如何解决尝试训练模型时出现的错误？
How can I solve this error that arises when trying to train a model?
我在尝试使用此架构训练模型时遇到此错误。该问题与输入形状有关。谁能帮帮我？下面附上模型架构和报错
def simple_unet_model(IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS, num_classes):
inputs = Input((IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS))
s = inputs
#Contraction path
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(s)
c1 = Dropout(0.1)(c1)
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c1)
p1 = MaxPooling3D((2, 2, 2))(c1)
c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p1)
c2 = Dropout(0.1)(c2)
c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c2)
p2 = MaxPooling3D((2, 2, 2))(c2)
c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p2)
c3 = Dropout(0.2)(c3)
c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c3)
p3 = MaxPooling3D((2, 2, 2))(c3)
c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p3)
c4 = Dropout(0.2)(c4)
c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c4)
p4 = MaxPooling3D(pool_size=(2, 2, 2))(c4)
c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p4)
c5 = Dropout(0.3)(c5)
c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c5)
#Expansive path
u6 = Conv3DTranspose(128, (2, 2, 2), strides=(2, 2, 2), padding='same')(c5)
u6 = concatenate([u6, c4])
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u6)
c6 = Dropout(0.2)(c6)
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c6)
u7 = Conv3DTranspose(64, (2, 2, 2), strides=(2, 2, 2), padding='same')(c6)
u7 = concatenate([u7, c3])
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u7)
c7 = Dropout(0.2)(c7)
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c7)
u8 = Conv3DTranspose(32, (2, 2, 2), strides=(2, 2, 2), padding='same')(c7)
u8 = concatenate([u8, c2])
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u8)
c8 = Dropout(0.1)(c8)
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c8)
u9 = Conv3DTranspose(16, (2, 2, 2), strides=(2, 2, 2), padding='same')(c8)
u9 = concatenate([u9, c1])
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u9)
c9 = Dropout(0.1)(c9)
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c9)
outputs = Conv3D(num_classes, (1, 1, 1), activation='softmax')(c9)
model = Model(inputs=[inputs], outputs=[outputs])
#compile model outside of this function to make it flexible.
model.summary()
return model
同时，图像和蒙版的输入形状分别为 (1,172,128,128,1) 和 (1,172,128,128,4)。类型分别为float64和float32 。错误如下：
Epoch 1/50
2022-06-03 08:45:27.043299: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-06-03 08:45:27.776684: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 2151 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1650, pci bus id: 0000:01:00.0, compute capability: 7.5
2022-06-03 08:45:49.914398: I tensorflow/stream_executor/cuda/cuda_dnn.cc:366] Loaded cuDNN version 8101
2022-06-03 08:45:27.043299: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-06-03 08:45:27.776684: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 2151 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1650, pci bus id: 0000:01:00.0, compute capability: 7.5
2022-06-03 08:45:49.914398: I tensorflow/stream_executor/cuda/cuda_dnn.cc:366] Loaded cuDNN version 8101
2022-06-03 08:45:55.278696: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 601.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.278748: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 601.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.289252: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.289295: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.302345: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.27GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.302387: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.27GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
Traceback (most recent call last):
Input In [6] in <cell line: 1>
history=model.fit(train_img_datagen,
File ~\anaconda3\envs\tf2.7\lib\site-packages\keras\utils\traceback_utils.py:67 in error_handler
raise e.with_traceback(filtered_tb) from None
File ~\anaconda3\envs\tf2.7\lib\site-packages\tensorflow\python\eager\execute.py:58 in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [1,128,24,16,16] vs. shape[1] = [1,128,25,16,16]
[[node model_1/concatenate_4/concat
(defined at C:\Users\USER\anaconda3\envs\tf2.7\lib\site-packages\keras\backend.py:3224)
]] [Op:__inference_train_function_4350]
Errors may have originated from an input operation.
Input Source operations connected to node model_1/concatenate_4/concat:
In[0] model_1/conv3d_transpose_4/BiasAdd (defined at C:\Users\USER\anaconda3\envs\tf2.7\lib\site-packages\keras\layers\convolutional.py:1660)
In[1] model_1/conv3d_26/Relu (defined at C:\Users\USER\anaconda3\envs\tf2.7\lib\site-packages\keras\backend.py:4867)
In[2] model_1/concatenate_4/concat/axis: ...
错误在于 Concat 层的输入形状：
ConcatOp : Dimensions of inputs should match: shape[0] = [1,128,24,16,16] vs. shape[1] = [1,128,25,16,16]
检查 Concat 层的输入。
Post题中模型架构代码
我在尝试使用此架构训练模型时遇到此错误。该问题与输入形状有关。谁能帮帮我？下面附上模型架构和报错
def simple_unet_model(IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS, num_classes):
inputs = Input((IMG_HEIGHT, IMG_WIDTH, IMG_DEPTH, IMG_CHANNELS))
s = inputs
#Contraction path
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(s)
c1 = Dropout(0.1)(c1)
c1 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c1)
p1 = MaxPooling3D((2, 2, 2))(c1)
c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p1)
c2 = Dropout(0.1)(c2)
c2 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c2)
p2 = MaxPooling3D((2, 2, 2))(c2)
c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p2)
c3 = Dropout(0.2)(c3)
c3 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c3)
p3 = MaxPooling3D((2, 2, 2))(c3)
c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p3)
c4 = Dropout(0.2)(c4)
c4 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c4)
p4 = MaxPooling3D(pool_size=(2, 2, 2))(c4)
c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(p4)
c5 = Dropout(0.3)(c5)
c5 = Conv3D(256, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c5)
#Expansive path
u6 = Conv3DTranspose(128, (2, 2, 2), strides=(2, 2, 2), padding='same')(c5)
u6 = concatenate([u6, c4])
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u6)
c6 = Dropout(0.2)(c6)
c6 = Conv3D(128, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c6)
u7 = Conv3DTranspose(64, (2, 2, 2), strides=(2, 2, 2), padding='same')(c6)
u7 = concatenate([u7, c3])
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u7)
c7 = Dropout(0.2)(c7)
c7 = Conv3D(64, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c7)
u8 = Conv3DTranspose(32, (2, 2, 2), strides=(2, 2, 2), padding='same')(c7)
u8 = concatenate([u8, c2])
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u8)
c8 = Dropout(0.1)(c8)
c8 = Conv3D(32, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c8)
u9 = Conv3DTranspose(16, (2, 2, 2), strides=(2, 2, 2), padding='same')(c8)
u9 = concatenate([u9, c1])
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(u9)
c9 = Dropout(0.1)(c9)
c9 = Conv3D(16, (3, 3, 3), activation='relu', kernel_initializer=kernel_initializer, padding='same')(c9)
outputs = Conv3D(num_classes, (1, 1, 1), activation='softmax')(c9)
model = Model(inputs=[inputs], outputs=[outputs])
#compile model outside of this function to make it flexible.
model.summary()
return model
同时，图像和蒙版的输入形状分别为 (1,172,128,128,1) 和 (1,172,128,128,4)。类型分别为float64和float32 。错误如下：
Epoch 1/50
2022-06-03 08:45:27.043299: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-06-03 08:45:27.776684: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 2151 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1650, pci bus id: 0000:01:00.0, compute capability: 7.5
2022-06-03 08:45:49.914398: I tensorflow/stream_executor/cuda/cuda_dnn.cc:366] Loaded cuDNN version 8101
2022-06-03 08:45:27.043299: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2
To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.
2022-06-03 08:45:27.776684: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1525] Created device /job:localhost/replica:0/task:0/device:GPU:0 with 2151 MB memory: -> device: 0, name: NVIDIA GeForce GTX 1650, pci bus id: 0000:01:00.0, compute capability: 7.5
2022-06-03 08:45:49.914398: I tensorflow/stream_executor/cuda/cuda_dnn.cc:366] Loaded cuDNN version 8101
2022-06-03 08:45:55.278696: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 601.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.278748: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 601.00MiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.289252: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.289295: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 1.15GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.302345: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.27GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
2022-06-03 08:45:55.302387: W tensorflow/core/common_runtime/bfc_allocator.cc:275] Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.27GiB with freed_by_count=0. The caller indicates that this is not a failure, but may mean that there could be performance gains if more memory were available.
Traceback (most recent call last):
Input In [6] in <cell line: 1>
history=model.fit(train_img_datagen,
File ~\anaconda3\envs\tf2.7\lib\site-packages\keras\utils\traceback_utils.py:67 in error_handler
raise e.with_traceback(filtered_tb) from None
File ~\anaconda3\envs\tf2.7\lib\site-packages\tensorflow\python\eager\execute.py:58 in quick_execute
tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [1,128,24,16,16] vs. shape[1] = [1,128,25,16,16]
[[node model_1/concatenate_4/concat
(defined at C:\Users\USER\anaconda3\envs\tf2.7\lib\site-packages\keras\backend.py:3224)
]] [Op:__inference_train_function_4350]
Errors may have originated from an input operation.
Input Source operations connected to node model_1/concatenate_4/concat:
In[0] model_1/conv3d_transpose_4/BiasAdd (defined at C:\Users\USER\anaconda3\envs\tf2.7\lib\site-packages\keras\layers\convolutional.py:1660)
In[1] model_1/conv3d_26/Relu (defined at C:\Users\USER\anaconda3\envs\tf2.7\lib\site-packages\keras\backend.py:4867)
In[2] model_1/concatenate_4/concat/axis: ...
错误在于 Concat 层的输入形状：
ConcatOp : Dimensions of inputs should match: shape[0] = [1,128,24,16,16] vs. shape[1] = [1,128,25,16,16]
检查 Concat 层的输入。
Post题中模型架构代码