我正在创建一个高度=128，宽度=128，通道=3的3D CNN模型。3D CNN的代码-
def get_model(width=128, height=128, depth=3):
"""
Build a 3D convolutional neural network
"""
inputs = tf.keras.Input((width, height, depth, 1))
x = layers.Conv3D(filters=64, kernel_size=3, activation="relu")(inputs)
x = layers.MaxPool3D(pool_size=2)(x)
x = layers.BatchNormalization()(x)
x = layers.Conv3D(filters=128, kernel_size=3, activation="relu")(x)
x = layers.MaxPool3D(pool_size=2)(x)
x = layers.BatchNormalization()(x)
x = layers.Conv3D(filters=256, kernel_size=3, activation="relu")(x)
x = layers.MaxPool3D(pool_size=2)(x)
x = layers.BatchNormalization()(x)
x = layers.GlobalAveragePooling3D()(x)
x = layers.Dense(units=512, activation="relu")(x)
x = layers.Dropout(0.3)(x)
outputs = layers.Dense(units=4, activation='softmax')(x)
model= keras.Model(inputs, outputs, name="3DCNN")
return model
因此，在创建模型函数后，当我试图构建模型时，它会抛出一个值错误
-ValueError: Negative dimension size caused by subtracting 2 from 1 for '{{node max_pooling3d_5/MaxPool3D}} = MaxPool3D[T=DT_FLOAT, data_format="NDHWC", ksize=[1, 2, 2, 2, 1], padding="VALID", strides=[1, 2, 2, 2, 1]](Placeholder)' with input shapes: [?,126,126,1,64].
构建模型的代码：-#建立模型
model = get_model(width=128, height=128, depth=3)
model.summary()
完全错误-
InvalidArgumentError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs, op_def)
1879 try:
-> 1880 c_op = pywrap_tf_session.TF_FinishOperation(op_desc)
1881 except errors.InvalidArgumentError as e:
InvalidArgumentError: Negative dimension size caused by subtracting 2 from 1 for '{{node max_pooling3d_5/MaxPool3D}} = MaxPool3D[T=DT_FLOAT, data_format="NDHWC", ksize=[1, 2, 2, 2, 1], padding="VALID", strides=[1, 2, 2, 2, 1]](Placeholder)' with input shapes: [?,126,126,1,64].
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
14 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/ops.py in _create_c_op(graph, node_def, inputs, control_inputs, op_def)
1881 except errors.InvalidArgumentError as e:
1882 # Convert to ValueError for backwards compatibility.
-> 1883 raise ValueError(str(e))
1884
1885 return c_op
ValueError: Negative dimension size caused by subtracting 2 from 1 for '{{node max_pooling3d_5/MaxPool3D}} = MaxPool3D[T=DT_FLOAT, data_format="NDHWC", ksize=[1, 2, 2, 2, 1], padding="VALID", strides=[1, 2, 2, 2, 1]](Placeholder)' with input shapes:
[?,126,126,1,64].
这个错误是什么意思？？我的尺寸有问题吗？？
提前感谢！！！！！
在不指定data_format参数的情况下，Conv3D层将输入形状视为：
batch_shape + (conv_dim1, conv_dim2, conv_dim3, channels)
您已指定为：
batch_shape + (width=128, height=128, depth=3, channels=1)
因此，您有一个数据，它的形状是(128,128,3)，并且有一个通道。
由于卷积运算适用于(128,128,3)的前3个维度，因此在kernel_size=3进行第一次卷积后，第3个维度(指定为深度=3的维度(将缩小为1。然后在下一层(MaxPooling3D(中，由于形状不合适，它无法通过2获得池化。因此，可以考虑将深度维度更改较大的数字或更改kernel_size参数。例如，输入形状可以是(128,128,128,1)，或者kernel_size应该改变为类似(3,3,1)的其他形状。
第页。S： 如果有RGB图像，则通道数为3，最后一个维度应设置为3。在3D图像中，有另一个不同于通道的概念，称为深度(另一个维度(。因此：
- 3D图像RGB:
(width, height, depth, 3) - 3D图像灰度：
(width, height, depth, 1) - 2D图像RGB:
(width, height, 3) - 2D图像灰度：
(width, height, 1)