针对错误：Cannot feed value of shape (0,) for Tensor ‘input_image:0’, which has shape ‘(?, 224, 224, 3)’]

最新推荐文章于 2021-11-30 16:31:02 发布

转载最新推荐文章于 2021-11-30 16:31:02 发布 · 3.6k 阅读

CC 4.0 BY-SA版权

原文链接：https://blog.youkuaiyun.com/qq_29309987/article/details/82944278和https://blog.youkuaiyun.com/chaofanjun/article/details/84985109

本文针对Tensor形状不匹配的问题，提供了两种解决方案。一是调整文件路径读取方式，二是确保使用正确的MITSceneParsing.pickle文件，后者通过下载特定链接的文件得以实现，有效解决了运行时的形状错误。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

针对错误：Cannot feed value of shape (0,) for Tensor ‘input_image:0’, which has shape ‘(?, 224, 224, 3)’]的解决办法
方法1：
修改read_MITSceneParsingData.py这个文件中filename = os.path.splitext(f.split("/")[-1])[0]这行代码即可，将“/”修改为“\”（两个）就能运行了。
注：我用此方法没有解决问题
方法2：
这是因为没有正确的 MITSceneParsing.pickle文件，需要下载正确的MITSceneParsing.pickle文件，文件位置如下图在这里插入图片描述
这个方法完美解决了此问题。
MITSceneParsing.pickle文件下载链接https://download.youkuaiyun.com/download/qq_29309987/10702448
本文分别参考博客：https://blog.youkuaiyun.com/qq_29309987/article/details/82944278和https://blog.youkuaiyun.com/chaofanjun/article/details/84985109

确定要放弃本次机会？

福利倒计时

: :

立减 ¥

普通VIP年卡可用

立即使用

qq_35648125

关注关注

1
点赞
踩
0

收藏

觉得还不错? 一键收藏
7
评论
分享

复制链接

分享到 QQ

分享到新浪微博

扫一扫
举报

举报

FCN-tensorflow WIN10系统运行出错Cannot feed value of shape (0,) for Tensor 'input_image:0'

baby12511的博客

01-16

520

#最主要还是read_MITSceneParsingData.py这个文件里面的filename = os.path.splitext(f.split("/")[-1])[0]没改过来，人家git中是再linxu下运行的，你是再window下运行的。具体改第二个，第一个不要改，第一个改了“\\”就生成不了MITSceneParsing.pickle文件了 # coding=utf-8 __auth...

ValueError: Cannot feed value of shape (0,) for Tensor ‘input:0‘, which has shape ‘(?, 112, 112, 3)‘

shroudiwnl的博客

02-25

1673

【深度学习】給了tf_input 一個shape為(0,)的資料，但是tf_input需要的資料維度是(?,112,112,3) 报错： ValueError: Cannot feed value of shape (0,) for Tensor 'input:0', which has shape '(?, 112, 112, 3)' 除了矩阵的型相同外（如果矩阵的型不相同，可以用reshape），还应该考虑，读取文件的路径，不能是中文名称，中文名称就会报错，改成英文名称就好了。从 train_img

7 条评论您还未登录，请先登录后发表或查看评论

Cannot feed value of shape (0,) for Tensor 'input_image:0', which has shape '(?, 224, 224, 3)']

chaofanjun

12-13

5868

现在windows也支持tensorflow，于是想在windows下跑下代码，结果发现有这样的错误： Cannot feed value of shape (0,) for Tensor ‘input_image:0’, which has shape ‘(?, 224, 224, 3)’] 主要原因是windows下和Linux下使用os.path.splitext()这个函数时有所区别，在...

Cannot feed value of shape (0,) for Tensor ‘input_image:0‘, which has shape ‘(?, 112, 112， 3）

m0_54636296的博客

11-30

1387

tensorflow 1Cannot feed value of shape (0,) for Tensor 'input_image:0', which has shape '(?, 112, 112， 3）

Cannot feed value of shape (0,) for Tensor ‘real_A_and_B_images:0‘, which has shape ‘(2, 256, 512, 6

star0w的博客

11-28

377

解决ValueError: Cannot feed value of shape (0,) for Tensor u'input_image:0', which has shape '(?, 224,

diaoshipu的博客

07-09

2248

错误描述：参考https://blog.youkuaiyun.com/MOU_IT/article/details/81073149，使用FCN训练ADEChallengeData2016时出错，“ValueError: Cannot feed value of shape (0,) for Tensor u'input_image:0', which has shape '(?, 224, 224, 3...

ValueError: Cannot feed value of shape (784,) for Tensor 'Placeholder:0', which has shape '(?, 784)'

qq_29462849的博客

10-15

5334

这个错误是tensorflow在读取数据进行推理时经常出现的一个错误，这里以mnist数据为例，mnist训练集数据维度为（55000，784），如果读取单个数据的话只有一个数据[0,0,0,1,…,0]其维度为1x784。但是在推理时，feed_dict需要采用的是[[0,0,0,1,…,0]],这样的话才知道有多少个数据被送进来，所以需要进行扩维度。 batch_xs=mnist.train...

Cannot feed value of shape (130, 246, 145) for Tensor 'real_A_and_B_images:0', which has shape '(130, 246, 246, 5)'

03-11

input_layer = tf.keras.layers.Input(shape=(246, 145, 1)) # 调整输入形状 ``` --- ### 示例修正代码 ```python # 假设原始输入形状为(130, 246, 145) input_data = tf.placeholder(tf.float32, [None, 246, ...

依然报错--------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-41-f53d3c8bb89c> in <cell line: 2>() 3 input_tensor = graph.get_tensor_by_name('ImageTensor:0') 4 output_tensor = graph.get_tensor_by_name('SemanticPredictions:0') ----> 5 output = sess.run(output_tensor, feed_dict={input_tensor: np.expand_dims(image_resized, axis=0)}) 1 frames /usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata) 1163 if (not is_tensor_handle_feed and 1164 not subfeed_t.get_shape().is_compatible_with(np_val.shape)): -> 1165 raise ValueError( 1166 f'Cannot feed value of shape {str(np_val.shape)} for Tensor ' 1167 f'{subfeed_t.name}, which has shape ' ValueError: Cannot feed value of shape (1, 804, 804) for Tensor ImageTensor:0, which has shape (1, None, None, 3)

07-14

output = sess.run(output_tensor, feed_dict={input_tensor: np.expand_dims(image_resized, axis=0)}) # 解码并可视化分割结果（DeepLabv3+模型） segmentation_mask = np.squeeze(output) segmentation_mask = ...

--------------------------------------------------------------------------- ValueError Traceback (most recent call last) <ipython-input-38-73c498ba6fc2> in <cell line: 2>() 3 input_tensor = graph.get_tensor_by_name('ImageTensor:0') 4 output_tensor = graph.get_tensor_by_name('SemanticPredictions:0') ----> 5 output = sess.run(output_tensor, feed_dict={input_tensor: img_a}) 1 frames /usr/local/lib/python3.10/dist-packages/tensorflow/python/client/session.py in _run(self, handle, fetches, feed_dict, options, run_metadata) 1163 if (not is_tensor_handle_feed and 1164 not subfeed_t.get_shape().is_compatible_with(np_val.shape)): -> 1165 raise ValueError( 1166 f'Cannot feed value of shape {str(np_val.shape)} for Tensor ' 1167 f'{subfeed_t.name}, which has shape ' ValueError: Cannot feed value of shape (1608, 1608) for Tensor ImageTensor:0, which has shape (1, None, None, 3)

07-14

output = sess.run(output_tensor, feed_dict={input_tensor: np.expand_dims(image_resized, axis=0)}) # 解码并可视化分割结果 segmentation_mask = np.squeeze(output) segmentation_mask = np.uint8...

ValueError: Cannot feed value of shape (0,) for Tensor ‘Placeholder_15:0‘, which has shape ‘(16, 498

qq_39482236的博客

10-07

1272

ValueError: Cannot feed value of shape (0,) for Tensor 'Placeholder_15:0', which has shape '(16, 498, 498, 3)' 出现原因为输入数据label是[],Placeholder已经被设置为(16, 498, 498, 3)，而需要仔细检查程序。

解决ValueError: Cannot feed value of shape (1,) for Tensor 'Placeholder_1:0', which has shape '(?, 1)'

qq_36033919的博客

04-02

1万+

我的问题出现在如下代码段： feed_dict = {model.user_input: user_input[i], model.item_input_pos: item_input_pos[i], model.item_input_neg: item_input_neg[i]} if output_adv: loss, outpu...

ValueError: Cannot feed value of shape (100, 160) for Tensor 'Placeholder:0', which has shape '(?,

肖永威的专栏

03-15

3万+

学习Tensorflow中遇到一个坑，Cannot feed value of shape (100, 160) for Tensor...，分享解决方法：np.reshape()。

成功解决ValueError: Cannot feed value of shape (1, 10, 4) for Tensor Placeholder:0 , which has shape

头部AI社区如有邀博主AI主题演讲请私信—心比天高，仗剑走天涯，保持热爱，奔赴向梦想！低调，专注，谦虚，自律，反思，成长，还算比较正能量的博主，公益免费传播…内心特别想在AI界做出一些可以推进历史进程影响力的技术(兴趣使然，有点小情怀，也有点使命感呀

12-28

2万+

成功解决ValueError: Cannot feed value of shape (1, 10, 4) for Tensor 'Placeholder:0', which has shape '( 目录解决问题解决方法解决问题 ValueError: Cannot feed value of shape (1, 10, 4) for Tensor 'Pl...

ValueError: Cannot feed value of shape (1,) for Tensor u'Placeholder:0', which has shape '(1, 1)'