entityMap|blocks|key|95o4g|text|所以碰巧的是，我已经更新了TensorFlow代码，但是训练失败了。因此，我回滚到以前的版本，对run脚本进行了适当的新更改，并使其正常工作。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|cer0g^0|0^^$0|$]|1|@$2|3|4|5|6|7|8|D|9|@]|A|@]|B|$]]|$2|C|4|-4|6|7|8|E|9|@]|A|@]|B|$]]]]

So as it happens, I had updated the TensorFlow code but had failed to train it. So I rolled back to the previous version, made the appropriate new changes to the run script and got it working.

entityMap|blocks|key|68qgl|text|尝试删除从以前的运行中保存的任何检查点。有时，当更改体系结构并再次运行时，TF将从旧的检查点(但使用新的定义)拾取，您会得到此错误。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|54kv3^0|0^^$0|$]|1|@$2|3|4|5|6|7|8|D|9|@]|A|@]|B|$]]|$2|C|4|-4|6|7|8|E|9|@]|A|@]|B|$]]]]

Try deleting any checkpoints that were saved from previous runs. Sometimes when changing the architecture and running again, TF will pick up from the old checkpoint (but with new definition), and you get this error.

entityMap|blocks|key|d5160|text|我也遇到了这个问题，问题是标签和类编号不匹配，所以我更改并修复了类编号计数和到处都是的标签。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|2eian|在我的例子中，它更改了faster_rcnn.config和"label_map.pbtxt“文件中的"num_classes”参数，使其与实际值相匹配。|67p26^0|0|0^^$0|$]|1|@$2|3|4|5|6|7|8|F|9|@]|A|@]|B|$]]|$2|C|4|D|6|7|8|G|9|@]|A|@]|B|$]]|$2|E|4|-4|6|7|8|H|9|@]|A|@]|B|$]]]]

I also ran into this problem, the problem was that the labels and class numbers didn't matched so I changed and fix the class number cound and labels everywhere.

In my case it was to change the "num_classes" parameter in the faster_rcnn.config
and the "label_map.pbtxt" file to match with the real values.

entityMap|blocks|key|da9tb|text|如果删除检查点不起作用，则此错误是由于尺寸引起的，因此请检查类的数量是否与图像的尺寸相同|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1soqu^0|0^^$0|$]|1|@$2|3|4|5|6|7|8|D|9|@]|A|@]|B|$]]|$2|C|4|-4|6|7|8|E|9|@]|A|@]|B|$]]]]

If deleting checkpoints didn't work, this error is due to dimensions, so chek if the number of classes correspond to the same, as well as the dimensions of the image

entityMap|blocks|key|2ic3i|text|在我的例子中，training/faster_rcnnresnet50_coco.config文件中的num_classes不正确。因此得到了这个错误。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|3ia2o^0|0^^$0|$]|1|@$2|3|4|5|6|7|8|D|9|@]|A|@]|B|$]]|$2|C|4|-4|6|7|8|E|9|@]|A|@]|B|$]]]]

In my case the num_classes in training/faster_rcnn_resnet50_coco.config file was not correct. Hence got this error.

entityMap|blocks|key|31a14|text|也会发生输入图像形状与输入图像张量不匹配的情况。这意味着，当模型期望将输入图像作为RGB，但您正在向其发送灰度图像时，您可能会遇到此问题。因此，请确保具有正确的输入数据。使用opencv的image.shape函数查看。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|5m1gh|import+cv2
im+=+cv2.imread('lena.jpg')
h,+w,+c+=+im.shape
print(h,w,c)|code-block|syntax|javascript|anplj|其中；h是高度w是宽度c是通道|b9m2b^0|0|0|0^^$0|$]|1|@$2|3|4|5|6|7|8|K|9|@]|A|@]|B|$]]|$2|C|4|D|6|E|8|L|9|@]|A|@]|B|$F|G]]|$2|H|4|I|6|7|8|M|9|@]|A|@]|B|$]]|$2|J|4|-4|6|7|8|N|9|@]|A|@]|B|$]]]]

It also happens that the input image shape doesn't match with the input image tensor. Meaning, you may experience this problem when the model is expecting to have an input image as RGB but you are sending it Gray scale image. So, make sure to have the right input data. Check it by using the image.shape function of opencv.
<pre><code>import cv2
im = cv2.imread('lena.jpg')
h, w, c = im.shape
print(h,w,c)
</code></pre>
where;
h is height
w is width
c is channel

I am a TensorFlow noob. I have trained a TensorFlow model from the open source implementation of deeppose and have to now run the model against a new set of images.

The model was trained on images of size <code>100 * 100</code> so I have resized the new set of images to the same size. I have <code>149</code> new images to run the model against. When I run the model, I get the following error.

<pre><code>InvalidArgumentError (see above for traceback): Assign requires shapes
of both tensors to match. lhs shape= [20] rhs shape= [48]
</code></pre>

At the line

<pre><code>saver = tf.train.Saver(tf.all_variables())
</code></pre>

I suspect the trained model size and the test image sizes are not matching. I am not clear how to fix this issue. I printed out the list of variables from the <code>tf.all_variables()</code> call. Here it is

<pre><code>Tensor("Placeholder:0", shape=(128, 100, 100, 3), dtype=float32)
(11, 11, 3, 20)
conv1/weights:0
(20,)
conv1/biases:0
(5, 5, 20, 35)
conv2/weights:0
(35,)
conv2/biases:0
(3, 3, 35, 50)
conv4/weights:0
(50,)
conv4/biases:0
(3, 3, 50, 75)
conv5/weights:0
(75,)
conv5/biases:0
(300, 1024)
local1/weights:0
(1024,)
local1/biases:0
(1024, 1024)
local2/weights:0
(1024,)
local2/biases:0
(1024, 0)
softmax_linear/weights:0
(0,)
softmax_linear/biases:0
</code></pre>

I am not sure where the RHS parameter is coming from. I've looked at all config files and there doesn't seem to be any parameter specifying this config.

Any help in resolving this will be greatly appreciated.

Tensorflow Assign requires shapes of both tensors to match. lhs shape= [20] rhs shape= [48]

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

教程

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

腾讯云智能顾问专区

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

聚焦“写作效率、视觉美观与运行性能”三方面进行全面升级，为您提供更高效、稳定的创作环境

社区富文本&Markdown编辑器全新改版上线，欢迎大家体验!

诚挚邀请您参与本次调研，分享您的真实使用感受与建议。您的反馈至关重要，感谢您的支持与参与！

社区新版编辑器体验调研

 我是TensorFlow新手。我已经从deeppose的开源实现中训练了一个TensorFlow模型，现在必须对一组新的图像运行该模型。 该模型是在100 * 100大小的图像上训练的，因此我将新图像集的大小调整为相同的大小。我有要运行模型的149新图像。当我运行模型时，我得到以下错误。 InvalidArgumen...

问Tensorflow Assign需要两个张量的形状才能匹配。lhs shape= [20] rhs shape= [48]
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Tensorflow Assign需要两个张量的形状才能匹配。lhs shape= [20] rhs shape= [48]EN