blocks|key|1295125|text|平坦方法不以输入大小作为参数。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1295126|model+=+Sequential()
I+=+Input((None,+None,+1))
c+=+Conv2D(filters=1,+kernel_size=(1,+1))(I)
f+=+Flatten()
o+=+Dense(10,+activation="softmax")(I)
m+=+Model(I,+o)
m.compile(loss="categorical_crossentropy",+optimizer=SGD(),+metrics=["accuracy"])|code-block|syntax|javascript|1295127|这应该能解决你的问题。|1295128|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|$]]

Flatten method doesn't take input size as argument.

<pre><code>model = Sequential()
I = Input((None, None, 1))
c = Conv2D(filters=1, kernel_size=(1, 1))(I)
f = Flatten()
o = Dense(10, activation="softmax")(I)
m = Model(I, o)
m.compile(loss="categorical_crossentropy", optimizer=SGD(), metrics=["accuracy"])
</code></pre>

This should solve your problem.

blocks|key|1925641|text|我认为问题是由于你的变量input_sizes。这里说，如果您使用的是完全连接的层，则不能更改input_sizes。请参阅：如何训练图像，当它们有不同的大小？|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1925642|entityMap|0|LINK|mutability|MUTABLE|url|https://stackoverflow.com/questions/41907598/how-to-train-images-when-they-have-different-size^0|1R|H|0|0^^$0|@$1|2|3|4|5|6|7|L|8|@]|9|@$A|M|B|N|1|O]]|C|$]]|$1|D|3|-4|5|6|7|P|8|@]|9|@]|C|$]]]|E|$F|$5|G|H|I|C|$J|K]]]]

I think the problem is due to your variable input_sizes. It says here that you can't vary input_sizes if you're using a fully connected layer. See: <a href="https://stackoverflow.com/questions/41907598/how-to-train-images-when-they-have-different-size">How to train images, when they have different size ?</a>

blocks|key|481452|text|稠密需要固定大小的输入/输出，因为它的权重变量的数量必须固定。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|481453|在你的案例中有两种解决方案。|481454|使用GAP(全球平均池)而不是扁平。GAP的输出大小是前一层的通道数。所以，它的大小在你的情况下是固定的。|ordered-list-item|481455|使用不具有稠密层的全卷积网。在这种情况下，网络的输出是二维的，而不是一维的。所以y的大小应该是这个大小。|481456|下面是为艾伦M的请求添加。|481457|下面是一个代码示例：|481458|#+The+original+number+of+Conv+filters+are+one.
#+But+I+set+it+16+to+depict+how+GAP+works.
#+And+B/H/W+means+BatchSize/Height/Width.

#1.+using+GAP
I+=+Input((None,+None,+1))+#+output+shape=(B,+H(None),+W(None),+1)
c+=+Conv2D(filters=16,+kernel_size=(1,+1))(I)++#+output+shape=(B,+H,+W,+16)
f+=+GlobalAveragePooling2D()(c)+#+output+shape=(B,+16)+<-+space+data(H/W)+are+aggregated+by+average
o+=+Dense(10,+activation="softmax")(f)+#+output+shape+=+(B,+10)
m+=+Model(I,+o)

#2.+all+conv
I+=+Input((None,+None,+1))+#+output+shape=(B,+H,+W,+1)
c+=+Conv2D(filters=16,+kernel_size=(1,+1))(I)+#+output+shape=(B,+H,+W,+16)
o+=+Conv2D(filters=10,+kernel_size=(1,+1),+activation="softmax")(c)
++++#+output+shape=(B,+H,+W,+10)
m+=+Model(I,+o)
#+The+output+size+of+all+conv+is+H+*+W+*+10,+where+10+is+the+number+of+classes.
#+so+the+shape+of+y+should+be+(B,+H,+W,+1)+or+(B,+H,+W)+or+(B,+H,+W,+10).
#+That+is+pixel-wise+classification+or+semantic+segmentation.|code-block|syntax|javascript|481459|entityMap^0|0|0|0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|T|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|U|8|@]|9|@]|A|$]]|$1|D|3|E|5|F|7|V|8|@]|9|@]|A|$]]|$1|G|3|H|5|F|7|W|8|@]|9|@]|A|$]]|$1|I|3|J|5|6|7|X|8|@]|9|@]|A|$]]|$1|K|3|L|5|6|7|Y|8|@]|9|@]|A|$]]|$1|M|3|N|5|O|7|Z|8|@]|9|@]|A|$P|Q]]|$1|R|3|-4|5|6|7|10|8|@]|9|@]|A|$]]]|S|$]]

Dense needs fix-sized inputs/outputs because the number of weights variables of it must be fixed.
There are two solutions in your case.
<ol>
<li>To use GAP(Global Average Pooling) instead of Flatten. GAP's outputs size is the number of channels of the previous layer. so, its size is fixed in your case.</li>
<li>To employ the all convolution net that doesn't have dense layer. In this case, the output of the net is two dimensional, not one. So the size of y should be that size.</li>
</ol>
below was added for Allen M's request. 
Here is a code sample:
<pre><code># The original number of Conv filters are one.
# But I set it 16 to depict how GAP works.
# And B/H/W means BatchSize/Height/Width.

#1. using GAP
I = Input((None, None, 1)) # output shape=(B, H(None), W(None), 1)
c = Conv2D(filters=16, kernel_size=(1, 1))(I) # output shape=(B, H, W, 16)
f = GlobalAveragePooling2D()(c) # output shape=(B, 16) &lt;- space data(H/W) are aggregated by average
o = Dense(10, activation=&quot;softmax&quot;)(f) # output shape = (B, 10)
m = Model(I, o)

#2. all conv
I = Input((None, None, 1)) # output shape=(B, H, W, 1)
c = Conv2D(filters=16, kernel_size=(1, 1))(I) # output shape=(B, H, W, 16)
o = Conv2D(filters=10, kernel_size=(1, 1), activation=&quot;softmax&quot;)(c)
 # output shape=(B, H, W, 10)
m = Model(I, o)
# The output size of all conv is H * W * 10, where 10 is the number of classes.
# so the shape of y should be (B, H, W, 1) or (B, H, W) or (B, H, W, 10).
# That is pixel-wise classification or semantic segmentation.
</code></pre>

I am using python 3 with anaconda, and keras with over tensorflow, My goal is to create a network with a Conv layer of variable input size 

I found <a href="https://github.com/keras-team/keras/issues/4449" rel="nofollow noreferrer">here</a> to use this code 

<pre><code>i = Input((None, None, 1))
o = Conv2D(1, 3, 3)(i)
model = Model(i, o)
model.compile('sgd', 'mse')
</code></pre>

I have used it to create my own model with this code (I need a flatten layer) 

<pre><code>model = Sequential()
I = Input((None, None, 1))
c = Conv2D(filters=1, kernel_size=(1, 1))(I)
f = Flatten()(c)
o = Dense(10, activation="softmax")(f)
m = Model(I, o)
m.compile(loss=categorical_crossentropy, optimizer=SGD(), metrics=["accuracy"])
</code></pre>

And I keep getting this error 

<blockquote>
 ValueError: The shape of the input to "Flatten" is not fully defined
 (got (None, None, 1). Make sure to pass a complete "input_shape" or
 "batch_input_shape" argument to the first layer in your model.
</blockquote>

Seems like the issue is with the input shape for the Flatten layer, When I remove it, it's fine.

How can I make it play well with the variable size? 

Thanks

Keras with tensorflow Conv net with variable input size

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

我使用python 3和anaconda，使用keras和，我的目标是创建一个具有可变输入大小的Conv层的网络。我发现使用这段代码i = Input((None, None, 1))o = Conv2D(1, 3, 3)(i)model = Model(i, o)model.compile('sgd', 'mse')...

问带有tensorflow Conv网的Keras
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

问带有tensorflow Conv网的KerasEN