【发布时间】:2019-01-10 08:41:47
【问题描述】:
我搜索了几个涵盖类似问题的类似主题。例如this、this 和this 等。尽管如此,我仍然没有设法解决它。
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,我使用以下生成器分批输入 16 个 CNN:
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
生成器还将矩阵大小调整 8 倍以适应内存。 MMscale_param 函数只是将参数重新缩放为 [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:
_________________________________________________________________
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”批量大小值可以在此处替换为“无”,因此我的输入 (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:
ValueError: Error when checking target: expected dense_4 to have shape (1,) but got array with shape (3,)
我觉得很奇怪的是密集层 dense_4 具有形状 (1, ) 的说法。但在上面的架构中,它不是显示为 (3, ) 形状吗?这应该很适合输入数组的形状 (3, )。
我尝试以多种方式重塑和/或转置数组,但均未成功。我什至卸载并重新安装了 TensorFlow 和 Keras,认为那里有问题,但仍然没有。
然而,似乎可行的是仅预测三个参数之一,为我们提供 (1, 0) 的输入形状。 (虽然后来产生了其他与内存相关的错误。)这实际上独立于我如何塑造 dense_4 层,这意味着 (None, 1) 和 (None, 3) 都有效,根据我的知识有限,没有任何意义。
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')
还有训练代码:
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, )。我一定错过了这里的一些东西。
任何帮助将不胜感激。
我在 Ubuntu 上使用带有 TensorFlow 1.9.0 后端的 Keras 版本 2.2.2。
【问题讨论】:
标签: python tensorflow keras conv-neural-network linear-regression