Reputation: 95
3D Convolutional Neural Network input shape
I'm having a problem feeding a 3D CNN using Keras and Python to classify 3D shapes. I have a folder with some models in JSON format. I read those models into a Numpy Array. The models are 25*25*25 and represent the occupancy grid of the voxelized model (each position represents if the voxel in position (i,j,k) has points in it or no), so I only have 1 channel of input, like grayscale images in 2D images. The code that I have is the following:
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)
After this, I get the following error
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].
What am I doing wrong to get this error?
Upvotes: 7
Views: 12623
Answers (2)
Reputation: 9
if you use 3d CNN to frame prediction ,you must use : input=( no. of frame ,hight, width ,channel ) my code def cnn_network(): model = Sequential()
# # Layer 1
# model.add(
# Conv3D(512, kernel_size=(3, 3, 3), strides=(1, 1, 1), input_shape=(6, 14, 14, 512), use_bias=512, padding='SAME',
# activation='relu',
# name='conv3D_1_1'))
# model.add(Conv3D(512, kernel_size=(3, 3, 3), strides=(1, 1, 1),use_bias=512, padding='SAME',
# activation='relu',name='conv3D_1_5'))
# model.add(MaxPooling3D(pool_size=(4, 2, 2), strides=(1, 2, 2)))
# model.add(BatchNormalization())
# # Layer 2
# model.add(
# Conv3DTranspose(512, kernel_size=(1, 3, 3), strides=(1, 2, 2), use_bias=512, padding='SAME', activation='relu',
# name='Deconv3D_16'))
# model.add(Conv3D(512, kernel_size=(3, 3, 3), strides=(1, 1, 1), use_bias=512,
# padding='SAME', activation='relu', name='conv3D_2__19'))
# #model.add(Conv3D(512, kernel_size=(3, 3, 3), strides=(1, 1, 1), use_bias=512,
# # padding='SAME', activation='relu', name='conv3D_2__77'))
# model.add(
# Conv3DTranspose(256, kernel_size=(3, 3, 3), strides=(1, 2, 2), use_bias=256, padding='SAME', activation='relu',
# name='Deconv3D_1'))
# model.add(Conv3D(256, kernel_size=(3, 3, 3), strides=(1, 1, 1), use_bias=256,
# padding='SAME', activation='relu', name='conv3D_2__1'))
# model.add(Conv3D(256, kernel_size=(3, 3, 3), strides=(1, 1, 1), use_bias=256, padding='SAME', activation='relu',
# name='conv3D_2__2'))
# model.add(MaxPooling3D(pool_size=(3, 1, 1), strides=(1, 1, 1)))
# #model.add(Conv3D(256, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=256, padding='SAME', activation='relu',
# #name='conv3D_18'))
# #model.add(MaxPooling3D(pool_size=(2, 1, 1), strides=(2, 1, 1)))
# model.add(BatchNormalization())
# # Layer 3
# model.add(
# Conv3DTranspose(128, kernel_size=(1, 3, 3), strides=(1, 2, 2), use_bias=128, padding='SAME', activation='relu',
# name='Deconv3D_2'))
# model.add(Conv3D(128, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=128, padding='SAME', activation='relu',
# name='conv3D__3__1'))
# model.add(Conv3D(128, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=128, padding='SAME', activation='relu',
# name='conv3D__3__2'))
# model.add(BatchNormalization())
# # Layer4
# model.add(
# Conv3DTranspose(64, kernel_size=(1, 3, 3), strides=(1, 2, 2), use_bias=64, padding='SAME', activation='relu',
# name='Deconv3D_3'))
# model.add(Conv3D(64, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=64, padding='SAME', activation='relu',
# name='conv3D__4__1'))
# model.add(Conv3D(64, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=64, padding='SAME', activation='relu',
# name='conv3D__4__2'))
# model.add(BatchNormalization())
# # Layer 5
# model.add(
# Conv3DTranspose(32, kernel_size=(1, 3, 3), strides=(1, 2, 2), use_bias=32, padding='SAME', activation='relu',
# name='Deconv3D_4'))
# model.add(Conv3D(32, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=32, padding='SAME', activation='relu',
# name='conv3D__5__1'))
# model.add(Conv3D(16, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=16, padding='SAME', activation='relu',
# name='conv3D__5__2'))
# #model.add(Conv3D(8, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=8, padding='SAME', activation='relu',
# #name='conv3D2_23'))
# model.add(Conv3D(1, kernel_size=(1, 3, 3), strides=(1, 1, 1), use_bias=1, padding='SAME', activation='sigmoid',
# name='conv3D__5__3'))
# #model.add(BatchNormalization())
Upvotes: 1
Reputation: 2534
I think that the problem is that you are setting the input shape in Theano ordering but you are using Keras with Tensorflow backend and Tensorflow img ordering. In addition the y_train array has to be converted to categorical labels.
Updated code:
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)
Adding this lines should fix it.
Upvotes: 7