blocks|key|200566|text|Keras尚未在当前模块中包括resnet、resnet_v2和resnext，它们将从Keras2.2.5中添加，正如前面提到的这里。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|200567|对于解决方法，可以使用keras_applications模块直接导入所有ResNet、ResNetV2和ResNeXt模型，如下所示|200568|from+keras_applications.resnet+import+ResNet50|code-block|syntax|javascript|200569|或者如果您只想使用ResNet50|200570|from+keras.applications.resnet50+import+ResNet50|200571|或者，您也可以像前面提到的这里那样从源构建。|200572|entityMap|0|LINK|mutability|MUTABLE|url|https://github.com/keras-team/keras/issues/12289|1|https://keras.io/#installation^0|1T|2|0|0|0|0|0|0|D|2|1|0^^$0|@$1|2|3|4|5|6|7|10|8|@]|9|@$A|11|B|12|1|13]]|C|$]]|$1|D|3|E|5|6|7|14|8|@]|9|@]|C|$]]|$1|F|3|G|5|H|7|15|8|@]|9|@]|C|$I|J]]|$1|K|3|L|5|6|7|16|8|@]|9|@]|C|$]]|$1|M|3|N|5|H|7|17|8|@]|9|@]|C|$I|J]]|$1|O|3|P|5|6|7|18|8|@]|9|@$A|19|B|1A|1|1B]]|C|$]]|$1|Q|3|-4|5|6|7|1C|8|@]|9|@]|C|$]]]|R|$S|$5|T|U|V|C|$W|X]]|Y|$5|T|U|V|C|$W|Z]]]]

Keras team hasn't included resnet, resnet_v2 and resnext in the current module, they will be added from Keras 2.2.5, as mentioned <a href="https://github.com/keras-team/keras/issues/12289" rel="noreferrer">here</a>.

For a workaround, you can use keras_applications module directly to import all ResNet, ResNetV2 and ResNeXt models, as given below

<pre><code>from keras_applications.resnet import ResNet50
</code></pre>

Or if you just want to use ResNet50

<pre><code>from keras.applications.resnet50 import ResNet50
</code></pre>

Alternatively, you can always build from source as mentioned <a href="https://keras.io/#installation" rel="noreferrer">here</a>.

blocks|key|2388848|text|试着使用|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2388849|from+tensorflow.keras.applications.resnet50+import+ResNet50|code-block|syntax|javascript|2388850|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

try to use
<pre><code>from tensorflow.keras.applications.resnet50 import ResNet50
</code></pre>

blocks|key|2388774|text|找到了在Keras2.2.4+ResNeXt中使用这里的解决办法。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|2388775|ResNeXt50()函数还需要4个参数:后端、层、模型和实用程序。|blockquote|2388776|import+keras
from+keras_applications.resnext+import+ResNeXt50

model+=+ResNeXt50(weights='imagenet',
++++++++++++++++++backend=keras.backend,
++++++++++++++++++layers=keras.layers,
++++++++++++++++++models=keras.models,
++++++++++++++++++utils=keras.utils)|code-block|syntax|javascript|2388777|entityMap|0|LINK|mutability|MUTABLE|url|http://donghao.org/2019/02/22/using-resnext-in-keras-2-2-4/^0|P|2|0|0|0|0^^$0|@$1|2|3|4|5|6|7|T|8|@]|9|@$A|U|B|V|1|W]]|C|$]]|$1|D|3|E|5|F|7|X|8|@]|9|@]|C|$]]|$1|G|3|H|5|I|7|Y|8|@]|9|@]|C|$J|K]]|$1|L|3|-4|5|6|7|Z|8|@]|9|@]|C|$]]]|M|$N|$5|O|P|Q|C|$R|S]]]]

Found a workaround to use ResNeXt in Keras 2.2.4 <a href="http://donghao.org/2019/02/22/using-resnext-in-keras-2-2-4/" rel="noreferrer">here</a>.

<blockquote>
 ResNeXt50() function needs 4 more arguments: backend, layers, models and utils.
</blockquote>

<pre><code>import keras
from keras_applications.resnext import ResNeXt50

model = ResNeXt50(weights='imagenet',
 backend=keras.backend,
 layers=keras.layers,
 models=keras.models,
 utils=keras.utils)
</code></pre>

blocks|key|200496|text|在Keras中，有多种口味的ResNet，您必须指定您想要的ResNet版本，例如您希望加载ResNet50。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|200497|使用|200498|from+keras.applications+import+ResNet50|offset|length|style|CODE|200499|编辑2这是在应用程序上使用dir()命令时得到的列表|BOLD|200500|['DenseNet121',+'DenseNet169',+'DenseNet201',+'InceptionResNetV2',+'InceptionV3',+'MobileNet',+'MobileNetV2',+'NASNetLarge',+'NASNetMobile',+'ResNet50',+'VGG16',+'VGG19',+'Xception',+'__builtins__',+'__cached__',+'__doc__',+'__file__',+'__loader__',+'__name__',+'__package__',+'__path__',+'__spec__',+'absolute_import',+'backend',+'densenet',+'division',+'inception_resnet_v2',+'inception_v3',+'keras_applications',+'keras_modules_injection',+'layers',+'mobilenet',+'mobilenet_v2',+'models',+'nasnet',+'print_function',+'resnet50',+'utils',+'vgg16',+'vgg19',+'xception']，这里可见的模型可以是这样的，这里有一些像ResNet101这样的模型，让我看看我能不能想出一种方法来解决这个问题。|200501|编辑证明了这也是可行的|200502|​|200503|📷|atomic|200504|200505|要查看Resnet模型的所有可用版本，请访问https://keras.io/applications/#resnet|200506|entityMap|0|IMAGE|mutability|IMMUTABLE|imageUrl|https://developer.qcloudimg.com/http-save/yehe-900000/205985f8fce6db73c4411893add424eb.png|imageAlt|1|LINK|MUTABLE|url|https://keras.io/applications/#resnet^0|0|0|0|13|0|0|3|D|5|0|0|FU|0|0|2|0|0|0|1|0|0|0|M|11|1|0^^$0|@$1|2|3|4|5|6|7|1C|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|1D|8|@]|9|@]|A|$]]|$1|D|3|E|5|6|7|1E|8|@$F|1F|G|1G|H|I]]|9|@]|A|$]]|$1|J|3|K|5|6|7|1H|8|@$F|1I|G|1J|H|L]|$F|1K|G|1L|H|I]]|9|@]|A|$]]|$1|M|3|N|5|6|7|1M|8|@$F|1N|G|1O|H|I]]|9|@]|A|$]]|$1|O|3|P|5|6|7|1P|8|@$F|1Q|G|1R|H|L]]|9|@]|A|$]]|$1|Q|3|R|5|6|7|1S|8|@]|9|@]|A|$]]|$1|S|3|T|5|U|7|1T|8|@]|9|@$F|1U|G|1V|1|1W]]|A|$]]|$1|V|3|R|5|6|7|1X|8|@]|9|@]|A|$]]|$1|W|3|X|5|6|7|1Y|8|@]|9|@$F|1Z|G|20|1|21]]|A|$]]|$1|Y|3|-4|5|6|7|22|8|@]|9|@]|A|$]]]|Z|$10|$5|11|12|13|A|$14|15|16|-4]]|17|$5|18|12|19|A|$1A|1B]]]]

In Keras there are multiple flavours of ResNet, you will have to specify the version of ResNet that you want e.g. You wish to load the ResNet50.

Use 

<code>from keras.applications import ResNet50</code>

Edit 2 This is the list you get when you use <code>dir()</code> command on applications 

<code>['DenseNet121', 'DenseNet169', 'DenseNet201', 'InceptionResNetV2', 'InceptionV3', 'MobileNet', 'MobileNetV2', 'NASNetLarge', 'NASNetMobile', 'ResNet50', 'VGG16', 'VGG19', 'Xception', '__builtins__', '__cached__', '__doc__', '__file__', '__loader__', '__name__', '__package__', '__path__', '__spec__', 'absolute_import', 'backend', 'densenet', 'division', 'inception_resnet_v2', 'inception_v3', 'keras_applications', 'keras_modules_injection', 'layers', 'mobilenet', 'mobilenet_v2', 'models', 'nasnet', 'print_function', 'resnet50', 'utils', 'vgg16', 'vgg19', 'xception']</code>, the models visible here can be laoded like this, There are some models like ResNet101 missing here, let me see if I can come up with a way to fix this.

Edit Proof that this works too

<a href="https://i.stack.imgur.com/EnZZf.png" rel="nofollow noreferrer"><img src="https://i.stack.imgur.com/EnZZf.png" alt="enter image description here"></a>

To see all the available versions of the Resnet models, visit <a href="https://keras.io/applications/#resnet" rel="nofollow noreferrer">https://keras.io/applications/#resnet</a>

blocks|key|1005877|text|检查版本：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1005878|pip+list+%7C+grep+Keras|code-block|syntax|javascript|1005879|如果已经安装，请卸载并升级：|1005880|pip+uninstall+Keras
pip+install+Keras==2.3.1

pip+uninstall+Keras-Applications
pip+install+Keras-Applications==1.0.8

pip+uninstall+Keras-Preprocessing
pip+install+Keras-Preprocessing==1.1.0|1005881|entityMap^0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|N|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|O|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|P|8|@]|9|@]|A|$E|F]]|$1|K|3|-4|5|6|7|Q|8|@]|9|@]|A|$]]]|L|$]]

Check the versions:
<pre><code>pip list | grep Keras
</code></pre>
If it's already installed, uninstall and upgrade:
<pre><code>pip uninstall Keras
pip install Keras==2.3.1

pip uninstall Keras-Applications
pip install Keras-Applications==1.0.8

pip uninstall Keras-Preprocessing
pip install Keras-Preprocessing==1.1.0
</code></pre>

blocks|key|200669|text|有一个名为“keras”的python包，它包含ResNet50、ResNet101、ResNet152和更多的ResNet变体。(https://pypi.org/project/keras-resnet/)|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|200670|安装也相当容易。只是打字|200671|pip+install+keras-resnet|code-block|syntax|javascript|200672|它将安装这个模块，然后使用它如下：|200673|from+keras_resnet.models+import+ResNet50,+ResNet101,+ResNet152

backbone+=+ResNet50(inputs=image_input,+include_top=False,+freeze_bn=True)
C2,+C3,+C4,+C5+=+backbone.outputs+#+this+will+give+you+intermediate+
#+outputs+of+four+blocks+of+resnet+if+you+want+to+merge+low+and+high+level+features|200674|我正在使用这个模块的骨干，并且为我工作的很好！|200675|entityMap|0|LINK|mutability|MUTABLE|url|https://pypi.org/project/keras-resnet/^0|1U|12|0|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|Y|8|@]|9|@$A|Z|B|10|1|11]]|C|$]]|$1|D|3|E|5|6|7|12|8|@]|9|@]|C|$]]|$1|F|3|G|5|H|7|13|8|@]|9|@]|C|$I|J]]|$1|K|3|L|5|6|7|14|8|@]|9|@]|C|$]]|$1|M|3|N|5|H|7|15|8|@]|9|@]|C|$I|J]]|$1|O|3|P|5|6|7|16|8|@]|9|@]|C|$]]|$1|Q|3|-4|5|6|7|17|8|@]|9|@]|C|$]]]|R|$S|$5|T|U|V|C|$W|X]]]]

There is a python package named 'keras-resnet' which has ResNet50, ResNet101, ResNet152 and many more variants of ResNet. (<a href="https://pypi.org/project/keras-resnet/" rel="nofollow noreferrer">https://pypi.org/project/keras-resnet/</a>)
Installation is also quite easy. Just type
<pre><code>pip install keras-resnet
</code></pre>
It will install this module and then use it like:
<pre><code>from keras_resnet.models import ResNet50, ResNet101, ResNet152

backbone = ResNet50(inputs=image_input, include_top=False, freeze_bn=True)
C2, C3, C4, C5 = backbone.outputs # this will give you intermediate 
# outputs of four blocks of resnet if you want to merge low and high level features
</code></pre>
I am using backbones from this module and is working fine for me!

blocks|key|2388854|text|from+keras.applications.resnet
import+ResNet101++++

tf.keras.backend.clear_session
model=VGG19()
model.summary()


tf.keras.utils.plot_model(model,show_shapes=True)
visualkeras.layered_view(model,legend=True)|type|code-block|depth|inlineStyleRanges|entityRanges|data|syntax|javascript|2388855|unstyled|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|G|8|@]|9|@]|A|$B|C]]|$1|D|3|-4|5|E|7|H|8|@]|9|@]|A|$]]]|F|$]]

<pre><code>from keras.applications.resnet
import ResNet101 

tf.keras.backend.clear_session
model=VGG19()
model.summary()


tf.keras.utils.plot_model(model,show_shapes=True)
visualkeras.layered_view(model,legend=True)
</code></pre>

blocks|key|200703|text|跑前|type|unstyled|depth|inlineStyleRanges|entityRanges|data|200704|tensorflow.keras.applications.resnet50+import+ResNet50+|code-block|syntax|javascript|200705|你得跑|200706|from+tensorflow+import+keras|200707|entityMap^0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|N|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|O|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|P|8|@]|9|@]|A|$E|F]]|$1|K|3|-4|5|6|7|Q|8|@]|9|@]|A|$]]]|L|$]]

Before running
<pre><code>tensorflow.keras.applications.resnet50 import ResNet50 
</code></pre>
you need to run
<pre><code>from tensorflow import keras
</code></pre>

I'm unable to import this module

<pre><code>import keras.applications.resnet
</code></pre>

<blockquote>
 ModuleNotFoundError 
 in ()
 ----> 1 import keras.applications.resnet
</blockquote>

<code>ModuleNotFoundError: No module named 'keras.applications.resnet'</code>

<hr>

keras resnet <a href="https://keras.io/applications/#resnet" rel="noreferrer">link</a>

I am not able to import resnet from keras.applications module

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

我无法导入这个模块import keras.applications.resnetModuleNotFoundError在() ->1进口keras.applications.resnet中ModuleNotFoundError: No module named 'keras.applications.resnet'keras 

问我无法从keras.applications模块导入resnet
EN

回答 8

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

问我无法从keras.applications模块导入resnetEN

回答 8

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

问我无法从keras.applications模块导入resnet
EN