尝试使用自己的数据集(稍微修改一下)使神经网络用于人脸识别。
尝试使用自己的数据集(稍微修改一下)使神经网络用于人脸识别。
提问于 2016-04-11 18:42:10
我正在做一个基本的千层面例子：https://github.com/Lasagne/Lasagne/blob/master/examples/mnist.py
我把它和另一个类似的例子结合起来稍微修改了一下。
我试图运行CNN模型，在这里，我增加了一些额外的投入，CNN的发展，但它不应该有任何不同。还将示例中输入层的默认值28更改为60 (用于高度和宽度)，在代码后面将使用类，但代码“挂起”在最后一条网络行上，这意味着代码仍在运行，但什么也没有发生。运行代码时输出。在主循环中将input_var定义为这样：
input_var = T.tensor4('input_var')其余代码：
def build_cnn(classes, height, width, input_var=None):
print("Input layer, with height: {}, width: {} and input var: {}".format(height, width, input_var))
network = lasagne.layers.InputLayer(shape = (None, 1, height, width),
input_var=input_var)
print("Convolutional layer with 32 kernels of size 5x5")
network = lasagne.layers.Conv2DLayer(network,
num_filters = 32,
filter_size = (5, 5),
nonlinearity = lasagne.nonlinearities.rectify,
W = lasagne.init.HeNormal(gain = 'relu')) 编辑：，好的，根据我到目前为止尝试过的内容，问题似乎是我自己的数据集。我已经对数据集进行了调整，以匹配MNIST数据集。X_train有形状图像，通道，高度，宽度。其中通道=1和高度，宽度= 60。检索这些代码的代码是：
def load_images():
dataset_path = os.path.abspath("C:/Users/laende/Dropbox/Skole UiS/4. semester/Master/Master/data/test_database")
[bilder, label, names] = read_images1(dataset_path, (28, 28))
label = np.array(label)
bilder = bilder / np.float32(256)
bilder = bilder[:, newaxis, :, :]
X_train1, X_test1, Y_train1, Y_test1 = train_test_split(bilder, label, test_size = 0.2)
list_of_labels = list(xrange(max(label) + 1))
classes = len(list_of_labels)
return X_train1, X_test1, Y_train1, Y_test1, classes其中read_images1是：
def read_images1(path, sz = None, channel = None):
c = 0
X = []
y = []
folder_names = []
for dirname, dirnames, filenames, in os.walk(path):
for subdirname in dirnames:
subject_path = os.path.join(dirname, subdirname)
folder_names.append(subdirname)
for filename in os.listdir(subject_path):
try:
im = cv2.imread(os.path.join(subject_path, filename), cv2.IMREAD_GRAYSCALE)
if (sz is not None):
im = cv2.resize(im, sz)
X.append(np.asarray(im, dtype = np.uint8))
y.append(c)
except IOError, (errno, strerror):
print "I/O error ({0]): {1}".format(errno, strerror)
except:
print "unexpected error:", sys.exc_info()[0]
raise
c = c + 1
return [X, y, folder_names]main中运行的代码：
def main(model='mlp', num_epochs=100):
# Load the dataset
print("Loading data...")
mnist = 1
if mnist == 1:
classes = 10
X_train, y_train, X_val, y_val, X_test, y_test = load_dataset()
dataset = {
'train': {'X': X_train, 'y': y_train},
'test': {'X': X_test, 'y': y_test}}
shape = dataset['train']['X'][0].shape
else:
X_train, X_test, y_train, y_test, classes = load_images()
dataset = {
'train': {'X': X_train, 'y': y_train},
'test': {'X': X_test, 'y': y_test}}
shape = dataset['train']['X'][0].shape
input_var = T.tensor4('inputs')
target_var = T.ivector('targets')
print("Building model and compiling functions...")
if model == 'mlp':
network = build_mlp(height=int(shape[1]),
width=int(shape[2]),
channel=int(shape[0]),
classes=int(classes),
input_var=input_var)如果mnist =1(大体上)代码运行良好，那么如果我尝试使用我自己的数据集，它就会卡在build_mlp中(类似于cnn的原始问题)：
def build_mlp(classes, channel, height, width, input_var=None):
neurons = int(height * width)
network = lasagne.layers.InputLayer(shape = (None, channel, height, width),
input_var=input_var)
network = lasagne.layers.DropoutLayer(network, p = 0.2)
#Code gets stuck on this point, running forever, doing nothing.
#No error messages received either.
network = lasagne.layers.DenseLayer(
network,
num_units = neurons,
nonlinearity = lasagne.nonlinearities.rectify,
W = lasagne.init.GlorotUniform())编辑2:在与此进行了一段时间的斗争之后，我发现在read_images1()中进行的图像大小调整导致了问题：
def read_images1(path, sz = None, channel = None):
c = 0
X = []
y = []
folder_names = []
for dirname, dirnames, filenames, in os.walk(path):
for subdirname in dirnames:
subject_path = os.path.join(dirname, subdirname)
folder_names.append(subdirname)
for filename in os.listdir(subject_path):
try:
im = cv2.imread(os.path.join(subject_path, filename), cv2.IMREAD_GRAYSCALE)
#This part caused the problems.
if (sz is not None):
im = cv2.resize(im, sz)
X.append(np.asarray(im, dtype = np.uint8))
y.append(c)
except IOError, (errno, strerror):
print "I/O error ({0]): {1}".format(errno, strerror)
except:
print "unexpected error:", sys.exc_info()[0]
raise
c = c + 1
return [X, y, folder_names]如果我没有传递任何调整大小并使用文件夹中的默认图像大小，神经网络就能够编译。有人知道为什么吗？我更新了read_images1()如下：
def read_images1(path, sz = None, na = False):
"""
:param path: sti til mappe med underliggende mapper tilhørende personer.
:param sz: Størrelse på bildefilene
:return: returnerer liste av bilder, labels og navn
"""
c = 0
X = []
y = []
folder_names = []
for dirname, dirnames, filenames, in os.walk(path):
for subdirname in dirnames:
subject_path = os.path.join(dirname, subdirname)
folder_names.append(subdirname)
for filename in os.listdir(subject_path):
try:
im = cv2.imread(os.path.join(subject_path, filename), cv2.IMREAD_GRAYSCALE)
if (sz is not None):
im = cv2.resize(im, dsize=sz, interpolation = cv2.INTER_LANCZOS4)
if (na == True):
im = im[newaxis, :, :]
X.append(np.asarray(im, dtype = np.uint8))
y.append(c)
except IOError, (errno, strerror):
print "I/O error ({0]): {1}".format(errno, strerror)
except:
print "unexpected error:", sys.exc_info()[0]
raise
c = c + 1
return [X, y, folder_names] 如果我使用sz = None和na = True运行程序，那么它就能工作。如果给出sz参数的任何大小，代码就会被卡住，试图再次编译神经网络。
Stack Overflow用户
回答已采纳
发布于 2016-04-15 19:15:34
好吧，我想我可以在这里看到一些问题，不知道你遇到的是哪一个.
- 在
read_images1()中，X是numpy数组的python列表。它在哪里被转换成一个numpy数组？尝试添加X = numpy.asarray(X)。你也需要重塑它到(n_images，n_channels，宽度，高度)，在那里，我假设n_channels=1的灰度。该网络期望4D输入，而不是3D。 - 这个代码
list_of_labels = list(xrange(max(label) + 1)); classes = len(list_of_labels)假设标签是从0到N的序列号，是吗？ - 您的
build_mlp(classes, height, width, input_var=None)与最初的示例build_mlp(input_var=None)非常不同。最初的例子显然有效，所以任何错误都与差异有关。最大的区别之一是，您一直将变量赋值给相同的变量，比如这个network = lasagne.layers.DenseLayer(network, ...)，其中原始的每个层l_hid1 = lasagne.layers.DenseLayer(l_in_drop, ...)都有不同的变量。 - 另外，如果它在
build_mlp()期间挂起，那么问题显然不在于如何读取图像。尝试在图像中使用原始版本的build_mlp()。试着自己运行它。跳过图像读取，只需使用常量参数调用build_mlp()。
页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/36556704
复制相关文章
相似问题
腾讯云开发者
