我遇到了一个问题。我想构建一个3D卷积U-net。为此，我使用了Keras。
我的数据来自2017年数据科学碗竞赛的MRI图像。所有的MRI图像都被保存为numpy数组（所有像素值已缩放到0到1之间），形状为：
data_ch.shape(94, 50, 50, 50, 1)94 – 患者，50个MRI切片，每个切片为50×50的图像，1个通道：
我想构建一个3D卷积U-net，因此这个网络的输入和输出是相同的3D数组。3D U-net的结构如下：
input_img= Input(shape=(data_ch.shape[1], data_ch.shape[2], data_ch.shape[3], data_ch.shape[4]))x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(input_img)x=MaxPooling3D(pool_size=(2, 2, 2), padding='same')(x)x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(x)x=MaxPooling3D(pool_size=(2, 2, 2), padding='same')(x)x=UpSampling3D(size=(2, 2, 2))(x)x=Conv3D(filters=8, kernel_size=(3, 3, 3), activation='relu', padding='same')(x) # PADDING IS NOT THE SAME!!!!!x=UpSampling3D(size=(2, 2, 2))(x)x=Conv3D(filters=1, kernel_size=(3, 3, 3), activation='sigmoid')(x)model=Model(input_img, x)model.compile(optimizer='adadelta', loss='binary_crossentropy')model.summary()Layer (type) Output Shape Param # =================================================================input_5 (InputLayer) (None, 50, 50, 50, 1) 0 _________________________________________________________________conv3d_27 (Conv3D) (None, 50, 50, 50, 8) 224 _________________________________________________________________max_pooling3d_12 (MaxPooling (None, 25, 25, 25, 8) 0 _________________________________________________________________conv3d_28 (Conv3D) (None, 25, 25, 25, 8) 1736 _________________________________________________________________max_pooling3d_13 (MaxPooling (None, 13, 13, 13, 8) 0 _________________________________________________________________up_sampling3d_12 (UpSampling (None, 26, 26, 26, 8) 0 _________________________________________________________________conv3d_29 (Conv3D) (None, 26, 26, 26, 8) 1736 _________________________________________________________________up_sampling3d_13 (UpSampling (None, 52, 52, 52, 8) 0 _________________________________________________________________conv3d_30 (Conv3D) (None, 50, 50, 50, 1) 217 =================================================================Total params: 3,913Trainable params: 3,913Non-trainable params: 0但是，当我尝试将数据拟合到这个网络时：
model.fit(data_ch, data_ch, epochs=1, batch_size=10, shuffle=True, verbose=1)程序显示了一个错误：
ValueError Traceback (most recent call last)C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs) 883 outputs =\--> 884 self.fn() if output_subset is None else\ 885 self.fn(output_subset=output_subset)ValueError: CudaNdarray_CopyFromCudaNdarray: need same dimensions for dim 1, destination=13, source=14During handling of the above exception, another exception occurred:ValueError Traceback (most recent call last)<ipython-input-26-b334d38d9608> in <module>()----> 1 model.fit(data_ch, data_ch, epochs=1, batch_size=10, shuffle=True, verbose=1)C:\Users\Taranov\Anaconda3\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs) 1496 val_f=val_f, val_ins=val_ins, shuffle=shuffle, 1497 callback_metrics=callback_metrics,-> 1498 initial_epoch=initial_epoch) 1499 1500 def evaluate(self, x, y, batch_size=32, verbose=1, sample_weight=None):C:\Users\Taranov\Anaconda3\lib\site-packages\keras\engine\training.py in _fit_loop(self, f, ins, out_labels, batch_size, epochs, verbose, callbacks, val_f, val_ins, shuffle, callback_metrics, initial_epoch) 1150 batch_logs['size'] = len(batch_ids) 1151 callbacks.on_batch_begin(batch_index, batch_logs)-> 1152 outs = f(ins_batch) 1153 if not isinstance(outs, list): 1154 outs = [outs]C:\Users\Taranov\Anaconda3\lib\site-packages\keras\backend\theano_backend.py in __call__(self, inputs) 1156 def __call__(self, inputs): 1157 assert isinstance(inputs, (list, tuple))-> 1158 return self.function(*inputs) 1159 1160 C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs) 896 node=self.fn.nodes[self.fn.position_of_error], 897 thunk=thunk,--> 898 storage_map=getattr(self.fn, 'storage_map', None)) 899 else: 900 # old-style linkers raise their own exceptionsC:\Users\Taranov\Anaconda3\lib\site-packages\theano\gof\link.py in raise_with_op(node, thunk, exc_info, storage_map) 323 # extra long error message in that case. 324 pass--> 325 reraise(exc_type, exc_value, exc_trace) 326 327 C:\Users\Taranov\Anaconda3\lib\site-packages\six.py in reraise(tp, value, tb) 683 value = tp() 684 if value.__traceback__ is not tb:--> 685 raise value.with_traceback(tb) 686 raise value 687 C:\Users\Taranov\Anaconda3\lib\site-packages\theano\compile\function_module.py in __call__(self, *args, **kwargs) 882 try: 883 outputs =\--> 884 self.fn() if output_subset is None else\ 885 self.fn(output_subset=output_subset) 886 except Exception:ValueError: CudaNdarray_CopyFromCudaNdarray: need same dimensions for dim 1, destination=13, source=14Apply node that caused the error: GpuAlloc(GpuDimShuffle{0,2,x,3,4,1}.0, Shape_i{0}.0, TensorConstant{13}, TensorConstant{2}, TensorConstant{13}, TensorConstant{13}, TensorConstant{8})Toposort index: 163Inputs types: [CudaNdarrayType(float32, (False, False, True, False, False, False)), TensorType(int64, scalar), TensorType(int64, scalar), TensorType(int8, scalar), TensorType(int64, scalar), TensorType(int64, scalar), TensorType(int64, scalar)]Inputs shapes: [(10, 14, 1, 14, 14, 8), (), (), (), (), (), ()]Inputs strides: [(21952, 196, 0, 14, 1, 2744), (), (), (), (), (), ()]Inputs values: ['not shown', array(10, dtype=int64), array(13, dtype=int64), array(2, dtype=int8), array(13, dtype=int64), array(13, dtype=int64), array(8, dtype=int64)]Outputs clients: [[GpuReshape{5}(GpuAlloc.0, MakeVector{dtype='int64'}.0)]]HINT: Re-running with most Theano optimization disabled could give you a back-trace of when this node was created. This can be done with by setting the Theano flag 'optimizer=fast_compile'. If that does not work, Theano optimizations can be disabled with 'optimizer=None'.HINT: Use the Theano flag 'exception_verbosity=high' for a debugprint and storage map footprint of this apply node.我尝试按照建议使用theano标志：
import theanoimport osos.environ["THEANO_FLAGS"] = "mode=FAST_RUN,device=gpu,floatX=float32, optimizer='None',exception_verbosity=high"但它仍然不起作用。
你能帮我吗？非常感谢！
回答：
好的…这听起来很奇怪，但MaxPooling3D在使用padding='same'时似乎存在某种bug。所以我写了你的代码，去掉了这个padding，并在开始时添加了一个padding以使你的维度兼容：
import keras.backend as KinputShape = (data_ch.shape[1], data_ch.shape[2], data_ch.shape[3], data_ch.shape[4])paddedShape = (data_ch.shape[1]+2, data_ch.shape[2]+2, data_ch.shape[3]+2, data_ch.shape[4])#初始paddinginput_img= Input(shape=inputShape)x = Lambda(lambda x: K.spatial_3d_padding(x, padding=((1, 1), (1, 1), (1, 1))), output_shape=paddedShape)(input_img) #Lambda层需要output_shape#你的原始代码，去掉了MaxPooling层的padding（用x替换input_img）x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x)x=MaxPooling3D(pool_size=2)(x)x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x)x=MaxPooling3D(pool_size=2)(x)x=UpSampling3D(size=2)(x)x=Conv3D(filters=8, kernel_size=3, activation='relu', padding='same')(x) # PADDING IS NOT THE SAME!!!!!x=UpSampling3D(size=2)(x)x=Conv3D(filters=1, kernel_size=3, activation='sigmoid')(x)model=Model(input_img, x)model.compile(optimizer='adadelta', loss='binary_crossentropy')model.summary()print(model.predict(data_ch)[1])model.fit(data_ch,data_ch,epochs=1,verbose=2,batch_size=10)