Python Theano/Lasagne/Nolearn神经网络图像输入
我正在从事图像分类任务,并决定使用Lasagne+Nolearn作为神经网络原型。 所有标准示例,如MNIST数字分类,都运行良好,但当我尝试处理自己的图像时,会出现问题 我想使用3通道图像,而不是灰度图像。 下面是我试图从图像中获取数组的代码:Python Theano/Lasagne/Nolearn神经网络图像输入,python,machine-learning,theano,deep-learning,Python,Machine Learning,Theano,Deep Learning,我正在从事图像分类任务,并决定使用Lasagne+Nolearn作为神经网络原型。 所有标准示例,如MNIST数字分类,都运行良好,但当我尝试处理自己的图像时,会出现问题 我想使用3通道图像,而不是灰度图像。 下面是我试图从图像中获取数组的代码: img = Image.open(item) img = ImageOps.fit(img, (256, 256), Image.ANTIALIAS) img = np.asarray(img, dtype = 'float64') / 255.
img = Image.open(item)
img = ImageOps.fit(img, (256, 256), Image.ANTIALIAS)
img = np.asarray(img, dtype = 'float64') / 255.
img = img.transpose(2,0,1).reshape(3, 256, 256)
X.append(img)
以下是NN及其配件的代码:
X, y = simple_load("new")
X = np.array(X)
y = np.array(y)
net1 = NeuralNet(
layers=[ # three layers: one hidden layer
('input', layers.InputLayer),
('hidden', layers.DenseLayer),
('output', layers.DenseLayer),
],
# layer parameters:
input_shape=(None, 65536), # 96x96 input pixels per batch
hidden_num_units=100, # number of units in hidden layer
output_nonlinearity=None, # output layer uses identity function
output_num_units=len(y), # 30 target values
# optimization method:
update=nesterov_momentum,
update_learning_rate=0.01,
update_momentum=0.9,
regression=True, # flag to indicate we're dealing with regression problem
max_epochs=400, # we want to train this many epochs
verbose=1,
)
net1.fit(X, y)
我收到的例外情况如下:
Traceback (most recent call last):
File "las_mnist.py", line 39, in <module>
net1.fit(X[i], y[i])
File "/usr/local/lib/python2.7/dist-packages/nolearn/lasagne.py", line 266, in fit
self.train_loop(X, y)
File "/usr/local/lib/python2.7/dist-packages/nolearn/lasagne.py", line 273, in train_loop
X, y, self.eval_size)
File "/usr/local/lib/python2.7/dist-packages/nolearn/lasagne.py", line 377, in train_test_split
kf = KFold(y.shape[0], round(1. / eval_size))
IndexError: tuple index out of range
回溯(最近一次呼叫最后一次):
文件“las_mnist.py”,第39行,在
net1.fit(X[i],y[i])
文件“/usr/local/lib/python2.7/dist packages/nolearn/lasagne.py”,第266行,适合
自循环列车(X,y)
文件“/usr/local/lib/python2.7/dist packages/nolearn/lasagne.py”,第273行,列车循环中
十、 y,自我评估(尺寸)
文件“/usr/local/lib/python2.7/dist packages/nolearn/lasagne.py”,第377行,列车内测试
kf=KFold(y形[0],圆形(1./eval_尺寸))
索引器错误:元组索引超出范围
那么,您用哪种格式向网络“提供”图像数据?
谢谢你的回答或任何提示 我也在lasagne用户论坛上问过,Oliver Duerr在代码示例方面帮了我很多忙:
如果要进行分类,则需要修改以下几项:
回归=True
。要进行分类,请删除此行X, y = simple_load("new")
X = np.array(X)
y = np.array(y)
net1 = NeuralNet(
layers=[ # three layers: one hidden layer
('input', layers.InputLayer),
('hidden', layers.DenseLayer),
('output', layers.DenseLayer),
],
# layer parameters:
input_shape=(None, 3, 256, 256), # TODO: change this
hidden_num_units=100, # number of units in hidden layer
output_nonlinearity=lasagne.nonlinearities.softmax, # TODO: change this
output_num_units=len(y), # 30 target values
# optimization method:
update=nesterov_momentum,
update_learning_rate=0.01,
update_momentum=0.9,
max_epochs=400, # we want to train this many epochs
verbose=1,