})|code-block|syntax|javascript|517442|在您的导入行中，请记住：|517443|from+tensorflow.keras.initializers+import+glorot_uniform|517444|而不是from+keras.initializers+import+glorot_uniform。|offset|length|style|CODE|517445|当我尝试阅读tf2.2中仅用tf1.9保存的模型时，我就明白了这一点。|517446|entityMap^0|0|0|0|0|3|19|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]]|$1|G|3|H|5|6|7|W|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|X|8|@]|9|@]|A|$E|F]]|$1|K|3|L|5|6|7|Y|8|@$M|Z|N|10|O|P]]|9|@]|A|$]]|$1|Q|3|R|5|6|7|11|8|@]|9|@]|A|$]]|$1|S|3|-4|5|6|7|12|8|@]|9|@]|A|$]]]|T|$]]

For the json file problem mentioned by @Derk in one of the comment, you can write the following:
<pre><code>model_from_json(model_path, custom_objects = {'GlorotUniform': glorot_uniform()})
</code></pre>
and in your import line, remember to write:
<pre><code>from tensorflow.keras.initializers import glorot_uniform
</code></pre>
instead of <code>from keras.initializers import glorot_uniform</code>.
It worked out for me when I try to read a model saved in tf2.2 in the environment with only tf1.9.

I trained my CNN (VGG) through google colab and generated .h5 file. Now problem is, I can predict my output successfully through google colab but when i download that .h5 trained model file and try to predict output on my laptop, I am getting error when loading the model.

Here is the code:

<pre><code>import tensorflow as tf
from tensorflow import keras
import h5py

# Initialization

loaded_model = keras.models.load_model('./train_personCount_model.h5')
</code></pre>

And the error:

<pre><code>ValueError: Unknown initializer: GlorotUniform
</code></pre>

Unknown initializer: GlorotUniform when loading Keras model

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

我通过google训练我的CNN (VGG)并生成.h5文件。现在的问题是，我可以通过google成功地预测我的输出，但是当我下载经过.h5训练的模型文件并尝试在我的笔记本电脑上预测输出时，我在加载模型时会出现错误。以下是代码：import tensorflow as tffrom tensorflow import kerasimport h5py# Initializationloaded_m

问未知初始化程序:加载Keras模型时的GlorotUniform
EN

回答 11

Stack Overflow用户

Stack Overflow用户

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

问未知初始化程序:加载Keras模型时的GlorotUniformEN

回答 11

Stack Overflow用户

Stack Overflow用户

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

问未知初始化程序:加载Keras模型时的GlorotUniform
EN