ValueError: Shape mismatch: The shape of labels (received (768,)) should equal the shape of logits e

问题

运行tensorflow 的resnet网络，预测结果，出现报错

原因

解决：use of sparse_softmax_cross_entropy. feed it one hot encoded labels which it doesn’t want.

Switch to just normal softmax_cross_entropy and see if that works.
这个问题是由于输出层的类别数和训练数据shape不同导致。
在训练模型时，一般会将label使用one hot编码，然后模型的loss使用交叉熵：

解决方法

Use this crossentropy loss function when there are two or more label classes. We expect labels to be provided in a one_hot representation. If you want to provide labels as integers, please use SparseCategoricalCrossentropy loss. There should be # classes floating point values per feature.

修改sparse_categorical_crossentropy为ategorical_crossentropy

ValueError: Shape mismatch: The shape of labels (received (768,)) should equal the shape of logits e相关推荐

成功解决IndexError: shape mismatch: indexing arrays could not be broadcast together with shapes (100,)
成功解决IndexError: shape mismatch: indexing arrays could not be broadcast together with shapes (100,) 目 ...
Cannot copy param 0 weights from layer 'fc6'; shape mismatch.
问题: Cannot copy param 0 weights from layer 'fc6'; shape mismatch. Source param shape is 4096 9216 (3 ...
超分辨率分割SLIC算法实现过程遇到的问题，shape mismatch: value array of shape (3,) could not be broadcast to indexing
超分辨率分割SLIC算法实现过程遇到的问题 shape mismatch: value array of shape (3,) could not be broadcast to indexing r ...
size mismatch for roi_heads.box_predictor.cls_score.weight: copying a param with shape torch.Size([9
1. 报错 RuntimeError: Error(s) in loading state_dict for FasterRCNN: size mismatch for roi_heads.box_p ...
ValueError: mode mismatch
项目场景:PIL库Image模块处理数组合并成3通道RGB图像项目中,使用Pytorch的torch.utils.data.DataLoader加载自己准备好的数据集.同时想要直观查看或验证生成的数 ...
valueError: Length mismatch: Expected axis has 40 elements, new values have 38 elements
背景我拿原来的模型准备跑一个新数据集,当然列就会不同新数据集没有head,我就自己傻乎乎一个一个数的列数(应该是数错了我原来数的38其实是40) 就报了valueError: Length mi ...
成功解决 ValueError: feature_names mismatch training data did not have the following fields
成功解决 ValueError: feature_names mismatch training data did not have the following fields 目录解决问题解决思路 ...
编写一个抽象类Shape，声明计算图形面积的抽象方法。再分别定义Shape的子类Circle（圆）和Rectangle（矩形），在两个子类中按照不同图形的面积计算公式，实现Shape类中计算面积的方法
编写一个抽象类Shape,声明计算图形面积的抽象方法.再分别定义Shape的子类Circle(圆)和Rectangle(矩形),在两个子类中按照不同图形的面积计算公式,实现Shape类中计算面积的方法 ...
Check failed: top_shape[j] == bottom[i]-shape(j) (1 vs. 2) All inputs must have the same shape, exc
在运行ShuffleNet的过程中碰到了如下报错 : I1018 19:26:19.104892 3548 net.cpp:84] Creating Layer resx13_concat I1018 ...

ValueError: Shape mismatch: The shape of labels (received (768,)) should equal the shape of logits e

问题

原因

解决方法

ValueError: Shape mismatch: The shape of labels (received (768,)) should equal the shape of logits e相关推荐

最新文章

热门文章