我在使用 Keras 馈送 3D CNN 时遇到问题和 Python 对 3D 形状进行分类。我有一个文件夹，其中包含一些 JSON 格式的模型。我将这些模型读入 Numpy 数组。这些模型是 25*25*25，代表体素化模型的占用网格(每个位置代表位置 (i,j,k) 中的体素是否有点)，所以我只有 1 个输入 channel ，就像二维图像中的灰度图像。我的代码如下:

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution3D, MaxPooling3D
from keras.optimizers import SGD
from keras.utils import np_utils
from keras import backend as K

# Number of Classes and Epochs of Training
nb_classes = 3 # cube, cone or sphere
nb_epoch = 100
batch_size = 2

# Input Image Dimensions
img_rows, img_cols, img_depth = 25, 25, 25

# Number of Convolutional Filters to use
nb_filters = 32

# Convolution Kernel Size
kernel_size = [5,5,5]

X_train, Y_train = [], []

# Read from File
import os
import json

i=0
for filename in os.listdir(os.path.join(os.getcwd(), 'models')):
    with open(os.path.join(os.getcwd(), 'models', filename)) as f:
        file = f.readlines()
        json_file = '\n'.join(file)
        content = json.loads(json_file)
        occupancy = content['model']['occupancy']
        form = []
        for value in occupancy:
            form.append(int(value))
        final_model = [ [ [ 0 for i in range(img_rows) ]
                              for j in range(img_cols) ]
                              for k in range(img_depth) ]
        a = 0
        for i in range(img_rows):
            for j in range(img_cols):
                for k in range(img_depth):
                    final_model[i][j][k] = form[a]
                    a = a + 1
        X_train.append(final_model)
        Y_train.append(content['model']['label'])

X_train = np.array(X_train)
Y_train = np.array(Y_train)

# (1 channel, 25 rows, 25 cols, 25 of depth)
input_shape = (1, img_rows, img_cols, img_depth)

# Init
model = Sequential()

# 3D Convolution layer
model.add(Convolution3D(nb_filters, kernel_size[0], kernel_size[1], kernel_size[2],
                        input_shape=input_shape,
                        activation='relu'))

# Fully Connected layer
model.add(Flatten())
model.add(Dense(128,
          init='normal',
          activation='relu'))
model.add(Dropout(0.5))

# Softmax Layer
model.add(Dense(nb_classes,
                init='normal'))
model.add(Activation('softmax'))

# Compile
model.compile(loss='categorical_crossentropy',
              optimizer=SGD())

# Fit network
model.fit(X_train, Y_train, nb_epoch=nb_epoch,
         verbose=1)

在此之后，我得到以下错误

Using TensorFlow backend. Traceback (most recent call last): File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 670, in _call_cpp_shape_fn_impl status) File "/usr/local/Cellar/python3/3.6.0/Frameworks/Python.framework/Versions/3.6/lib/python3.6/contextlib.py", line 89, in exit next(self.gen) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 469, in raise_exception_on_not_ok_status pywrap_tensorflow.TF_GetCode(status)) tensorflow.python.framework.errors_impl.InvalidArgumentError: Negative dimension size caused by subtracting 5 from 1 for 'Conv3D' (op: 'Conv3D') with input shapes: [?,1,25,25,25], [5,5,5,25,32].

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "CNN_3D.py", line 76, in activation='relu')) File "/usr/local/lib/python3.6/site-packages/keras/models.py", line 299, in add layer.create_input_layer(batch_input_shape, input_dtype) File "/usr/local/lib/python3.6/site-packages/keras/engine/topology.py", line 401, in create_input_layer self(x) File "/usr/local/lib/python3.6/site-packages/keras/engine/topology.py", line 572, in call self.add_inbound_node(inbound_layers, node_indices, tensor_indices) File "/usr/local/lib/python3.6/site-packages/keras/engine/topology.py", line 635, in add_inbound_node Node.create_node(self, inbound_layers, node_indices, tensor_indices) File "/usr/local/lib/python3.6/site-packages/keras/engine/topology.py", line 166, in create_node output_tensors = to_list(outbound_layer.call(input_tensors[0], mask=input_masks[0])) File "/usr/local/lib/python3.6/site-packages/keras/layers/convolutional.py", line 1234, in call filter_shape=self.W_shape) File "/usr/local/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py", line 2831, in conv3d x = tf.nn.conv3d(x, kernel, strides, padding) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 522, in conv3d strides=strides, padding=padding, name=name) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op op_def=op_def) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2397, in create_op set_shapes_for_outputs(ret) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1757, in set_shapes_for_outputs shapes = shape_func(op) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1707, in call_with_requiring return call_cpp_shape_fn(op, require_shape_fn=True) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 610, in call_cpp_shape_fn debug_python_shape_fn, require_shape_fn) File "/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py", line 675, in _call_cpp_shape_fn_impl raise ValueError(err.message) ValueError: Negative dimension size caused by subtracting 5 from 1 for 'Conv3D' (op: 'Conv3D') with input shapes: [?,1,25,25,25], [5,5,5,25,32].

我做错了什么导致出现这个错误？

最佳答案

我认为问题在于您在 Theano 排序中设置输入形状，但您使用的是带有 Tensorflow 后端和 Tensorflow img 排序的 Keras。此外，y_train 数组必须转换为分类标签。

更新代码:

from keras.utils import np_utils
from keras import backend as K

if K.image_dim_ordering() == 'th':
    X_train = X_train.reshape(X_train.shape[0], 1, img_rows, img_cols, img_depth)
    input_shape = (1, img_rows, img_cols, img_depth)
else:
    X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, img_depth, 1)
    input_shape = (img_rows, img_cols, img_depth, 1)

Y_train = np_utils.to_categorical(Y_train, nb_classes)

添加此行应该可以解决它。

关于python - 3D 卷积神经网络输入形状，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/42699956/