3D卷积神经网络输入形状

Question

我在使用Keras和Python 输入3D CNN时遇到了问题,无法对3D形状进行分类.我有一个包含JSON格式的模型的文件夹.我把这些模型读成Numpy数组.模型是25*25*25并且表示体素化模型的占用网格(每个位置表示位置(i,j,k)中的体素是否具有点或否),因此我只有1个输入通道,喜欢2D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,我收到以下错误

使用TensorFlow后端.回溯(最近一次调用最后一次):文件"/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py",第670行,_call_cpp_shape_fn_impl状态)文件"/ usr/local/Cellar/python3/3.6.0/Frameworks/Python.framework/Versions/3.6/lib/python3.6/contextlib.py",第89行,在exit next(self.gen)文件"/ usr/local/lib/python3 .6/site-packages/tensorflow/python/framework/errors_impl.py",第469行,在raise_exception_on_not_ok_status pywrap_tensorflow.TF_GetCode(status)中)tensorflow.python.framework.errors_impl.InvalidArgumentError:由于从1减去5而导致的负维度大小具有输入形状的'Conv3D'(op:'Conv3D'):[？,1,25,25,25],[5,5,5,25,32].

在处理上述异常期间,发生了另一个异常:

回溯(最近一次调用最后一次):文件"CNN_3D.py",第76行,激活='relu'))文件"/usr/local/lib/python3.6/site-packages/keras/models.py",第299行,添加了layer.create_input_layer(batch_input_shape,input_dtype)文件"/usr/local/lib/python3.6/site-packages/keras/engine/topology.py",第401行,在create_input_layer self(x)文件中/usr/local/lib/python3.6/site-packages/keras/engine/topology.py",第572行,调用 self.add_inbound_node(inbound_layers,node_indices,tensor_indices)文件"/ usr/local/lib/python3. 6/site-packages/keras/engine/topology.py",第635行,在add_inbound_node中Node.create_node(self,inbound_layers,node_indices,tensor_indices)文件"/usr/local/lib/python3.6/site-packages/keras /engine/topology.py",第166行,在create_node中output_tensors = to_list(outbound_layer.call(input_tensors [0],mask = input_masks [0]))文件"/usr/local/lib/python3.6/site-packages /keras/layers/convolutional.py",第1234行,在调用filter_shape = self.W_shape中)文件"/usr/local/lib/python3.6/s ite-packages/keras/backend/tensorflow_backend.py",第2831行,在conv3d中x = tf.nn.conv3d(x,内核,步幅,填充)文件"/usr/local/lib/python3.6/site-packages /tensorflow/python/ops/gen_nn_ops.py",第522行,在conv3d strides = strides,padding = padding,name = name)文件"/usr/local/lib/python3.6/site-packages/tensorflow/python/ framework/op_def_library.py",第763行,在apply_op中op_def = op_def)文件"/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py",第2397行,在create_op中set_shapes_for_outputs (ret)文件"/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/ops.py",第1757行,in set_shapes_for_outputs shapes = shape_func(op)文件"/ usr/local/lib /python3.6/site-packages/tensorflow/python/framework/ops.py",第1707行,在call_with_requiring中返回call_cpp_shape_fn(op,require_shape_fn = True)文件"/usr/local/lib/python3.6/site-packages /tensorflow/python/framework/common_shapes.py",第610行,在call_cpp_shape_fn debug_python_shape_fn中,require_shape _fn)文件"/usr/local/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py",第675行,在_call_cpp_shape_fn_impl中引发ValueError(err.message)ValueError:由减去引起的负尺寸大小对于'Conv3D'(op:'Conv3D'),输入形状为[？,1,25,25,25],[5,5,5,25,32].

得到这个错误我做错了什么？

Answer 1

我认为问题是你在Theano排序中设置输入形状,但你使用的是Keras with Tensorflow后端和Tensorflow img排序.此外,必须将y_train数组转换为分类标签.

更新的代码:

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)

添加这些行应该修复它.