ValueError:检查目标时出错:预期dense_44具有形状(1，)但得到形状为(3，)的数组 [英] ValueError: Error when checking target: expected dense_44 to have shape (1,) but got array with shape (3,)
问题描述
我搜索了几个涵盖类似问题的类似主题.例如这个, 这个 和 这个 等等.尽管如此，我仍然没有设法解决它.
I've searched several similar topics covering similar problems. For example this, this and this, among others. Despite this, I still haven't managed to solve it.
我最终要做的是使用 CNN 预测三个参数.输入是初始大小为 (3724, 4073, 3) 的矩阵(现在可以在预处理后绘制为 RGB 图像).由于数据集的大小，我使用以下生成器以 16 个批次为 CNN 提供数据:
What I'm ultimately trying to do is predicting three parameters using CNNs. The inputs are matrices (which can now be plotted as RGB images after pre-processing) with the initial size of (3724, 4073, 3). Due to the size of the data set I'm feeding the CNN in batches of 16 using the following generator:
class My_Generator(Sequence):
""" Generates batches of training data and ground truth. Inputs are the image paths and batch size. """
def __init__(self, image_paths, batch_size, normalise=True):
self.image_paths, self.batch_size = image_paths, batch_size
self.normalise = normalise
def __len__(self):
return int(np.ceil(len(self.image_paths) / float(self.batch_size)))
def __getitem__(self, idx):
batch = self.image_paths[idx * self.batch_size:(idx + 1) * self.batch_size]
matrices, parameters = [], []
for file_path in batch:
mat, param, name = get_Matrix_and_Parameters(file_path)
#Transform the matrix from 2D to 3D as a (mat.shape[0], mat.shape[1]) RBG image. Rescale its values to [0,1]
mat = skimage.transform.resize(mat, (mat.shape[0]//8, mat.shape[1]//8, 3),
mode='constant', preserve_range=self.normalise)
param = MMscale_param(param, name) # Rescale the parameters
matrices.append(mat)
parameters.append(param)
MAT, PAM = np.array(matrices), np.array(parameters)
PAM = np.reshape(PAM, (PAM.shape[0], PAM.shape[1]))
print("Shape Matrices: {0}, Shape Parameters: {1}".format(MAT.shape, PAM.shape))
print("Individual PAM shape: {0}".format(PAM[0,:].shape))
return MAT, PAM
生成器还将矩阵的大小调整为 8 倍以适应内存.函数 MMscale_param 只是将参数重新缩放为 [0, 1].
The generator is also resizing the matrices by 8 times to fit into memory. The function MMscale_param is simply rescaling the parameters to [0, 1].
生成的批次现在具有形状 (16, 465, 509, 3).这些现在被输入到以下 CNN 架构中:
The generated batches now have shape (16, 465, 509, 3). These are now fed into the following CNN architecture:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 463, 507, 16) 448
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 231, 253, 16) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 229, 251, 32) 4640
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 114, 125, 32) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 112, 123, 64) 18496
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 56, 61, 64) 0
_________________________________________________________________
conv2d_4 (Conv2D) (None, 54, 59, 128) 73856
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 27, 29, 128) 0
_________________________________________________________________
conv2d_5 (Conv2D) (None, 25, 27, 256) 295168
_________________________________________________________________
max_pooling2d_5 (MaxPooling2 (None, 12, 13, 256) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 39936) 0
_________________________________________________________________
dense_1 (Dense) (None, 1000) 39937000
_________________________________________________________________
dense_2 (Dense) (None, 100) 100100
_________________________________________________________________
dense_3 (Dense) (None, 20) 2020
_________________________________________________________________
dense_4 (Dense) (None, 3) 63
=================================================================
Total params: 40,431,791
Trainable params: 40,431,791
Non-trainable params: 0
_________________________________________________________________
如上所示，模型中的最后一层期望输入为 (None, 3).如果我理解正确，任何"批量大小值可以替换为无"；在这里，我的输入 (16, 3) 或 (batch_size, number_of_parameters_to_predict) 应该是有效的.但是，我仍然收到以下错误消息:
As displayed above, the last layer in the model expects the input to be (None, 3). If I understand this correct, "any" batch size value could be replaced by "None" here, so my input, (16, 3) or (batch_size, number_of_parameters_to_predict), should be valid. However, I'm still getting the following error message:
ValueError: Error when checking target: expected dense_4 to have shape (1,) but got array with shape (3,)
我觉得很奇怪的是 Dense 层 dense_4 具有形状 (1, ) 的说法.但是在上面的架构中不是显示它是一个 (3, ) 形状吗?这应该很适合输入数组的形状 (3, ).
What I find to be very strange is the claim that Dense layer dense_4 has shape (1, ). But isn't it displayed in the architecture above that it's a (3, ) shape? This should then fit well with the input array's shape (3, ).
我尝试以多种方式重塑和/或转置数组，但没有成功.我什至卸载并重新安装了 TensorFlow 和 Keras，因为我认为那里出了点问题，但仍然没有.
I've tried to reshape and/or transpose the array in several ways but without success. I've even uninstalled and reinstalled TensorFlow and Keras in the belief that something was wrong there, but still nothing.
然而，似乎可行的是只预测三个参数中的一个，从而为我们提供 (1, 0) 的输入形状.(尽管后来产生了其他与内存相关的错误.)这实际上与我如何塑造 dense_4 层无关，这意味着 (None, 1) 和 (None, 3) 都可以工作，根据我的知识有限，没有任何意义.
What seem to work however, is to only predict one of the three parameters, giving us an input shape of (1, 0). (Later yielding other, memory related, errors though.) This actually works independently of how I shape the dense_4 layer, meaning that both (None, 1) and (None, 3) works, which according to my limited knowledge, doesn't make any sense.
添加编译；
batch_size = 16
my_training_batch_generator_NIR = My_Generator(training_paths_NIR, batch_size)
my_validation_batch_generator_NIR = My_Generator(validation_paths_NIR, batch_size)
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam')
以及训练代码:
model_path = "/Models/weights.best.hdf5"
num_epochs = 10
checkpointer = ModelCheckpoint(filepath=model_path,
verbose=1,
save_best_only=True)
model.fit_generator(generator=my_training_batch_generator_NIR,
steps_per_epoch=(len(validation_paths_NIR) // batch_size),
epochs=num_epochs,
verbose=1,
callbacks=[checkpointer],
validation_data=my_validation_batch_generator_NIR,
validation_steps=(len(validation_paths_NIR) // batch_size),
use_multiprocessing=True,
max_queue_size=1,
workers=1)
所以，总结一下:我在将 (3, ) 数组拟合到我认为是 (3, ) 层时遇到了问题.然而，后者声称是形状 (1, ).我一定在这里错过了一些东西.
So, to sum up: I'm having problems fitting a (3, ) array into, what I believe is, a (3, ) layer. However, the latter is claimed to be of shape (1, ). I must be missing out on something here.
任何帮助将不胜感激.
我在 Ubuntu 上使用 Keras 2.2.2 版和 TensorFlow 1.9.0 后端.
I'm using Keras version 2.2.2 with TensorFlow 1.9.0 backend on Ubuntu.
推荐答案
这是因为您使用的损失函数.将其替换为
This is because of loss function you are using. Replace that with
loss='categorical_crossentropy'
代码应该可以工作了.
这篇关于ValueError:检查目标时出错:预期dense_44具有形状(1，)但得到形状为(3，)的数组的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
